{"object":"list","data":[{"id":"glm-5-3","object":"model","created":1786665600,"owned_by":"zhipu","display_name":"GLM 5.3","author":"zhipu","provider":"zhipu","description":"Coding and agentic model with a 1M token context, 128K output, always-on reasoning at low, high, or max effort, native web search, and tool calling.","modality":"text","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","function_calling","web_search"],"aliases":["glm-5.3","zai/glm-5.3","zhipu/glm-5.3"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1048576,"context_length":1048576,"max_output_tokens":131072,"model_released_at":"2026-08-14","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum number of output tokens to generate.","required":false,"metadata":{"ui":{"control":"slider","section":"Generation"}},"default":65536,"min":1,"max":131072},{"name":"temperature","label":"Temperature","type":"number","description":"Controls randomness. Lower values make responses more deterministic.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":1,"min":0,"max":1},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling cutoff.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":0.95,"min":0.01,"max":1},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"This model always reasons and cannot be turned off. low is lightweight, high is enhanced, and max is deep reasoning. max is recommended for complex coding.","required":false,"metadata":{"ui":{"control":"segmented","section":"Reasoning"}},"default":"max","options":["low","high","max"]},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens.","required":false,"metadata":{"ui":{"control":"toggle","section":"Reasoning"}},"default":false},{"name":"do_sample","label":"Sampling","type":"boolean","description":"Enable sampling. Turn off for greedy deterministic output (temperature and top_p are ignored).","required":false,"metadata":{"ui":{"control":"toggle","section":"Generation"}},"default":true},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable built-in web search. Adds $0.033 per request when used.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"search_recency_filter","label":"Search Recency","type":"enum","description":"Limit web search results to a recency window.","required":false,"metadata":{"ui":{"control":"segmented","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":"noLimit","options":["oneDay","oneWeek","oneMonth","oneYear","noLimit"]},{"name":"count","label":"Search Results","type":"number","description":"Number of web search results to retrieve when web search is enabled.","required":false,"metadata":{"ui":{"control":"slider","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":10,"min":1,"max":50},{"name":"search_domain_filter","label":"Search Domain","type":"string","description":"Restrict web search to a specific domain.","required":false,"metadata":{"ui":{"control":"text","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}}},{"name":"search_prompt","label":"Search Prompt","type":"string","description":"Optional prompt used to summarize retrieved web search results.","required":false,"metadata":{"ui":{"control":"text","section":"Tools","hide_in_playground":true}}},{"name":"search_result","label":"Return Search Metadata","type":"boolean","description":"Return web search result metadata in the response when web search is enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":true},{"name":"tool_stream","label":"Tool Stream","type":"boolean","description":"Stream function-call arguments incrementally when streaming.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function calling tool definitions.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}},"default":[]},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible tool choice control.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}}},{"name":"stop","label":"Stop","type":"string","description":"Optional stop sequences (up to 4).","required":false,"metadata":{"ui":{"control":"tags","section":"Generation","hide_in_playground":true},"control":"stop-sequences"}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"ui":{"control":"json","section":"Structured Output","hide_in_playground":true},"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/glm-5-3:generateContent"],"pricing":{"prompt":"0.0000014","completion":"0.0000044","image":"0","request":"0","input_cache_read":"0.0000014"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.40"},{"spec":"per 1M generated tokens","label":"Output","value":"$4.40"},{"spec":"per request","label":"Web search","value":"$0.033"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.4","label":"Input"},{"unit":"1m_tokens","usd":"4.4","label":"Output"},{"unit":"request","usd":"0.033","label":"Web search"}],"limits":null,"notes":"This model always reasons and cannot be run with thinking disabled. Reasoning effort accepts low, high, or max, with max recommended for complex coding; a request that asks for a different effort, or for thinking to be turned off, is served at the nearest supported level. Built-in web search adds a per-request fee when used. Structured output is JSON mode, so describe the fields you want in your prompt rather than supplying a JSON Schema.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=glm-5-3","api_url":"https://docs.empiriolabs.ai/models/glm-5-3","logo":"https://media.empiriolabs.ai/model-logos/glm.png","status":"available"},{"id":"kling-3-0-turbo","object":"model","created":1781654400,"owned_by":"kling","display_name":"Kling 3.0 Turbo","author":"kling","provider":"kling","description":"Text-to-video and image-to-video with synchronized native audio, at 720p or 1080p for 3 to 15 seconds, with aspect ratio and prompt control.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image"],"output_modalities":["video"],"features":["text_to_video","image_to_video","audio","video_generation"],"aliases":["kling-3.0-turbo","kling/kling-3-0-turbo"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-06-17","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Describe the video (text-to-video) or the motion to apply to the source image (image-to-video).","required":true,"metadata":{}},{"name":"image","label":"Image","type":"string","description":"Optional source image (URL or base64). When provided, the request is image-to-video; when omitted, text-to-video.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution. 720p renders faster; 1080p is higher fidelity.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"720p","options":["720p","1080p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Aspect ratio of the output. Used for text-to-video; image-to-video follows the source image.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"16:9","options":["16:9","9:16","1:1"]},{"name":"duration","label":"Duration","type":"number","description":"Video length in seconds.","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":5,"min":3,"max":15},{"name":"watermark","label":"Watermark","type":"boolean","description":"Add a watermark to the generated video. Off by default.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"720p","value":"$0.18"},{"spec":"per second","label":"1080p","value":"$0.225"}],"unit_pricing":[{"unit":"second","usd":"0.18","label":"720p"},{"unit":"second","usd":"0.225","label":"1080p"}],"limits":{"note":"Text-to-video and image-to-video with synchronized native audio, up to 1080p. Workflow auto-detected: a prompt alone is text-to-video, adding a source image is image-to-video.\n\n**Prompting**\n\n- There is no separate negative prompt. To steer away from unwanted elements, describe them in your prompt, for example: \"a calm forest at dawn, avoid blurry motion, no on-screen text\".\n\n**Multi-shot**\n\n- Generate up to 6 sequential shots by formatting the prompt like this (shot durations must sum to the total duration):\n\n```\nshot 1, <seconds>, <description>; shot 2, <seconds>, <description>;\n```\n\n**Input limits**\n\n- Prompt up to 3,072 characters. Resolution 720p or 1080p. Duration 3 to 15 seconds. Aspect ratio 16:9, 9:16, or 1:1 for text-to-video (image-to-video follows the source image).\n- Image inputs: JPEG or PNG, at least 300px per side, aspect within 1:2.5 to 2.5:1, up to 50 MB."},"notes":"Text-to-video and image-to-video with synchronized native audio, up to 1080p. Workflow auto-detected: a prompt alone is text-to-video, adding a source image is image-to-video.\n\n**Prompting**\n\n- There is no separate negative prompt. To steer away from unwanted elements, describe them in your prompt, for example: \"a calm forest at dawn, avoid blurry motion, no on-screen text\".\n\n**Multi-shot**\n\n- Generate up to 6 sequential shots by formatting the prompt like this (shot durations must sum to the total duration):\n\n```\nshot 1, <seconds>, <description>; shot 2, <seconds>, <description>;\n```\n\n**Input limits**\n\n- Prompt up to 3,072 characters. Resolution 720p or 1080p. Duration 3 to 15 seconds. Aspect ratio 16:9, 9:16, or 1:1 for text-to-video (image-to-video follows the source image).\n- Image inputs: JPEG or PNG, at least 300px per side, aspect within 1:2.5 to 2.5:1, up to 50 MB.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=kling-3-0-turbo","api_url":"https://docs.empiriolabs.ai/models/kling-3-0-turbo","logo":"https://media.empiriolabs.ai/model-logos/kling-3-0-turbo.png","status":"available"},{"id":"glm-5-3-flash","object":"model","created":1787702400,"owned_by":"zhipu","display_name":"GLM 5.3 Flash","author":"zhipu","provider":"zhipu","description":"Natively multimodal flash model with a 1M token context, image and video input, always-on reasoning, native web search, and tool calling.","modality":"text","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video","file"],"input_modalities":["text","image","video","file"],"output_modalities":["text"],"features":["reasoning","vision","video_understanding","document_understanding","function_calling","web_search"],"aliases":["glm-5.3-flash","zai/glm-5.3-flash","zhipu/glm-5.3-flash"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1048576,"context_length":1048576,"max_output_tokens":131072,"model_released_at":"2026-08-26","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum number of output tokens to generate.","required":false,"metadata":{"ui":{"control":"slider","section":"Generation"}},"default":65536,"min":1,"max":131072},{"name":"temperature","label":"Temperature","type":"number","description":"Controls randomness. Lower values make responses more deterministic.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":1,"min":0,"max":1},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling cutoff.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":0.95,"min":0.01,"max":1},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"This model always reasons and cannot be turned off. low is lightweight, high is enhanced, and max is deep reasoning. max is recommended for complex coding.","required":false,"metadata":{"ui":{"control":"segmented","section":"Reasoning"}},"default":"max","options":["low","high","max"]},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens.","required":false,"metadata":{"ui":{"control":"toggle","section":"Reasoning"}},"default":false},{"name":"do_sample","label":"Sampling","type":"boolean","description":"Enable sampling. Turn off for greedy deterministic output (temperature and top_p are ignored).","required":false,"metadata":{"ui":{"control":"toggle","section":"Generation"}},"default":true},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable built-in web search. Adds $0.033 per request when used.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"search_recency_filter","label":"Search Recency","type":"enum","description":"Limit web search results to a recency window.","required":false,"metadata":{"ui":{"control":"segmented","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":"noLimit","options":["oneDay","oneWeek","oneMonth","oneYear","noLimit"]},{"name":"count","label":"Search Results","type":"number","description":"Number of web search results to retrieve when web search is enabled.","required":false,"metadata":{"ui":{"control":"slider","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":10,"min":1,"max":50},{"name":"search_domain_filter","label":"Search Domain","type":"string","description":"Restrict web search to a specific domain.","required":false,"metadata":{"ui":{"control":"text","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}}},{"name":"search_prompt","label":"Search Prompt","type":"string","description":"Optional prompt used to summarize retrieved web search results.","required":false,"metadata":{"ui":{"control":"text","section":"Tools","hide_in_playground":true}}},{"name":"search_result","label":"Return Search Metadata","type":"boolean","description":"Return web search result metadata in the response when web search is enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":true},{"name":"tool_stream","label":"Tool Stream","type":"boolean","description":"Stream function-call arguments incrementally when streaming.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function calling tool definitions.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}},"default":[]},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible tool choice control.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}}},{"name":"stop","label":"Stop","type":"string","description":"Optional stop sequences (up to 4).","required":false,"metadata":{"ui":{"control":"tags","section":"Generation","hide_in_playground":true},"control":"stop-sequences"}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"ui":{"control":"json","section":"Structured Output","hide_in_playground":true},"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/glm-5-3-flash:generateContent"],"pricing":{"prompt":"0.000000075","completion":"0.00000025","image":"0","request":"0","input_cache_read":"0.000000075"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.075"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.25"},{"spec":"per request","label":"Web search","value":"$0.033"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.075","label":"Input"},{"unit":"1m_tokens","usd":"0.25","label":"Output"},{"unit":"request","usd":"0.033","label":"Web search"}],"limits":null,"notes":"This model always reasons and cannot be run with thinking disabled. Reasoning effort accepts low, high, or max, with max recommended for complex coding; a request that asks for a different effort, or for thinking to be turned off, is served at the nearest supported level. Images and videos are passed as URLs (recommended) or base64 data URLs. Built-in web search adds a per-request fee when used. Structured output is JSON mode, so describe the fields you want in your prompt rather than supplying a JSON Schema.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=glm-5-3-flash","api_url":"https://docs.empiriolabs.ai/models/glm-5-3-flash","logo":"https://media.empiriolabs.ai/model-logos/glm.png","status":"available"},{"id":"glm-5-2","object":"model","created":1781568000,"owned_by":"zhipu","display_name":"GLM 5.2","author":"zhipu","provider":"zhipu","description":"Reasoning and coding model with a 1M token context, 128K output, adjustable reasoning effort, native web search, and tool calling.","modality":"text","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","function_calling","web_search"],"aliases":["glm-5.2","zai/glm-5.2","zhipu/glm-5.2"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1048576,"context_length":1048576,"max_output_tokens":131072,"model_released_at":"2026-06-16","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum number of output tokens to generate.","required":false,"metadata":{"ui":{"control":"slider","section":"Generation"}},"default":65536,"min":1,"max":131072},{"name":"temperature","label":"Temperature","type":"number","description":"Controls randomness. Lower values make responses more deterministic.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":1,"min":0,"max":1},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling cutoff.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":0.95,"min":0.01,"max":1},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"GLM-5.2 reasoning effort. none disables thinking; minimal through max set how hard the model reasons before answering. max is recommended for complex coding.","required":false,"metadata":{"ui":{"control":"segmented","section":"Reasoning"}},"default":"max","options":["none","minimal","low","medium","high","xhigh","max"]},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Allow the model to reason before answering. Turn off for the lowest-latency replies or strict structured output.","required":false,"metadata":{"ui":{"control":"toggle","section":"Reasoning"}},"default":true},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens.","required":false,"metadata":{"ui":{"control":"toggle","section":"Reasoning"}},"default":false},{"name":"do_sample","label":"Sampling","type":"boolean","description":"Enable sampling. Turn off for greedy deterministic output (temperature and top_p are ignored).","required":false,"metadata":{"ui":{"control":"toggle","section":"Generation"}},"default":true},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable built-in web search. Adds $0.033 per request when used.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"search_recency_filter","label":"Search Recency","type":"enum","description":"Limit web search results to a recency window.","required":false,"metadata":{"ui":{"control":"segmented","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":"noLimit","options":["oneDay","oneWeek","oneMonth","oneYear","noLimit"]},{"name":"count","label":"Search Results","type":"number","description":"Number of web search results to retrieve when web search is enabled.","required":false,"metadata":{"ui":{"control":"slider","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":10,"min":1,"max":50},{"name":"search_domain_filter","label":"Search Domain","type":"string","description":"Restrict web search to a specific domain.","required":false,"metadata":{"ui":{"control":"text","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}}},{"name":"search_prompt","label":"Search Prompt","type":"string","description":"Optional prompt used to summarize retrieved web search results.","required":false,"metadata":{"ui":{"control":"text","section":"Tools","hide_in_playground":true}}},{"name":"search_result","label":"Return Search Metadata","type":"boolean","description":"Return web search result metadata in the response when web search is enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":true},{"name":"tool_stream","label":"Tool Stream","type":"boolean","description":"Stream function-call arguments incrementally when streaming.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function calling tool definitions.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}},"default":[]},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible tool choice control.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}}},{"name":"stop","label":"Stop","type":"string","description":"Optional stop sequences (up to 4).","required":false,"metadata":{"ui":{"control":"tags","section":"Generation","hide_in_playground":true},"control":"stop-sequences"}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"ui":{"control":"json","section":"Structured Output","hide_in_playground":true},"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/glm-5-2:generateContent"],"pricing":{"prompt":"0.0000014","completion":"0.0000044","image":"0","request":"0","input_cache_read":"0.0000014"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.40"},{"spec":"per 1M generated tokens","label":"Output","value":"$4.40"},{"spec":"per request","label":"Web search","value":"$0.033"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.4","label":"Input"},{"unit":"1m_tokens","usd":"4.4","label":"Output"},{"unit":"request","usd":"0.033","label":"Web search"}],"limits":null,"notes":"Reasoning effort is adjustable from minimal to max, with max recommended for complex coding. Built-in web search adds a per-request fee when used. Run structured output with thinking disabled.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=glm-5-2","api_url":"https://docs.empiriolabs.ai/models/glm-5-2","logo":"https://media.empiriolabs.ai/model-logos/glm.png","status":"available"},{"id":"kimi-k3","object":"model","created":1784073600,"owned_by":"moonshot","display_name":"Kimi K3","author":"moonshot","provider":"moonshot","description":"Kimi K3 is Moonshot's flagship reasoning model with a 1M token context, always-on thinking, native web search, and text, image, and video inputs.","modality":"multimodal","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","function_calling","multimodal","agentic_coding","web_search"],"aliases":["moonshotai/kimi-k3"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1048576,"context_length":1048576,"max_output_tokens":131072,"model_released_at":"2026-07-15","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. Reasoning tokens count toward this limit.","required":false,"metadata":{},"default":131072,"min":1,"max":1048576},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Kimi K3 reasoning effort. Thinking is always on. Higher effort spends more reasoning tokens before answering. Max is recommended and the default.","required":false,"metadata":{"ui":{"control":"segmented","section":"Reasoning"}},"default":"max","options":["low","high","max"]},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.015 to the request cost for each invoked web search call.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.015}},"default":false},{"name":"max_tool_calls","label":"Max Web Searches","type":"number","description":"Max number of web searches the model can run in one request. Each search is billed separately.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true},"clear_when_hidden":true},"default":5,"min":1,"max":20},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/kimi-k3:generateContent"],"pricing":{"prompt":"0.000003","completion":"0.000015","image":"0","request":"0","input_cache_read":"0.000003"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$3.00"},{"spec":"per 1M generated tokens","label":"Output","value":"$15.00"},{"spec":"per call when invoked","label":"Web search","value":"$0.015"}],"unit_pricing":[{"unit":"1m_tokens","usd":"3","label":"Input"},{"unit":"1m_tokens","usd":"15","label":"Output"},{"unit":"call","usd":"0.015","label":"Web search"}],"limits":{"note":"Supports text, image, and video inputs with a 1M token context, function calling, JSON schema structured output, and built-in web search at $0.015 per invoked call. Thinking is always on; reasoning depth is tunable with the reasoning_effort control (max is recommended) and reasoning tokens are billed as output tokens. Temperature and other sampling settings are fixed by the model service. Multi-step function calling through the API must replay the assistant message with its reasoning_content field intact.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. Tool counts are already factored into `cost_usd` and are surfaced for transparency."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=kimi-k3","api_url":"https://docs.empiriolabs.ai/models/kimi-k3","logo":"https://media.empiriolabs.ai/model-logos/kimi.png","status":"available"},{"id":"muse-spark-1-2","object":"model","created":1785888000,"owned_by":"meta","display_name":"Muse Spark 1.2","author":"meta","provider":"meta","description":"Meta's updated frontier reasoning model with a 1,048,576-token context, image, video, audio, and PDF understanding, web search, and tool calling.","modality":"multimodal","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video","audio","document"],"input_modalities":["text","image","video","audio","document"],"output_modalities":["text"],"features":["reasoning","multimodal","video_understanding","function_calling","structured_output","web_search","cache","audio_input","document_understanding"],"aliases":["muse-spark-1.2","meta/muse-spark-1-2","meta/muse-spark-1.2"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1048576,"context_length":1048576,"max_output_tokens":131072,"model_released_at":"2026-08-05","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum number of output tokens to generate. Reasoning tokens count against this budget.","required":false,"metadata":{"ui":{"control":"slider","section":"Generation"}},"default":16384,"min":1,"max":131072},{"name":"temperature","label":"Temperature","type":"number","description":"Controls randomness. Lower values make responses more deterministic.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":1,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling cutoff.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":1,"min":0.01,"max":1},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalizes tokens that already appeared, encouraging new topics. Not applied when web search is on.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":0,"min":-2,"max":2},{"name":"frequency_penalty","label":"Frequency Penalty","type":"number","description":"Penalizes frequent tokens, reducing repetition. Not applied when web search is on.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":0,"min":-2,"max":2},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Not applied when web search is on.","required":false,"metadata":{"ui":{"section":"Generation","hide_in_playground":true}}},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning is always on; this sets how much effort the model spends before answering. Higher effort uses more reasoning tokens. Reasoning text is not returned in responses.","required":false,"metadata":{"ui":{"control":"segmented","section":"Reasoning"}},"default":"medium","options":["minimal","low","medium","high","xhigh"]},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable built-in web search with cited sources. Adds $0.00825 per executed search query; a single request can run more than one search.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function and custom tool definitions. On /v1/responses, tool_search and defer_loading can discover deferred tools.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}},"default":[]},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible tool choice control. This model supports auto and none.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}}},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow the model to request multiple function tools in one response. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools","hide_in_playground":true}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return structured JSON output. JSON mode returns any valid JSON object; JSON Schema mode enforces an exact schema.","required":false,"metadata":{"ui":{"control":"json","section":"Structured Output","hide_in_playground":true},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/muse-spark-1-2:generateContent"],"pricing":{"prompt":"0.00000125","completion":"0.00000425","image":"0","request":"0","input_cache_read":"0.000001"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.25"},{"spec":"per 1M generated tokens","label":"Output","value":"$4.25"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$1.00"},{"spec":"per search query","label":"Web search","value":"$0.00825"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.25","label":"Input"},{"unit":"1m_tokens","usd":"4.25","label":"Output"},{"unit":"1m_tokens","usd":"1","label":"Implicit cache read"},{"unit":"search","usd":"0.00825","label":"Web search"}],"limits":{"note":"Reasoning is always on and cannot be disabled. Reasoning stays internal, and reasoning tokens are billed as output tokens and count against max_tokens. reasoning_effort accepts minimal through xhigh. Text, image, MP4 video, MP3/WAV audio, and PDF inputs are supported; up to 50 images can be attached. PDFs use text from the first 100 pages and page images from the first 50 pages. Built-in web search adds $0.00825 per executed search query and reports the count in usage.tool_usage. OpenAI Responses requests also support custom tools and deferred tool search. tool_choice supports auto and none. Prompts and completions sent to this Standard checkpoint are not used by Meta to train its models.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape. Exact field names, units, and which tools appear can vary by tool:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3}\n}\n```\n\nThe tool counts are already factored into `cost_usd` and are surfaced so you can audit per-tool billing. The field is omitted when no billed tool was invoked."},"notes":"Reasoning is always on and cannot be disabled. Reasoning stays internal, and reasoning tokens are billed as output tokens and count against max_tokens. reasoning_effort accepts minimal through xhigh. Text, image, MP4 video, MP3/WAV audio, and PDF inputs are supported; up to 50 images can be attached. PDFs use text from the first 100 pages and page images from the first 50 pages. Built-in web search adds $0.00825 per executed search query and reports the count in usage.tool_usage. OpenAI Responses requests also support custom tools and deferred tool search. tool_choice supports auto and none. Prompts and completions sent to this Standard checkpoint are not used by Meta to train its models.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=muse-spark-1-2","api_url":"https://docs.empiriolabs.ai/models/muse-spark-1-2","logo":"https://media.empiriolabs.ai/model-logos/muse-spark-1-1.png","status":"available"},{"id":"kimi-k3-1-pro","object":"model","created":1792713600,"owned_by":"moonshot","display_name":"Kimi K3.1 Pro","author":"moonshot","provider":"moonshot","description":"Moonshot's flagship reasoning model for long coding and agent work, with a 1M token context, image input, and web search.","modality":"multimodal","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image"],"input_modalities":["text","image"],"output_modalities":["text"],"features":["reasoning","function_calling","multimodal","vision","agentic_coding","cache"],"aliases":["kimi-k3.1-pro","moonshotai/kimi-k3.1-pro"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1048576,"context_length":1048576,"max_output_tokens":131072,"model_released_at":"2026-10-23","is_new":true,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. Reasoning tokens count toward this limit.","required":false,"metadata":{},"default":131072,"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. Turning it off lowers output quality.","required":false,"metadata":{"ui":{"control":"toggle","section":"Reasoning"}},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Kimi K3.1 Pro reasoning effort. Higher effort spends more reasoning tokens before answering. Max is recommended and the default.","required":false,"metadata":{"ui":{"control":"segmented","section":"Reasoning"},"hidden_when":{"op":"eq","field":"enable_thinking","value":false},"clear_when_hidden":true},"default":"max","options":["low","medium","high","max"]},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/kimi-k3-1-pro:generateContent"],"pricing":{"prompt":"0.000002","completion":"0.00001","image":"0","request":"0","input_cache_read":"0.000000184"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$2.00"},{"spec":"per 1M generated tokens","label":"Output","value":"$10.00"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.184"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"2","label":"Input"},{"unit":"1m_tokens","usd":"10","label":"Output"},{"unit":"1m_tokens","usd":"0.184","label":"Implicit cache read"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Supports text and image inputs with a 1M token context, function calling, and JSON schema structured output. Linkup web search is available through web_search_linkup and adds $0.013 per call when invoked. Thinking is on by default: set its depth with reasoning_effort (max is the default), or turn it off with enable_thinking, which lowers output quality. Reasoning tokens are billed as output tokens. Stop strings apply to reasoning as well as the answer, so a stop string that appears in the reasoning ends the reply early. Temperature and other sampling settings are fixed by the model service."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=kimi-k3-1-pro","api_url":"https://docs.empiriolabs.ai/models/kimi-k3-1-pro","logo":"https://media.empiriolabs.ai/model-logos/kimi.png","status":"available"},{"id":"kimi-k2-7-code","object":"model","created":1781568000,"owned_by":"moonshot","display_name":"Kimi K2.7 Code","author":"moonshot","provider":"moonshot","description":"Kimi K2.7 Code is Moonshot's trillion-parameter agentic coding model with 256K context, always-on reasoning, and text, image, and video inputs.","modality":"multimodal","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","function_calling","multimodal","agentic_coding","web_search"],"aliases":["kimi-k2.7-code","moonshotai/kimi-k2.7-code"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":262144,"context_length":262144,"max_output_tokens":131072,"model_released_at":"2026-06-16","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. Reasoning tokens count toward this limit.","required":false,"metadata":{},"default":32768,"min":1,"max":262144},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.015 to the request cost for each invoked web search call.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.015}},"default":false},{"name":"max_tool_calls","label":"Max Web Searches","type":"number","description":"Max number of web searches the model can run in one request. Each search is billed separately.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true},"clear_when_hidden":true},"default":5,"min":1,"max":20},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/kimi-k2-7-code:generateContent"],"pricing":{"prompt":"0.00000095","completion":"0.000004","image":"0","request":"0","input_cache_read":"0.00000095"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.95"},{"spec":"per 1M generated tokens","label":"Output","value":"$4.00"},{"spec":"per call when invoked","label":"Web search","value":"$0.015"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.95","label":"Input"},{"unit":"1m_tokens","usd":"4","label":"Output"},{"unit":"call","usd":"0.015","label":"Web search"}],"limits":{"note":"Supports text, image, and video inputs with 256K context, function calling, JSON mode structured output, and built-in web search at $0.015 per invoked call. Thinking is always on and cannot be disabled; reasoning tokens are billed as output tokens. Temperature and other sampling overrides are ignored because the model service uses fixed sampling settings. Multi-step function calling through the API must replay the assistant message with its reasoning_content field intact.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. Tool counts are already factored into `cost_usd` and are surfaced for transparency."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=kimi-k2-7-code","api_url":"https://docs.empiriolabs.ai/models/kimi-k2-7-code","logo":"https://media.empiriolabs.ai/model-logos/kimi.png","status":"available"},{"id":"muse-spark-1-1","object":"model","created":1783555200,"owned_by":"meta","display_name":"Muse Spark 1.1","author":"meta","provider":"meta","description":"Meta frontier reasoning model with a 1,048,576-token context plus image, video, audio, and PDF understanding, web search, and tool calling.","modality":"multimodal","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video","audio","document"],"input_modalities":["text","image","video","audio","document"],"output_modalities":["text"],"features":["reasoning","multimodal","video_understanding","function_calling","structured_output","web_search","cache","audio_input","document_understanding"],"aliases":["muse-spark-1.1","meta/muse-spark-1-1","meta/muse-spark-1.1"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1048576,"context_length":1048576,"max_output_tokens":131072,"model_released_at":"2026-07-09","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum number of output tokens to generate. Reasoning tokens count against this budget.","required":false,"metadata":{"ui":{"control":"slider","section":"Generation"}},"default":16384,"min":1,"max":131072},{"name":"temperature","label":"Temperature","type":"number","description":"Controls randomness. Lower values make responses more deterministic.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":1,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling cutoff.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":1,"min":0.01,"max":1},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalizes tokens that already appeared, encouraging new topics. Not applied when web search is on.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":0,"min":-2,"max":2},{"name":"frequency_penalty","label":"Frequency Penalty","type":"number","description":"Penalizes frequent tokens, reducing repetition. Not applied when web search is on.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":0,"min":-2,"max":2},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Not applied when web search is on.","required":false,"metadata":{"ui":{"section":"Generation","hide_in_playground":true}}},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning is always on; this sets how much effort the model spends before answering. Higher effort uses more reasoning tokens. Reasoning text is not returned in responses.","required":false,"metadata":{"ui":{"control":"segmented","section":"Reasoning"}},"default":"medium","options":["minimal","low","medium","high","xhigh"]},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable built-in web search with cited sources. Adds $0.00825 per executed search query; a single request can run more than one search.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function and custom tool definitions. On /v1/responses, tool_search and defer_loading can discover deferred tools.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}},"default":[]},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible tool choice control. This model supports auto and none.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}}},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow the model to request multiple function tools in one response. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools","hide_in_playground":true}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return structured JSON output. JSON mode returns any valid JSON object; JSON Schema mode enforces an exact schema.","required":false,"metadata":{"ui":{"control":"json","section":"Structured Output","hide_in_playground":true},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/muse-spark-1-1:generateContent"],"pricing":{"prompt":"0.00000125","completion":"0.00000425","image":"0","request":"0","input_cache_read":"0.000001"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.25"},{"spec":"per 1M generated tokens","label":"Output","value":"$4.25"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$1.00"},{"spec":"per search query","label":"Web search","value":"$0.00825"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.25","label":"Input"},{"unit":"1m_tokens","usd":"4.25","label":"Output"},{"unit":"1m_tokens","usd":"1","label":"Implicit cache read"},{"unit":"search","usd":"0.00825","label":"Web search"}],"limits":{"note":"Reasoning is always on and cannot be disabled. Reasoning stays internal, and reasoning tokens are billed as output tokens and count against max_tokens. reasoning_effort accepts minimal through xhigh. Text, image, MP4 video, MP3/WAV audio, and PDF inputs are supported; up to 50 images can be attached. PDFs use text from the first 100 pages and page images from the first 50 pages. Built-in web search adds $0.00825 per executed search query and reports the count in usage.tool_usage. OpenAI Responses requests also support custom tools and deferred tool search. tool_choice supports auto and none. Prompts and completions sent to this Standard checkpoint are not used by Meta to train its models.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape. Exact field names, units, and which tools appear can vary by tool:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3}\n}\n```\n\nThe tool counts are already factored into `cost_usd` and are surfaced so you can audit per-tool billing. The field is omitted when no billed tool was invoked."},"notes":"Reasoning is always on and cannot be disabled. Reasoning stays internal, and reasoning tokens are billed as output tokens and count against max_tokens. reasoning_effort accepts minimal through xhigh. Text, image, MP4 video, MP3/WAV audio, and PDF inputs are supported; up to 50 images can be attached. PDFs use text from the first 100 pages and page images from the first 50 pages. Built-in web search adds $0.00825 per executed search query and reports the count in usage.tool_usage. OpenAI Responses requests also support custom tools and deferred tool search. tool_choice supports auto and none. Prompts and completions sent to this Standard checkpoint are not used by Meta to train its models.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=muse-spark-1-1","api_url":"https://docs.empiriolabs.ai/models/muse-spark-1-1","logo":"https://media.empiriolabs.ai/model-logos/muse-spark-1-1.png","status":"available"},{"id":"fugu-ultra-v1-1","object":"model","created":1784764800,"owned_by":"sakana","display_name":"Fugu Ultra v1.1","author":"sakana","provider":"sakana","description":"Updated multi-agent conductor for hard reasoning, coding, and research, with distinct max effort, 1M context, image input, and web search.","modality":"multimodal","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image"],"input_modalities":["text","image"],"output_modalities":["text"],"features":["reasoning","multimodal","web_search","function_calling","agentic_coding","cache"],"aliases":["fugu-ultra-v1.1","sakana/fugu-ultra-v1-1","sakana/fugu-ultra-v1.1"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":131072,"model_released_at":"2026-07-23","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum number of output tokens for the final answer. Must be at least 16. Very small values can truncate or empty the answer. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"slider","section":"Generation"}},"min":16,"max":131072},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"How hard Fugu Ultra v1.1 reasons. Reasoning is always on. high balances speed and performance, xhigh provides deep reasoning for complex problems, and max is the distinct maximum level for the hardest problems.","required":false,"metadata":{"ui":{"control":"segmented","section":"Reasoning"}},"default":"high","options":["high","xhigh","max"]},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable built-in web search. There is no separate fee; the search cost is reflected in the orchestration tokens billed for the request.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function calling tool definitions.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}},"default":[]},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible tool choice control.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return structured JSON output. JSON mode returns any valid JSON object; JSON Schema mode enforces the exact schema you provide.","required":false,"metadata":{"ui":{"control":"json","section":"Structured Output","hide_in_playground":true},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/fugu-ultra-v1-1:generateContent"],"pricing":[{"prompt":"0.000005","completion":"0.00003","image":"0","request":"0","input_cache_read":"0.0000005"},{"prompt":"0.00001","completion":"0.000045","image":"0","request":"0","input_cache_read":"0.000001","min_context":272000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=272K $5.00; >272K $10.00"},{"spec":"per 1M generated tokens","label":"Output","value":"<=272K $30.00; >272K $45.00"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"<=272K $0.50; >272K $1.00"}],"unit_pricing":[],"limits":{"note":"Fugu Ultra v1.1 is an updated multi-agent conductor: each request coordinates a pool of expert models and composes their work into a single answer.\n\n**Latency and streaming**\n- Responses can take from a few seconds to a few minutes on complex prompts.\n- The full answer is returned all at once when the model finishes, not token by token. Streaming is accepted, but it delivers the complete response at the end rather than streaming tokens as they generate.\n- max_tokens must be at least 16. Leave generous headroom, since very small limits can truncate or empty the answer.\n\n**Capabilities**\n- Text and image input, with a 1M token context.\n- Always-on reasoning with high, xhigh, and a distinct max level for the hardest problems.\n- Function calling, strict JSON Schema structured output, and built-in web search that cites its sources when available (no separate fee).\n\n**Versioning**\n- Use fugu-ultra-v1-1 for v1.1. The legacy fugu-ultra id remains pinned to v1.0 for backward compatibility.\n\n**Billing**\n- Billed on full token usage, including the orchestration tokens the model uses internally, so even short prompts carry some cost.\n- Context-tiered: requests above 272K total input tokens use the higher rate shown."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=fugu-ultra-v1-1","api_url":"https://docs.empiriolabs.ai/models/fugu-ultra-v1-1","logo":"https://media.empiriolabs.ai/model-logos/fugu-ultra-v1-1.png","status":"available"},{"id":"qwen3-7-plus","object":"model","created":1780272000,"owned_by":"alibaba","display_name":"Qwen3.7 Plus","author":"alibaba","provider":"alibaba","description":"Cost-effective Qwen3.7 vision-language model for text, image, video, coding, tool use, GUI understanding, and 1M-context workflows.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","video","web_search","code_interpreter","function_calling","prefix_continuation","fine_tuning","agentic_coding"],"aliases":["qwen3.7-plus"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":983616,"context_length":983616,"max_output_tokens":65536,"model_released_at":"2026-06-01","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":262144},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies. Not available when a built-in tool is on, or on /v1/responses.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. Applies when no built-in tool is enabled, and not on /v1/responses.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"treat_images_as_video","label":"Treat Images as Video","type":"boolean","description":"Treat a sequence of images as video frames.","required":false,"metadata":{"ui":{"control":"toggle","section":"Video"}},"default":false},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.03 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.03},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_search_image","label":"Text-to-Image Search","type":"boolean","description":"Search the web for images from text descriptions. Adds $0.03 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.03},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_image_search","label":"Image-to-Image Search","type":"boolean","description":"Find similar images from an uploaded image. Adds $0.03 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.03},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added. Applies to streamed responses that use a built-in tool.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"default":false},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-7-plus:generateContent"],"pricing":[{"prompt":"0.0000004","completion":"0.0000016","image":"0","request":"0","input_cache_read":"0.0000004"},{"prompt":"0.0000012","completion":"0.0000048","image":"0","request":"0","input_cache_read":"0.0000012","min_context":256000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=256K $0.40; 256K-1M $1.20"},{"spec":"per 1M generated tokens","label":"Output","value":"<=256K $1.60; 256K-1M $4.80"},{"spec":"per call when invoked","label":"Web search","value":"$0.03"},{"spec":"per call when invoked","label":"Text-to-image search","value":"$0.03"},{"spec":"per call when invoked","label":"Image-to-image search","value":"$0.03"},{"spec":"per call when invoked","label":"Web extractor","value":"$0.00"},{"spec":"per call when invoked","label":"Code interpreter","value":"$0.00"}],"unit_pricing":[{"unit":"call","usd":"0.03","label":"Web search"},{"unit":"call","usd":"0.03","label":"Text-to-image search"},{"unit":"call","usd":"0.03","label":"Image-to-image search"},{"unit":"call","usd":"0","label":"Web extractor"},{"unit":"call","usd":"0","label":"Code interpreter"}],"limits":{"note":"Pricing is 3x for input/output above 256K tokens. Web Search, Text-to-Image Search, and Image-to-Image Search are billed only when invoked.\n\nText-to-Image Search and Image-to-Image Search use the Image Search pricing row. Thinking tokens are billed as output tokens.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. Tool counts are already factored into `cost_usd` and are surfaced for transparency."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-7-plus","api_url":"https://docs.empiriolabs.ai/models/qwen3-7-plus","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-7-plus:variant1","object":"model","created":1780272000,"owned_by":"alibaba","display_name":"Qwen3.7 Plus","author":"alibaba","provider":"alibaba","description":"Cost-effective Qwen3.7 vision-language model for text, image, video, coding, tool use, GUI understanding, and 1M-context workflows.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","video","web_search","code_interpreter","function_calling","prefix_continuation","cache","fine_tuning","agentic_coding"],"aliases":[],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":"batch","batch_discount_pct":35,"context_window":983616,"context_length":983616,"max_output_tokens":65536,"model_released_at":"2026-06-01","is_new":false,"is_featured":true,"discount":{"label":"Save up to 31%","percent":31},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":262144},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies. Not available when a built-in tool is on, or on /v1/responses.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. Applies when no built-in tool is enabled, and not on /v1/responses.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"treat_images_as_video","label":"Treat Images as Video","type":"boolean","description":"Treat a sequence of images as video frames.","required":false,"metadata":{"ui":{"control":"toggle","section":"Video"}},"default":false},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.01 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.01},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_search_image","label":"Text-to-Image Search","type":"boolean","description":"Search the web for images from text descriptions. Adds $0.01 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.01},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_image_search","label":"Image-to-Image Search","type":"boolean","description":"Find similar images from an uploaded image. Adds $0.01 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.01},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added. Applies to streamed responses that use a built-in tool.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"default":false},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-7-plus:variant1:generateContent"],"pricing":[{"prompt":"0.000000276","completion":"0.000001101","image":"0","request":"0","input_cache_read":"0.000000056"},{"prompt":"0.000000826","completion":"0.000003301","image":"0","request":"0","input_cache_read":"0.000000166","min_context":256000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=256K $0.276 (was $0.40); 256K-1M $0.826 (was $1.20)"},{"spec":"per 1M generated tokens","label":"Output","value":"<=256K $1.101 (was $1.60); 256K-1M $3.301 (was $4.80)"},{"spec":"per 1M cached prompt tokens","label":"Implicit cache read","value":"<=256K $0.056 (was $0.08); 256K-1M $0.166 (was $0.24)"},{"spec":"per call when invoked","label":"Web search","value":"$0.01"},{"spec":"per call when invoked","label":"Text-to-image search","value":"$0.01"},{"spec":"per call when invoked","label":"Image-to-image search","value":"$0.01"},{"spec":"per call when invoked","label":"Web extractor","value":"$0.00"},{"spec":"per call when invoked","label":"Code interpreter","value":"$0.00"}],"unit_pricing":[{"unit":"call","usd":"0.01","label":"Web search"},{"unit":"call","usd":"0.01","label":"Text-to-image search"},{"unit":"call","usd":"0.01","label":"Image-to-image search"},{"unit":"call","usd":"0","label":"Web extractor"},{"unit":"call","usd":"0","label":"Code interpreter"}],"limits":{"note":"China pricing is discounted versus Singapore. Implicit cache input uses the cached-token row. Web Search, Text-to-Image Search, and Image-to-Image Search are billed only when invoked.\n\nText-to-Image Search and Image-to-Image Search use the Image Search pricing row. China paid tool calls are $0.01 each. Thinking tokens are billed as output tokens.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. Tool counts are already factored into `cost_usd` and are surfaced for transparency."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-7-plus:variant1","api_url":"https://docs.empiriolabs.ai/models/qwen3-7-plus#variant1","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"kimi-k2-7-code-highspeed","object":"model","created":1781568000,"owned_by":"moonshot","display_name":"Kimi K2.7 Code Highspeed","author":"moonshot","provider":"moonshot","description":"Kimi K2.7 Code Highspeed is the faster-serving tier of Moonshot's agentic coding model, with 256K context, always-on reasoning, and image and video input.","modality":"multimodal","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","function_calling","multimodal","agentic_coding","web_search"],"aliases":["kimi-k2.7-code-highspeed","moonshotai/kimi-k2-7-code-highspeed","moonshotai/kimi-k2.7-code-highspeed"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":262144,"context_length":262144,"max_output_tokens":131072,"model_released_at":"2026-06-16","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. Reasoning tokens count toward this limit.","required":false,"metadata":{},"default":32768,"min":1,"max":262144},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.015 to the request cost for each invoked web search call.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.015}},"default":false},{"name":"max_tool_calls","label":"Max Web Searches","type":"number","description":"Max number of web searches the model can run in one request. Each search is billed separately.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true},"clear_when_hidden":true},"default":5,"min":1,"max":20},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/kimi-k2-7-code-highspeed:generateContent"],"pricing":{"prompt":"0.0000019","completion":"0.000008","image":"0","request":"0","input_cache_read":"0.0000019"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.90"},{"spec":"per 1M generated tokens","label":"Output","value":"$8.00"},{"spec":"per call when invoked","label":"Web search","value":"$0.015"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.9","label":"Input"},{"unit":"1m_tokens","usd":"8","label":"Output"},{"unit":"call","usd":"0.015","label":"Web search"}],"limits":{"note":"The faster-serving tier of Kimi K2.7 Code. Supports text, image, and video inputs with 256K context, function calling, JSON mode structured output, and built-in web search at $0.015 per invoked call. Thinking is always on and cannot be disabled; reasoning tokens are billed as output tokens. Temperature and other sampling overrides are ignored because the model service uses fixed sampling settings. Multi-step function calling through the API must replay the assistant message with its reasoning_content field intact.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. Tool counts are already factored into `cost_usd` and are surfaced for transparency."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=kimi-k2-7-code-highspeed","api_url":"https://docs.empiriolabs.ai/models/kimi-k2-7-code-highspeed","logo":"https://media.empiriolabs.ai/model-logos/kimi.png","status":"available"},{"id":"fugu-ultra-v1-0","object":"model","created":1782000000,"owned_by":"sakana","display_name":"Fugu Ultra v1.0","author":"sakana","provider":"sakana","description":"Original multi-agent conductor for hard reasoning, coding, and research, with 1M context, image input, function calling, and web search.","modality":"multimodal","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image"],"input_modalities":["text","image"],"output_modalities":["text"],"features":["reasoning","multimodal","web_search","function_calling","agentic_coding","cache"],"aliases":["fugu-ultra","fugu-ultra-20260615","fugu-ultra-v1.0","sakana/fugu-ultra","sakana/fugu-ultra-20260615","sakana/fugu-ultra-v1-0","sakana/fugu-ultra-v1.0"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":131072,"model_released_at":"2026-06-21","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum number of output tokens for the final answer. Must be at least 16. Very small values can truncate or empty the answer. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"slider","section":"Generation"}},"min":16,"max":131072},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"How hard the model reasons. Reasoning is always on. The default is high; xhigh and max are aliases of the same maximum effort.","required":false,"metadata":{"ui":{"control":"segmented","section":"Reasoning"}},"default":"high","options":["high","xhigh","max"]},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable built-in web search. There is no separate fee; the search cost is reflected in the orchestration tokens billed for the request.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function calling tool definitions.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}},"default":[]},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible tool choice control.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"ui":{"control":"json","section":"Structured Output","hide_in_playground":true},"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/fugu-ultra-v1-0:generateContent"],"pricing":[{"prompt":"0.0000075","completion":"0.000045","image":"0","request":"0","input_cache_read":"0.0000015"},{"prompt":"0.000015","completion":"0.0000675","image":"0","request":"0","input_cache_read":"0.000003","min_context":272000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=272K $7.50; >272K $15.00"},{"spec":"per 1M generated tokens","label":"Output","value":"<=272K $45.00; >272K $67.50"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"<=272K $1.50; >272K $3.00"}],"unit_pricing":[],"limits":{"note":"Fugu Ultra v1.0 is the original multi-agent conductor: each request coordinates a pool of expert models and composes their work into a single answer.\n\n**Latency and streaming**\n- Responses can take from a few seconds to a few minutes on complex prompts.\n- The full answer is returned all at once when the model finishes, not token by token. Streaming is accepted, but it delivers the complete response at the end rather than streaming tokens as they generate.\n- max_tokens must be at least 16. Leave generous headroom, since very small limits can truncate or empty the answer.\n\n**Capabilities**\n- Text and image input, with a 1M token context.\n- Always-on reasoning. high is the default; xhigh and max are aliases of the same maximum effort.\n- Function calling, JSON mode, and built-in web search that cites its sources when available (no separate fee).\n\n**Compatibility**\n- The legacy fugu-ultra, fugu-ultra-20260615, and sakana/fugu-ultra ids remain pinned to this version.\n\n**Billing**\n- Billed on full token usage, including the orchestration tokens the model uses internally, so even short prompts carry some cost.\n- Context-tiered: requests above 272K total input tokens use the higher rate shown."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=fugu-ultra-v1-0","api_url":"https://docs.empiriolabs.ai/models/fugu-ultra-v1-0","logo":"https://media.empiriolabs.ai/model-logos/fugu-ultra-v1-0.png","status":"available"},{"id":"qwen3-7-flash","object":"model","created":1784073600,"owned_by":"alibaba","display_name":"Qwen3.7 Flash","author":"alibaba","provider":"alibaba","description":"Fast Qwen3.7 vision-language model for text, image, video, tool use, and agentic tasks, with implicit caching and a 1M token context.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","video","web_search","code_interpreter","function_calling","prefix_continuation","cache","agentic_coding"],"aliases":["qwen3.7-flash"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":983616,"context_length":983616,"max_output_tokens":65536,"model_released_at":"2026-07-15","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":65536},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":131072},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies. Not available when a built-in tool is on, or on /v1/responses.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. Applies when no built-in tool is enabled, and not on /v1/responses.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"treat_images_as_video","label":"Treat Images as Video","type":"boolean","description":"Treat a sequence of images as video frames.","required":false,"metadata":{"ui":{"control":"toggle","section":"Video"}},"default":false},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.03 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.03},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_search_image","label":"Text-to-Image Search","type":"boolean","description":"Search the web for images from text descriptions. Adds $0.03 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.03},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_image_search","label":"Image-to-Image Search","type":"boolean","description":"Find similar images from an uploaded image. Adds $0.03 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.03},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added. Applies to streamed responses that use a built-in tool.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"default":false},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-7-flash:generateContent"],"pricing":[{"prompt":"0.00000003","completion":"0.00000013","image":"0","request":"0","input_cache_read":"0.000000006"},{"prompt":"0.0000001","completion":"0.0000004","image":"0","request":"0","input_cache_read":"0.00000002","min_context":32000},{"prompt":"0.0000002","completion":"0.0000008","image":"0","request":"0","input_cache_read":"0.00000004","min_context":256000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=32K $0.03; 32K-256K $0.10; 256K-1M $0.20"},{"spec":"per 1M generated tokens","label":"Output","value":"<=32K $0.13; 32K-256K $0.40; 256K-1M $0.80"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"<=32K $0.006; 32K-256K $0.02; 256K-1M $0.04"},{"spec":"per call when invoked","label":"Web search","value":"$0.03"},{"spec":"per call when invoked","label":"Text-to-image search","value":"$0.03"},{"spec":"per call when invoked","label":"Image-to-image search","value":"$0.03"},{"spec":"per call when invoked","label":"Web extractor","value":"$0.00"},{"spec":"per call when invoked","label":"Code interpreter","value":"$0.00"}],"unit_pricing":[{"unit":"call","usd":"0.03","label":"Web search"},{"unit":"call","usd":"0.03","label":"Text-to-image search"},{"unit":"call","usd":"0.03","label":"Image-to-image search"},{"unit":"call","usd":"0","label":"Web extractor"},{"unit":"call","usd":"0","label":"Code interpreter"}],"limits":{"note":"Token pricing is tiered by prompt size and steps up above 32K and again above 256K input tokens. Cached prompt tokens are billed at the implicit cache rate for the matching tier. Web Search, Text-to-Image Search, and Image-to-Image Search are billed only when invoked.\n\nText-to-Image Search and Image-to-Image Search use the Image Search pricing row. Thinking tokens are billed as output tokens.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. Tool counts are already factored into `cost_usd` and are surfaced for transparency."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-7-flash","api_url":"https://docs.empiriolabs.ai/models/qwen3-7-flash","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-7-flash:variant1","object":"model","created":1784073600,"owned_by":"alibaba","display_name":"Qwen3.7 Flash","author":"alibaba","provider":"alibaba","description":"Fast Qwen3.7 vision-language model for text, image, video, tool use, and agentic tasks, with implicit caching and a 1M token context.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","video","web_search","code_interpreter","function_calling","prefix_continuation","cache","agentic_coding"],"aliases":[],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":"batch","batch_discount_pct":35,"context_window":983616,"context_length":983616,"max_output_tokens":65536,"model_released_at":"2026-07-15","is_new":false,"is_featured":true,"discount":{"label":"Save up to 18%","percent":18},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":65536},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":131072},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies. Not available when a built-in tool is on, or on /v1/responses.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. Applies when no built-in tool is enabled, and not on /v1/responses.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"treat_images_as_video","label":"Treat Images as Video","type":"boolean","description":"Treat a sequence of images as video frames.","required":false,"metadata":{"ui":{"control":"toggle","section":"Video"}},"default":false},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.01 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.01},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_search_image","label":"Text-to-Image Search","type":"boolean","description":"Search the web for images from text descriptions. Adds $0.01 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.01},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_image_search","label":"Image-to-Image Search","type":"boolean","description":"Find similar images from an uploaded image. Adds $0.01 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.01},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added. Applies to streamed responses that use a built-in tool.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"default":false},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-7-flash:variant1:generateContent"],"pricing":[{"prompt":"0.000000028","completion":"0.00000011","image":"0","request":"0","input_cache_read":"0.000000006"},{"prompt":"0.000000083","completion":"0.00000033","image":"0","request":"0","input_cache_read":"0.000000017","min_context":32000},{"prompt":"0.000000165","completion":"0.00000066","image":"0","request":"0","input_cache_read":"0.000000033","min_context":256000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=32K $0.028 (was $0.03); 32K-256K $0.083 (was $0.10); 256K-1M $0.165 (was $0.20)"},{"spec":"per 1M generated tokens","label":"Output","value":"<=32K $0.11 (was $0.13); 32K-256K $0.33 (was $0.40); 256K-1M $0.66 (was $0.80)"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"<=32K $0.006; 32K-256K $0.017 (was $0.02); 256K-1M $0.033 (was $0.04)"},{"spec":"per call when invoked","label":"Web search","value":"$0.01"},{"spec":"per call when invoked","label":"Text-to-image search","value":"$0.01"},{"spec":"per call when invoked","label":"Image-to-image search","value":"$0.01"},{"spec":"per call when invoked","label":"Web extractor","value":"$0.00"},{"spec":"per call when invoked","label":"Code interpreter","value":"$0.00"}],"unit_pricing":[{"unit":"call","usd":"0.01","label":"Web search"},{"unit":"call","usd":"0.01","label":"Text-to-image search"},{"unit":"call","usd":"0.01","label":"Image-to-image search"},{"unit":"call","usd":"0","label":"Web extractor"},{"unit":"call","usd":"0","label":"Code interpreter"}],"limits":{"note":"China pricing is discounted versus Singapore. Token pricing is tiered by prompt size and steps up above 32K and again above 256K input tokens. Implicit cache input uses the cached-token row. Web Search, Text-to-Image Search, and Image-to-Image Search are billed only when invoked.\n\nText-to-Image Search and Image-to-Image Search use the Image Search pricing row. China paid tool calls are $0.01 each. Thinking tokens are billed as output tokens.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. Tool counts are already factored into `cost_usd` and are surfaced for transparency."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-7-flash:variant1","api_url":"https://docs.empiriolabs.ai/models/qwen3-7-flash#variant1","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"minimax-m3","object":"model","created":1780272000,"owned_by":"minimax","display_name":"MiniMax M3","author":"minimax","provider":"minimax","description":"MiniMax M3 is a multimodal reasoning model for coding, agents, and long-context analysis with text, image, and video input.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","video","web_search","function_calling","cache","long_context"],"aliases":["minimax-m3-standard","minimax/m3","minimax/m3-standard"],"structured_output":"none","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1048576,"context_length":1048576,"max_output_tokens":524288,"model_released_at":"2026-06-01","is_new":false,"is_featured":true,"discount":{"label":"Save up to 25%","percent":25},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_completion_tokens","label":"Max Completion Tokens","type":"number","description":"Maximum generated tokens, including reasoning tokens when thinking is enabled.","required":false,"metadata":{"aliases":["max_tokens"]},"default":4096,"min":1,"max":524288},{"name":"stop","label":"Stop","type":"string","description":"Optional stop sequence or list of stop sequences.","required":false,"metadata":{"items":"string"}},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.01 to the request cost for each invoked call.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.01}},"default":false},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable adaptive model thinking before answering. Set false to request a direct answer without a reasoning phase.","required":false,"metadata":{"true_value":"adaptive","false_value":"disabled","provider_field":"thinking.type"},"default":true},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible tool definitions for function calling.","required":false,"metadata":{"advanced":true}},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"Optional OpenAI-compatible tool_choice value.","required":false,"metadata":{"advanced":true}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/minimax-m3:generateContent"],"pricing":[{"prompt":"0.000000225","completion":"0.0000009","image":"0","request":"0","input_cache_read":"0.000000045"},{"prompt":"0.00000045","completion":"0.0000018","image":"0","request":"0","input_cache_read":"0.00000009","min_context":512000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=512K $0.225 (was $0.30); >512K $0.45 (was $0.60)"},{"spec":"per 1M generated tokens","label":"Output","value":"<=512K $0.90 (was $1.20); >512K $1.80 (was $2.40)"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"<=512K $0.045 (was $0.06); >512K $0.09 (was $0.12)"},{"spec":"per call when invoked","label":"Web search","value":"$0.01"}],"unit_pricing":[{"unit":"call","usd":"0.01","label":"Web search"}],"limits":{"note":"Text, image, and video input with text output. Thinking defaults to adaptive and can be disabled. Pricing is based on input tokens including cache hits: <=512K uses the discounted standard tier, while >512K uses the high-context tier. Supports up to 1M input tokens. Set tool_web_search to true to let the model search the web; each executed search is billed, and one request can run several searches. Answers that used web search end with a Sources list unless disable_formatting is true. Structured output through response_format is not supported; ask for JSON in the prompt instead.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes tools (web search, code interpreter, etc.) inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape, exact field names, units, and which tools appear can vary slightly per provider:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nThe tool counts are already factored into `cost_usd`, they are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=minimax-m3","api_url":"https://docs.empiriolabs.ai/models/minimax-m3","logo":"https://media.empiriolabs.ai/model-logos/minimax.png","status":"available"},{"id":"minimax-m3-1-flash","object":"model","created":1792368000,"owned_by":"minimax","display_name":"MiniMax M3.1 Flash","author":"minimax","provider":"minimax","description":"Fast multimodal coding and agent model with 1M context, adjustable reasoning depth, image and video input, function calling, and built-in web search.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","video","web_search","function_calling","cache","long_context","agentic_coding"],"aliases":["minimax-m3.1-flash","minimax/m3.1-flash","minimax/minimax-m3.1-flash"],"structured_output":"none","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1048576,"context_length":1048576,"max_output_tokens":524288,"model_released_at":"2026-10-19","is_new":true,"is_featured":true,"discount":{"label":"Save up to 25%","percent":25},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning is always on; this sets how much effort the model spends before answering. Higher effort uses more reasoning tokens.","required":false,"metadata":{"ui":{"control":"segmented","section":"Reasoning"}},"default":"max","options":["low","medium","high","xhigh","max"]},{"name":"max_completion_tokens","label":"Max Completion Tokens","type":"number","description":"Maximum generated tokens, including reasoning tokens.","required":false,"metadata":{"aliases":["max_tokens"]},"default":32768,"min":1,"max":524288},{"name":"stop","label":"Stop","type":"string","description":"Optional stop sequence or list of stop sequences.","required":false,"metadata":{"items":"string"}},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.01 to the request cost for each invoked call.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.01}},"default":false},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible tool definitions for function calling.","required":false,"metadata":{"advanced":true}},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"Optional OpenAI-compatible tool_choice value.","required":false,"metadata":{"advanced":true}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/minimax-m3-1-flash:generateContent"],"pricing":{"prompt":"0.0000001125","completion":"0.00000045","image":"0","request":"0","input_cache_read":"0.00000001125"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.1125 (was $0.15)"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.45 (was $0.60)"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.01125 (was $0.015)"},{"spec":"per call when invoked","label":"Web search","value":"$0.01"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.1125","label":"Input"},{"unit":"1m_tokens","usd":"0.45","label":"Output"},{"unit":"1m_tokens","usd":"0.01125","label":"Implicit cache read"},{"unit":"call","usd":"0.01","label":"Web search"}],"limits":{"note":"Text, image, and video input with text output, a 1M token context, and up to 524,288 output tokens. The model always reasons: reasoning_effort sets how deeply (low, medium, high, xhigh, or max; the default is max), and the reasoning text is returned in reasoning_content. Reasoning tokens are billed as output tokens. Repeated prompt prefixes are cached automatically and billed at the cached input rate. Set tool_web_search to true to let the model search the web; each executed search is billed, and one request can run several searches. Answers that used web search end with a Sources list unless disable_formatting is true. Structured output through response_format is not supported; ask for JSON in the prompt instead.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes tools (web search, code interpreter, etc.) inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape, exact field names, units, and which tools appear can vary slightly per provider:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nThe tool counts are already factored into `cost_usd`, they are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=minimax-m3-1-flash","api_url":"https://docs.empiriolabs.ai/models/minimax-m3-1-flash","logo":"https://media.empiriolabs.ai/model-logos/minimax.png","status":"available"},{"id":"qwen3-7-max","object":"model","created":1779321600,"owned_by":"alibaba","display_name":"Qwen3.7 Max","author":"alibaba","provider":"alibaba","description":"Qwen3.7 Max is a flagship text model for coding, productivity, long-running agents, deep thinking, tools, and 1M-token context.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","web_search","code_interpreter","function_calling","agentic_coding"],"aliases":["qwen3.7-max"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":983616,"context_length":983616,"max_output_tokens":65536,"model_released_at":"2026-05-21","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":262144},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false}],"clear_when_hidden":true},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies. Not available when a built-in tool is on, or on /v1/responses.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false}],"clear_when_hidden":true},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false}],"clear_when_hidden":true},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.02 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking. Adds $0.02 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"visible_when":{"op":"eq","field":"tool_web_search","value":true},"clear_when_hidden":true},"default":false},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking. Adds $0.02 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"default":false},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-7-max:generateContent"],"pricing":{"prompt":"0.0000025","completion":"0.0000075","image":"0","request":"0","input_cache_read":"0.0000025"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$2.50"},{"spec":"per 1M generated tokens","label":"Output","value":"$7.50"},{"spec":"per call when invoked","label":"Web search","value":"$0.02"},{"spec":"per call when invoked","label":"Web extractor","value":"$0.02"},{"spec":"per call when invoked","label":"Code interpreter","value":"$0.02"}],"unit_pricing":[{"unit":"1m_tokens","usd":"2.5","label":"Input"},{"unit":"1m_tokens","usd":"7.5","label":"Output"},{"unit":"call","usd":"0.02","label":"Web search"},{"unit":"call","usd":"0.02","label":"Web extractor"},{"unit":"call","usd":"0.02","label":"Code interpreter"}],"limits":{"note":"Text input only. Web search, web extractor, and code interpreter are optional built-in tools exposed through tool_* parameters. Each built-in tool call adds $0.02 when invoked. Thinking tokens are billed as output tokens.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. Tool counts are already factored into `cost_usd` and are surfaced for transparency."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-7-max","api_url":"https://docs.empiriolabs.ai/models/qwen3-7-max","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-7-max:variant1","object":"model","created":1779321600,"owned_by":"alibaba","display_name":"Qwen3.7 Max","author":"alibaba","provider":"alibaba","description":"Qwen3.7 Max is a flagship text model for coding, productivity, long-running agents, deep thinking, tools, and 1M-token context.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","web_search","code_interpreter","function_calling","agentic_coding"],"aliases":[],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":"batch","batch_discount_pct":35,"context_window":983616,"context_length":983616,"max_output_tokens":65536,"model_released_at":"2026-05-21","is_new":false,"is_featured":true,"discount":{"label":"Save up to 34%","percent":34},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":262144},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false}],"clear_when_hidden":true},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies. Not available when a built-in tool is on, or on /v1/responses.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false}],"clear_when_hidden":true},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false}],"clear_when_hidden":true},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.01 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.01},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking. Adds $0.01 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.01},"hidden_when":{"op":"exists","field":"response_format"},"visible_when":{"op":"eq","field":"tool_web_search","value":true},"clear_when_hidden":true},"default":false},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking. Adds $0.01 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.01},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"default":false},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-7-max:variant1:generateContent"],"pricing":{"prompt":"0.00000165","completion":"0.000004951","image":"0","request":"0","input_cache_read":"0.00000165"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.65 (was $2.50)"},{"spec":"per 1M generated tokens","label":"Output","value":"$4.951 (was $7.50)"},{"spec":"per call when invoked","label":"Web search","value":"$0.01"},{"spec":"per call when invoked","label":"Web extractor","value":"$0.01"},{"spec":"per call when invoked","label":"Code interpreter","value":"$0.01"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.65","label":"Input"},{"unit":"1m_tokens","usd":"4.951","label":"Output"},{"unit":"call","usd":"0.01","label":"Web search"},{"unit":"call","usd":"0.01","label":"Web extractor"},{"unit":"call","usd":"0.01","label":"Code interpreter"}],"limits":{"note":"Text input only. Web search, web extractor, and code interpreter are optional built-in tools exposed through tool_* parameters. Each built-in tool call adds $0.01 when invoked. Thinking tokens are billed as output tokens.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\\n\\nWhen this model invokes built-in tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. Tool counts are already factored into `cost_usd` and are surfaced for transparency."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-7-max:variant1","api_url":"https://docs.empiriolabs.ai/models/qwen3-7-max#variant1","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-8-max","object":"model","created":1785715200,"owned_by":"alibaba","display_name":"Qwen3.8 Max","author":"alibaba","provider":"alibaba","description":"Trillion-scale MoE flagship for coding, long-horizon agents, and professional work, with image and video understanding across a 1M-token context.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","multimodal","web_search","code_interpreter","function_calling","structured_output","agentic_coding"],"aliases":["qwen3.8-max"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":983616,"context_length":983616,"max_output_tokens":131072,"model_released_at":"2026-08-03","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":262144},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":true},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies. Not available when a built-in tool is on, or on /v1/responses.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. Applies when no built-in tool is enabled, and not on /v1/responses.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"treat_images_as_video","label":"Treat Images as Video","type":"boolean","description":"Treat a sequence of images as video frames.","required":false,"metadata":{"ui":{"control":"toggle","section":"Video"}},"default":false},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.02 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_search_image","label":"Text-to-Image Search","type":"boolean","description":"Search the web for images from text descriptions. Adds $0.02 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_image_search","label":"Image-to-Image Search","type":"boolean","description":"Find similar images from an uploaded image. Adds $0.02 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added. Applies to streamed responses that use a built-in tool.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"default":false},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-8-max:generateContent"],"pricing":{"prompt":"0.000002","completion":"0.000006","image":"0","request":"0","input_cache_read":"0.000002"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$2.00"},{"spec":"per 1M generated tokens","label":"Output","value":"$6.00"},{"spec":"per call when invoked","label":"Web search","value":"$0.02"},{"spec":"per call when invoked","label":"Text-to-image search","value":"$0.02"},{"spec":"per call when invoked","label":"Image-to-image search","value":"$0.02"},{"spec":"per call when invoked","label":"Web extractor","value":"$0.00"},{"spec":"per call when invoked","label":"Code interpreter","value":"$0.00"}],"unit_pricing":[{"unit":"1m_tokens","usd":"2","label":"Input"},{"unit":"1m_tokens","usd":"6","label":"Output"},{"unit":"call","usd":"0.02","label":"Web search"},{"unit":"call","usd":"0.02","label":"Text-to-image search"},{"unit":"call","usd":"0.02","label":"Image-to-image search"},{"unit":"call","usd":"0","label":"Web extractor"},{"unit":"call","usd":"0","label":"Code interpreter"}],"limits":{"note":"Text, image, and video input are supported. Web search, web extractor, code interpreter, text-to-image search, and image-to-image search are optional built-in tools exposed through tool_* parameters. Web search, text-to-image search, and image-to-image search add $0.02 for each invoked call; web extractor and code interpreter run at no extra cost. Web extractor requires web search, and both web extractor and code interpreter require thinking. A single request can invoke a tool more than once, and each invoked call is billed. Thinking tokens are billed as output tokens. The qwen3-8-max id always serves the current Qwen3.8 Max build and moves with Alibaba's snapshot upgrades; since September 5, 2026 it serves the qwen3-8-max-0902 snapshot. Use qwen3-8-max-0902 when output must stay pinned to that exact snapshot.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nTool counts are already factored into `cost_usd` and are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-8-max","api_url":"https://docs.empiriolabs.ai/models/qwen3-8-max","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-8-max:variant1","object":"model","created":1785715200,"owned_by":"alibaba","display_name":"Qwen3.8 Max","author":"alibaba","provider":"alibaba","description":"Trillion-scale MoE flagship for coding, long-horizon agents, and professional work, with image and video understanding across a 1M-token context.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","multimodal","web_search","code_interpreter","function_calling","structured_output","agentic_coding"],"aliases":["qwen3.8-max:variant1"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":"batch","batch_discount_pct":35,"context_window":983616,"context_length":983616,"max_output_tokens":131072,"model_released_at":"2026-08-03","is_new":false,"is_featured":true,"discount":{"label":"Save up to 18%","percent":18},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":262144},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":true},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies. Not available when a built-in tool is on, or on /v1/responses.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. Applies when no built-in tool is enabled, and not on /v1/responses.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"treat_images_as_video","label":"Treat Images as Video","type":"boolean","description":"Treat a sequence of images as video frames.","required":false,"metadata":{"ui":{"control":"toggle","section":"Video"}},"default":false},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.01 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_search_image","label":"Text-to-Image Search","type":"boolean","description":"Search the web for images from text descriptions. Adds $0.01 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_image_search","label":"Image-to-Image Search","type":"boolean","description":"Find similar images from an uploaded image. Adds $0.01 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added. Applies to streamed responses that use a built-in tool.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"default":false},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-8-max:variant1:generateContent"],"pricing":{"prompt":"0.00000165","completion":"0.000004951","image":"0","request":"0","input_cache_read":"0.00000165"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.65 (was $2.00)"},{"spec":"per 1M generated tokens","label":"Output","value":"$4.951 (was $6.00)"},{"spec":"per call when invoked","label":"Web search","value":"$0.01"},{"spec":"per call when invoked","label":"Text-to-image search","value":"$0.01"},{"spec":"per call when invoked","label":"Image-to-image search","value":"$0.01"},{"spec":"per call when invoked","label":"Web extractor","value":"$0.00"},{"spec":"per call when invoked","label":"Code interpreter","value":"$0.00"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.65","label":"Input"},{"unit":"1m_tokens","usd":"4.951","label":"Output"},{"unit":"call","usd":"0.01","label":"Web search"},{"unit":"call","usd":"0.01","label":"Text-to-image search"},{"unit":"call","usd":"0.01","label":"Image-to-image search"},{"unit":"call","usd":"0","label":"Web extractor"},{"unit":"call","usd":"0","label":"Code interpreter"}],"limits":{"note":"Text, image, and video input are supported. Web search, web extractor, code interpreter, text-to-image search, and image-to-image search are optional built-in tools exposed through tool_* parameters. Web search, text-to-image search, and image-to-image search add $0.02 for each invoked call; web extractor and code interpreter run at no extra cost. Web extractor requires web search, and both web extractor and code interpreter require thinking. A single request can invoke a tool more than once, and each invoked call is billed. Thinking tokens are billed as output tokens. This id always serves the current Qwen3.8 Max build on the China endpoint and moves with Alibaba's snapshot upgrades. Use qwen3-8-max-0902 when output must stay pinned to the September 2, 2026 snapshot.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nTool counts are already factored into `cost_usd` and are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-8-max%3Avariant1","api_url":"https://docs.empiriolabs.ai/models/qwen3-8-max","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-8-flash","object":"model","created":1787702400,"owned_by":"alibaba","display_name":"Qwen3.8 Flash","author":"alibaba","provider":"alibaba","description":"Fast Qwen3.8 vision-language model for coding, agents, and visual understanding, with image and video input, five built-in tools, and a 1M token context.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","multimodal","web_search","code_interpreter","function_calling","structured_output","agentic_coding"],"aliases":["qwen3.8-flash"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":983616,"context_length":983616,"max_output_tokens":131072,"model_released_at":"2026-08-26","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":262144},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":true},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies. Not available when a built-in tool is on, or on /v1/responses.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. Applies when no built-in tool is enabled, and not on /v1/responses.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"treat_images_as_video","label":"Treat Images as Video","type":"boolean","description":"Treat a sequence of images as video frames.","required":false,"metadata":{"ui":{"control":"toggle","section":"Video"}},"default":false},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.02 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_search_image","label":"Text-to-Image Search","type":"boolean","description":"Search the web for images from text descriptions. Adds $0.02 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_image_search","label":"Image-to-Image Search","type":"boolean","description":"Find similar images from an uploaded image. Adds $0.02 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added. Applies to streamed responses that use a built-in tool.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"default":false},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-8-flash:generateContent"],"pricing":{"prompt":"0.00000016","completion":"0.00000047","image":"0","request":"0","input_cache_read":"0.00000016"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.16"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.47"},{"spec":"per call when invoked","label":"Web search","value":"$0.02"},{"spec":"per call when invoked","label":"Text-to-image search","value":"$0.02"},{"spec":"per call when invoked","label":"Image-to-image search","value":"$0.02"},{"spec":"per call when invoked","label":"Web extractor","value":"$0.00"},{"spec":"per call when invoked","label":"Code interpreter","value":"$0.00"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.16","label":"Input"},{"unit":"1m_tokens","usd":"0.47","label":"Output"},{"unit":"call","usd":"0.02","label":"Web search"},{"unit":"call","usd":"0.02","label":"Text-to-image search"},{"unit":"call","usd":"0.02","label":"Image-to-image search"},{"unit":"call","usd":"0","label":"Web extractor"},{"unit":"call","usd":"0","label":"Code interpreter"}],"limits":{"note":"Text, image, and video input are supported. Web search, web extractor, code interpreter, text-to-image search, and image-to-image search are optional built-in tools exposed through tool_* parameters. Web search, text-to-image search, and image-to-image search add $0.02 for each invoked call; web extractor and code interpreter run at no extra cost. Web extractor requires web search, and both web extractor and code interpreter require thinking. A single request can invoke a tool more than once, and each invoked call is billed. Thinking tokens are billed as output tokens.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nTool counts are already factored into `cost_usd` and are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-8-flash","api_url":"https://docs.empiriolabs.ai/models/qwen3-8-flash","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-8-max-0902","object":"model","created":1788307200,"owned_by":"alibaba","display_name":"Qwen3.8 Max 0902","author":"alibaba","provider":"alibaba","description":"Upgraded Qwen3.8 Max snapshot with stronger coding, steadier multi-tool agent runs, and sharper chart and document vision across a 1M-token context.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","multimodal","web_search","code_interpreter","function_calling","structured_output","agentic_coding"],"aliases":["qwen3.8-max-0902","qwen3.8-max-2026-09-02"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":983616,"context_length":983616,"max_output_tokens":131072,"model_released_at":"2026-09-02","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":262144},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":true},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies. Not available when a built-in tool is on, or on /v1/responses.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. Applies when no built-in tool is enabled, and not on /v1/responses.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"treat_images_as_video","label":"Treat Images as Video","type":"boolean","description":"Treat a sequence of images as video frames.","required":false,"metadata":{"ui":{"control":"toggle","section":"Video"}},"default":false},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.02 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_search_image","label":"Text-to-Image Search","type":"boolean","description":"Search the web for images from text descriptions. Adds $0.02 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_image_search","label":"Image-to-Image Search","type":"boolean","description":"Find similar images from an uploaded image. Adds $0.02 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added. Applies to streamed responses that use a built-in tool.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"default":false},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-8-max-0902:generateContent"],"pricing":{"prompt":"0.000002","completion":"0.000006","image":"0","request":"0","input_cache_read":"0.000002"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$2.00"},{"spec":"per 1M generated tokens","label":"Output","value":"$6.00"},{"spec":"per call when invoked","label":"Web search","value":"$0.02"},{"spec":"per call when invoked","label":"Text-to-image search","value":"$0.02"},{"spec":"per call when invoked","label":"Image-to-image search","value":"$0.02"},{"spec":"per call when invoked","label":"Web extractor","value":"$0.00"},{"spec":"per call when invoked","label":"Code interpreter","value":"$0.00"}],"unit_pricing":[{"unit":"1m_tokens","usd":"2","label":"Input"},{"unit":"1m_tokens","usd":"6","label":"Output"},{"unit":"call","usd":"0.02","label":"Web search"},{"unit":"call","usd":"0.02","label":"Text-to-image search"},{"unit":"call","usd":"0.02","label":"Image-to-image search"},{"unit":"call","usd":"0","label":"Web extractor"},{"unit":"call","usd":"0","label":"Code interpreter"}],"limits":{"note":"Text, image, and video input are supported. Web search, web extractor, code interpreter, text-to-image search, and image-to-image search are optional built-in tools exposed through tool_* parameters. Web search, text-to-image search, and image-to-image search add $0.02 for each invoked call; web extractor and code interpreter run at no extra cost. Web extractor requires web search, and both web extractor and code interpreter require thinking. A single request can invoke a tool more than once, and each invoked call is billed. Thinking tokens are billed as output tokens. This id is pinned to the September 2, 2026 snapshot and will not change. The rolling qwen3-8-max id serves the same build since September 5, 2026 and will move to future snapshots.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nTool counts are already factored into `cost_usd` and are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-8-max-0902","api_url":"https://docs.empiriolabs.ai/models/qwen3-8-max-0902","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-8-omni-flash","object":"model","created":1789603200,"owned_by":"alibaba","display_name":"Qwen3.8 Omni Flash","author":"alibaba","provider":"alibaba","description":"Omni-modal reasoner that reads text, images, audio, and video and answers in text, with a 1M token context, thinking, and native web search.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","audio","video"],"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"features":["reasoning","vision","audio_in","video","web_search","function_calling","structured_output"],"aliases":["qwen3.8-omni-flash"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1006592,"context_length":1006592,"max_output_tokens":131072,"model_released_at":"2026-09-17","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":131072},{"name":"stop","label":"Stop Sequences","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":262144},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"visible_when":[{"op":"eq","field":"tool_web_search","value":false}],"clear_when_hidden":true},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies. Not available when a built-in tool is on, or on /v1/responses.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"},"visible_when":[{"op":"eq","field":"tool_web_search","value":false}],"clear_when_hidden":true},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"},"visible_when":[{"op":"eq","field":"tool_web_search","value":false}],"clear_when_hidden":true},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. Applies when no built-in tool is enabled, and not on /v1/responses.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"treat_images_as_video","label":"Treat Multiple Images as Video","type":"boolean","description":"Treat a sequence of images as video frames.","required":false,"metadata":{"ui":{"control":"toggle","section":"Video"}},"default":false},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.02 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added. Applies to streamed responses that use a built-in tool.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"default":false},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-8-omni-flash:generateContent"],"pricing":{"prompt":"0.0000003","completion":"0.00000094","image":"0","request":"0","input_cache_read":"0.0000003"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.30"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.94"},{"spec":"per call when invoked","label":"Web search","value":"$0.02"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.3","label":"Input"},{"unit":"1m_tokens","usd":"0.94","label":"Output"},{"unit":"call","usd":"0.02","label":"Web search"}],"limits":{"note":"Text, image, audio, and video input are supported, and the model replies in text. Thinking is on by default; use enable_thinking to turn it off and thinking_budget to cap it at up to 262144 tokens. Thinking tokens are billed as output tokens. Web search is an optional built-in tool exposed through tool_web_search and adds $0.02 for each invoked call; a single request can invoke it more than once, and each invoked call is billed. For audio input, pass the file as a URL or a base64 data URI. A video's soundtrack is billed as audio tokens alongside its video tokens.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3}\n}\n```\n\nTool counts are already factored into `cost_usd` and are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-8-omni-flash","api_url":"https://docs.empiriolabs.ai/models/qwen3-8-omni-flash","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen4-max","object":"model","created":1794787200,"owned_by":"alibaba","display_name":"Qwen4 Max","author":"alibaba","provider":"alibaba","description":"Next-generation Qwen flagship for coding, frontend design, office work, and complex agents, with image and video understanding across a 1M-token context.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","multimodal","web_search","code_interpreter","function_calling","structured_output","agentic_coding","cache"],"aliases":[],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":983616,"context_length":983616,"max_output_tokens":262144,"model_released_at":"2026-11-16","is_new":true,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens, reasoning included. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":262144},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning depth while thinking is on: low, high, or xhigh. Higher effort spends more reasoning tokens before answering. The default is high. low and xhigh cannot be combined with thinking_budget.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"hidden_when":{"op":"eq","field":"enable_thinking","value":false},"clear_when_hidden":true},"default":"high","options":["low","high","xhigh"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason. Runs at the default reasoning effort and cannot be combined with low or xhigh. Not used when a built-in tool is on, or on /v1/responses.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":[{"op":"eq","field":"enable_thinking","value":true},{"op":"in","field":"reasoning_effort","values":["high",null]}],"clear_when_hidden":true},"min":1,"max":262144},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":true},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies. Not available when a built-in tool is on, or on /v1/responses.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. Applies when no built-in tool is enabled, and not on /v1/responses.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"treat_images_as_video","label":"Treat Images as Video","type":"boolean","description":"Treat a sequence of images as video frames.","required":false,"metadata":{"ui":{"control":"toggle","section":"Video"}},"default":false},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.02 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_search_image","label":"Text-to-Image Search","type":"boolean","description":"Search the web for images from text descriptions. Adds $0.02 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_image_search","label":"Image-to-Image Search","type":"boolean","description":"Find similar images from an uploaded image. Adds $0.02 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added. Applies to streamed responses that use a built-in tool.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"default":false},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen4-max:generateContent"],"pricing":{"prompt":"0.0000015","completion":"0.0000045","image":"0","request":"0","input_cache_read":"0.000000075"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.50"},{"spec":"per 1M generated tokens","label":"Output","value":"$4.50"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.075"},{"spec":"per call when invoked","label":"Web search","value":"$0.02"},{"spec":"per call when invoked","label":"Text-to-image search","value":"$0.02"},{"spec":"per call when invoked","label":"Image-to-image search","value":"$0.02"},{"spec":"per call when invoked","label":"Web extractor","value":"$0.00"},{"spec":"per call when invoked","label":"Code interpreter","value":"$0.00"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.5","label":"Input"},{"unit":"1m_tokens","usd":"4.5","label":"Output"},{"unit":"1m_tokens","usd":"0.075","label":"Implicit cache read"},{"unit":"call","usd":"0.02","label":"Web search"},{"unit":"call","usd":"0.02","label":"Text-to-image search"},{"unit":"call","usd":"0.02","label":"Image-to-image search"},{"unit":"call","usd":"0","label":"Web extractor"},{"unit":"call","usd":"0","label":"Code interpreter"}],"limits":{"note":"Text, image, and video input are supported. Web search, web extractor, code interpreter, text-to-image search, and image-to-image search are optional built-in tools exposed through tool_* parameters. Web search, text-to-image search, and image-to-image search add $0.02 for each invoked call; web extractor and code interpreter run at no extra cost. Web extractor requires web search, and both web extractor and code interpreter require thinking. A single request can invoke a tool more than once, and each invoked call is billed. Thinking is on by default; reasoning_effort sets its depth (low, high, or xhigh, default high), and thinking tokens are billed as output tokens. max_tokens and max_completion_tokens cap reasoning and answer together. Repeated prompt prefixes are cached automatically, and cached input tokens bill at the implicit cache read rate. Explicit cache controls such as cache_control are not supported.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nTool counts are already factored into `cost_usd` and are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen4-max","api_url":"https://docs.empiriolabs.ai/models/qwen4-max","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"ace-step-1-5-xl","object":"model","created":1775088000,"owned_by":"ace-step","display_name":"ACE-Step 1.5 XL","author":"ace-step","provider":"ace-step","description":"Open-source music generation model for text-to-song and lyric-guided audio, with fast 8-step XL Turbo inference for controllable song iteration.","modality":null,"type":"generation","category":"audio","category_label":null,"modality_label":null,"modalities":["text","audio"],"input_modalities":["text"],"output_modalities":["audio"],"features":["music_generation","lyrics","text_to_music","seed_control","commercial_ready"],"aliases":["ace-step-1.5-xl","ace-step/acestep-v15-xl-turbo"],"structured_output":null,"native_inference":true,"weight_precision":"BF16","hugging_face_id":"ACE-Step/acestep-v15-xl-turbo","batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-04-02","is_new":false,"is_featured":true,"discount":{"label":"Save up to 17%","percent":17},"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"prompt","type":"string","description":"Genre, mood, instrumentation, and BPM hints describing the music to compose. Comma-separated tags work well.","required":true,"metadata":{"aliases":["description"]}},{"name":"lyrics","label":"lyrics","type":"string","description":"Vocal lyrics for the track. Use [verse] / [chorus] / [bridge] tags to mark sections, blank line for instrumental break. Leave empty for purely instrumental tracks.","required":false,"metadata":{}},{"name":"audio_duration","label":"audio_duration","type":"number","description":"Length of the generated track in seconds, from 10 to 600.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"aliases":["duration"]},"default":30,"min":10,"max":600},{"name":"num_inference_steps","label":"num_inference_steps","type":"number","description":"Number of diffusion steps. 8 is recommended for this Turbo model; more steps add polish, fewer steps give faster drafts.","required":false,"metadata":{"aliases":["steps"]},"default":8,"min":1,"max":20},{"name":"guidance_scale","label":"guidance_scale","type":"number","description":"Classifier-free guidance scale. 1.0 follows the model's natural distribution; higher values push closer to the prompt at the cost of variety.","required":false,"metadata":{},"default":1,"min":0,"max":20},{"name":"shift","label":"shift","type":"number","description":"Diffusion timestep shift. Default leaves the schedule unchanged; nudge to 1.0+ for shorter/punchier or below 1.0 for slower/dreamier results.","required":false,"metadata":{}},{"name":"seed","label":"seed","type":"number","description":"Random seed for reproducibility. Same seed + identical params produces the same track.","required":false,"metadata":{}},{"name":"format","label":"format","type":"enum","description":"Audio file format. FLAC is lossless, WAV is uncompressed, and OGG and MP3 are smaller lossy files.","required":false,"metadata":{"aliases":["output_format"]},"default":"flac","options":["flac","wav","ogg","mp3"]},{"name":"response_format","label":"response_format","type":"enum","description":"Return a signed media URL by default, or base64 JSON when requested.","required":false,"metadata":{},"default":"url","options":["url","b64_json"]},{"name":"return_base64","label":"return_base64","type":"boolean","description":"Compatibility alias for response_format=b64_json.","required":false,"metadata":{"aliases":["b64_json"]},"default":false}],"supported_endpoints":["POST /v1/audio/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per generated second","label":"Music generation","value":"$0.00025 (was $0.0003)"}],"unit_pricing":[{"unit":"second","usd":"0.00025","label":"Music generation"}],"limits":{"note":"**Defaults**\n\n- 8 inference steps\n- Guidance scale 1.0\n- Lossless FLAC output\n\n**Controls**\n\nSupports lyrics, prompt/description, 10-600s duration, seed, shift, and URL or base64 output mode."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=ace-step-1-5-xl","api_url":"https://docs.empiriolabs.ai/models/ace-step-1-5-xl","logo":"https://media.empiriolabs.ai/model-logos/ace-step-1-5-xl.png","status":"available"},{"id":"flux-2-klein-4b","object":"model","created":1768435200,"owned_by":"black-forest-labs","display_name":"FLUX.2 Klein 4B","author":"black-forest-labs","provider":"black-forest-labs","description":"Apache-licensed 4B FLUX.2 Klein image generation and editing model with text-to-image, reference-image editing, and creative workflow support.","modality":null,"type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["text","image"],"input_modalities":["text","image"],"output_modalities":["image"],"features":["image_generation","image_editing","reference_images","seed_control"],"aliases":["black-forest-labs/flux.2-klein-4b","flux.2-klein-4b"],"structured_output":null,"native_inference":true,"weight_precision":"BF16","hugging_face_id":"black-forest-labs/FLUX.2-klein-4B","batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-01-15","is_new":false,"is_featured":true,"discount":{"label":"Save up to 39%","percent":39},"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Text description of the image to generate.","required":true,"metadata":{}},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"1:1","options":["1:1","16:9","9:16","4:3","3:4","3:2","2:3"]},{"name":"size","label":"Size","type":"string","description":"Explicit WIDTHxHEIGHT override. Width x height must be at most 1,048,576 pixels. Leave unset to use aspect_ratio.","required":false,"metadata":{"max_product_pixels":1048576}},{"name":"width","label":"Width","type":"number","description":"Output width in pixels. Set width and height together. Width x height must be at most 1,048,576 pixels.","required":false,"metadata":{"ui":{"step":64},"paired_dimension":"height","max_product_pixels":1048576},"min":256,"max":2048},{"name":"height","label":"Height","type":"number","description":"Output height in pixels. Set width and height together. Width x height must be at most 1,048,576 pixels.","required":false,"metadata":{"ui":{"step":64},"paired_dimension":"width","max_product_pixels":1048576},"min":256,"max":2048},{"name":"num_inference_steps","label":"Num Inference Steps","type":"number","description":"Number of denoising steps. Higher = better quality but slower.","required":false,"metadata":{},"default":4,"min":1,"max":12},{"name":"guidance_scale","label":"Guidance Scale","type":"number","description":"Prompt adherence. Higher = closer to prompt but less creative.","required":false,"metadata":{},"default":1,"min":0,"max":8},{"name":"seed","label":"Seed","type":"number","description":"Random seed for reproducibility. Same seed + prompt = same output.","required":false,"metadata":{}},{"name":"num_images","label":"Num Images","type":"number","description":"How many images to generate (1-4).","required":false,"metadata":{},"default":1,"min":1,"max":4},{"name":"format","label":"Format","type":"enum","description":"Image file codec for the generated output.","required":false,"metadata":{"aliases":["output_format"]},"default":"webp","options":["webp","png","jpg","jpeg"]},{"name":"response_format","label":"Response Format","type":"enum","description":"Return a signed media URL by default, or base64 JSON when requested.","required":false,"metadata":{},"default":"url","options":["url","b64_json"]},{"name":"return_base64","label":"Return Base64","type":"boolean","description":"Compatibility alias for response_format=b64_json.","required":false,"metadata":{"aliases":["b64_json"],"visible_when":{"op":"eq","field":"response_format","value":"b64_json"}},"default":false},{"name":"max_sequence_length","label":"Max Sequence Length","type":"number","description":"Max prompt-token length the model conditions on.","required":false,"metadata":{},"default":512,"min":64,"max":512},{"name":"images","label":"Images","type":"string","description":"Comma-separated reference image URLs for image-conditioned generation.","required":false,"metadata":{"ui":{"hide_in_playground":true}}}],"supported_endpoints":["POST /v1/images/generations"],"pricing":{"prompt":"0","completion":"0","image":"0.0085","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Image generation","value":"$0.0085 (was $0.014)"}],"unit_pricing":[{"unit":"image","usd":"0.0085","label":"Image generation"}],"limits":{"note":"**Defaults**\n\n- 1024x1024 image\n- 4 inference steps\n- Guidance scale 1.0\n- WebP output\n\n**Controls**\n\nSupports prompt, size/aspect ratio or explicit width/height, seed, n/num_images, and reference images. Width x height must be at most 1,048,576 pixels. Examples: 1024x1024, 1344x768, 768x1344, or 2048x512. Billing is per returned image, so `num_images: 4` creates and bills 4 images.\n\n**Content safety**\n\n- Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=flux-2-klein-4b","api_url":"https://docs.empiriolabs.ai/models/flux-2-klein-4b","logo":"https://media.empiriolabs.ai/model-logos/flux-2-klein-4b.png","status":"available"},{"id":"tts-2","object":"model","created":1777939200,"owned_by":"inworld","display_name":"TTS 2","author":"inworld","provider":"inworld","description":"Realtime voice model that takes plain-English delivery direction, holds one voice identity across 200+ languages, and streams with word timestamps.","modality":"audio","type":"tts","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["multi_speaker","real_time","low_latency","streaming","word_timestamps","character_timestamps","multilingual","expressive_prosody","voice_direction"],"aliases":["inworld-tts-2"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-05-05","is_new":false,"is_featured":true,"discount":{"label":"Save up to 12%","percent":12},"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Text to synthesize. Max 2,000 characters per request; chunk longer copy at sentence boundaries on the client. Optionally open the text with a bracketed delivery direction in plain English, for example `[whispering]` or `[Speak warmly, like you are greeting an old friend]`. The bracketed text steers delivery instead of being read aloud, and its characters count toward the billed character total.","required":true,"metadata":{},"max":2000},{"name":"voice","label":"Voice","type":"enum","description":"Voice preset. 20 hand-picked voices covering English, Spanish, Portuguese, Hindi, and various accents. For the full voice catalog, use voice_id instead.","required":false,"metadata":{},"default":"Sarah","options":["Sarah","Olivia","Elizabeth","Ashley","Wendy","Julia","Priya","Pixie","Deborah","Alex","Mark","Edward","Theodore","Ronald","Dennis","Timothy","Shaun","Craig","Hades","Heitor"]},{"name":"voice_id","label":"Voice ID","type":"string","description":"Free-form voice ID. Overrides voice when set. Use this to address any voice beyond the curated 20-preset list, including regional voices. Pass any voice name from GET /v1/voices. Example: Ashley, Mark.","required":false,"metadata":{}},{"name":"language","label":"Language","type":"enum","description":"BCP-47 language code. This model holds one voice identity across 200+ languages and locales, so you can pass any supported code here even if it is not in the dropdown.","required":false,"metadata":{},"default":"en-US","options":["en-US","en-GB","es-ES","es-MX","fr-FR","de-DE","it-IT","pt-BR","pt-PT","nl-NL","pl-PL","ru-RU","ja-JP","ko-KR","zh-CN","hi-IN","ar-EG","he-IL","tr-TR","vi-VN","th-TH","id-ID","uk-UA","el-GR","cs-CZ","sv-SE"]},{"name":"output_format","label":"Output format","type":"enum","description":"Audio container/codec. WAV = LINEAR16 inside RIFF (ubiquitous). MP3 / OGG = compressed. PCM = 16-bit PCM in a WAV header on POST /v1/audio/speech, headerless chunks on the stream. FLAC = lossless.","required":false,"metadata":{},"default":"WAV","options":["MP3","WAV","OGG","FLAC","PCM","ALAW","MULAW"]},{"name":"sample_rate","label":"Sample rate","type":"enum","description":"Output sample rate in Hz. 24000 is the default; use 48000 for broadcast quality.","required":false,"metadata":{},"default":"24000","options":["8000","16000","22050","24000","32000","44100","48000"]},{"name":"speed","label":"Speed","type":"number","description":"Speaking rate multiplier. 0.5 = half speed, 1.5 = 50% faster.","required":false,"metadata":{},"default":1,"min":0.5,"max":1.5},{"name":"temperature","label":"Temperature","type":"number","description":"Voice expressiveness / variability. Lower = more consistent / \"flat\"; higher = more expressive but more variation between renders.","required":false,"metadata":{},"default":1,"min":0.1,"max":2},{"name":"bit_rate","label":"Bit rate","type":"number","description":"Bitrate in bps for MP3 / OGG_OPUS. Ignored for other encodings.","required":false,"metadata":{},"default":128000,"min":32000,"max":320000},{"name":"apply_text_normalization","label":"Text normalization","type":"enum","description":"When ON, numbers, abbreviations and dates are expanded into spoken form (\"USD 5\" becomes \"five US dollars\").","required":false,"metadata":{},"default":"ON","options":["ON","OFF"]},{"name":"timestamp_type","label":"Timestamps","type":"enum","description":"If not NONE, the response includes per-word or per-character timestamps in timestamp_info, on POST /v1/audio/speech and on its stream. Useful for captions and highlighting.","required":false,"metadata":{},"default":"NONE","options":["NONE","WORD","CHARACTER"]}],"supported_endpoints":["POST /v1/audio/speech","POST /v1/audio/speech:stream","GET /v1/voices"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per 1M characters","label":"Synthesis","value":"$22.00 (was $25.00)"}],"unit_pricing":[{"unit":"1m_characters","usd":"22","label":"Synthesis"}],"limits":{"note":"**Limits**\n\n- Max input: 2,000 characters per request (chunk longer text at sentence boundaries)\n- WebSocket: 20 concurrent connections, 5 contexts/connection\n- Per-WS message: 1,000 characters\n\n**Voice direction**\n\n- Open the text with a bracketed instruction in plain English to steer delivery, for example `[whispering]`, `[excited]`, or `[Speak warmly, like you are greeting an old friend]`\n- The bracketed text is treated as direction and is not read aloud\n- Direction text counts toward the billed character total, so keep it short\n\n**Latency**\n\n- p90 TTFB: under 100 ms (Inworld benchmark)\n\n**Voices**\n\n- One voice identity held across 200+ languages and locales, including switching language mid-generation\n- Curated presets in the dropdown; pass any other voice ID via `voice_id`"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=tts-2","api_url":"https://docs.empiriolabs.ai/models/tts-2","logo":"https://media.empiriolabs.ai/model-logos/tts-2.png","status":"available"},{"id":"tts-1-5-mini","object":"model","created":1768953600,"owned_by":"inworld","display_name":"TTS 1.5 Mini","author":"inworld","provider":"inworld","description":"Sub-130ms TTFB voice synthesis with 271+ voices across 15 languages, expressive prosody, and real-time SSE streaming for low-latency voice agents.","modality":"audio","type":"tts","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["multi_speaker","real_time","low_latency","streaming","word_timestamps","character_timestamps","multilingual","expressive_prosody"],"aliases":["inworld-tts-1.5-mini","tts-1.5-mini"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-01-21","is_new":false,"is_featured":true,"discount":{"label":"Save up to 30%","percent":30},"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Text to synthesize. Max 2,000 characters per request; chunk longer copy at sentence boundaries on the client.","required":true,"metadata":{},"max":2000},{"name":"voice","label":"Voice","type":"enum","description":"Voice preset. 20 hand-picked voices covering English, Spanish, Portuguese, Hindi, and various accents. For the full voice catalog, use voice_id instead.","required":false,"metadata":{},"default":"Sarah","options":["Sarah","Olivia","Elizabeth","Ashley","Wendy","Julia","Priya","Pixie","Deborah","Alex","Mark","Edward","Theodore","Ronald","Dennis","Timothy","Shaun","Craig","Hades","Heitor"]},{"name":"voice_id","label":"Voice ID","type":"string","description":"Free-form voice ID. Overrides voice when set. Use any voice name from GET /v1/voices, for example Maitê or Olivia.","required":false,"metadata":{}},{"name":"language","label":"Language","type":"enum","description":"BCP-47 language code. This model covers 15 languages.","required":false,"metadata":{},"default":"en-US","options":["en-US","en-GB","es-ES","es-MX","fr-FR","de-DE","it-IT","pt-BR","pt-PT","nl-NL","pl-PL","ru-RU","ja-JP","ko-KR","zh-CN","hi-IN","ar-EG","he-IL"]},{"name":"output_format","label":"Output format","type":"enum","description":"Audio container/codec. WAV = LINEAR16 inside RIFF (ubiquitous). MP3 / OGG = compressed. PCM = 16-bit PCM in a WAV header on POST /v1/audio/speech, headerless chunks on the stream. FLAC = lossless.","required":false,"metadata":{},"default":"WAV","options":["MP3","WAV","OGG","FLAC","PCM","ALAW","MULAW"]},{"name":"sample_rate","label":"Sample rate","type":"enum","description":"Output sample rate in Hz. 24000 is the default; use 48000 for broadcast quality.","required":false,"metadata":{},"default":"24000","options":["8000","16000","22050","24000","32000","44100","48000"]},{"name":"speed","label":"Speed","type":"number","description":"Speaking rate multiplier. 0.5 = half speed, 1.5 = 50% faster.","required":false,"metadata":{},"default":1,"min":0.5,"max":1.5},{"name":"temperature","label":"Temperature","type":"number","description":"Voice expressiveness / variability. Lower = more consistent / \"flat\"; higher = more expressive but more variation between renders.","required":false,"metadata":{},"default":1,"min":0.1,"max":2},{"name":"bit_rate","label":"Bit rate","type":"number","description":"Bitrate in bps for MP3 / OGG_OPUS. Ignored for other encodings.","required":false,"metadata":{},"default":128000,"min":32000,"max":320000},{"name":"apply_text_normalization","label":"Text normalization","type":"enum","description":"When ON, numbers, abbreviations and dates are expanded into spoken form (\"USD 5\" becomes \"five US dollars\").","required":false,"metadata":{},"default":"ON","options":["ON","OFF"]},{"name":"timestamp_type","label":"Timestamps","type":"enum","description":"If not NONE, the response includes per-word or per-character timestamps in timestamp_info, on POST /v1/audio/speech and on its stream. Useful for captions and highlighting.","required":false,"metadata":{},"default":"NONE","options":["NONE","WORD","CHARACTER"]}],"supported_endpoints":["POST /v1/audio/speech","POST /v1/audio/speech:stream","GET /v1/voices"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per 1M characters","label":"Synthesis","value":"$17.50 (was $25.00)"}],"unit_pricing":[{"unit":"1m_characters","usd":"17.5","label":"Synthesis"}],"limits":{"note":"**Limits**\n\n- Max input: 2,000 characters per request (chunk longer text at sentence boundaries)\n- WebSocket: 20 concurrent connections, 5 contexts/connection\n- Per-WS message: 1,000 characters\n\n**Latency**\n\n- p90 TTFB: under 130 ms (Inworld benchmark)\n\n**Voices**\n\n- 271+ named presets across 15 languages\n- 20 hand-picked presets exposed in the dropdown; pass any other voice ID via `voice_id`"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=tts-1-5-mini","api_url":"https://docs.empiriolabs.ai/models/tts-1-5-mini","logo":"https://media.empiriolabs.ai/model-logos/tts-1-5-mini.png","status":"available"},{"id":"tts-1-5-max","object":"model","created":1768953600,"owned_by":"inworld","display_name":"TTS 1.5 Max","author":"inworld","provider":"inworld","description":"Broadcast-quality voice synthesis with rich expressive prosody, 271+ voices across 15 languages, and real-time SSE streaming with per-word timestamps.","modality":"audio","type":"tts","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["multi_speaker","real_time","streaming","word_timestamps","character_timestamps","multilingual","expressive_prosody","broadcast_quality"],"aliases":["inworld-tts-1.5-max","tts-1.5-max"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-01-21","is_new":false,"is_featured":true,"discount":{"label":"Save up to 15%","percent":15},"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Text to synthesize. Max 2,000 characters per request; chunk longer copy at sentence boundaries on the client.","required":true,"metadata":{},"max":2000},{"name":"voice","label":"Voice","type":"enum","description":"Voice preset. 20 hand-picked voices covering English, Spanish, Portuguese, Hindi, and various accents. For the full voice catalog, use voice_id instead.","required":false,"metadata":{},"default":"Sarah","options":["Sarah","Olivia","Elizabeth","Ashley","Wendy","Julia","Priya","Pixie","Deborah","Alex","Mark","Edward","Theodore","Ronald","Dennis","Timothy","Shaun","Craig","Hades","Heitor"]},{"name":"voice_id","label":"Voice ID","type":"string","description":"Free-form voice ID. Overrides voice when set. Use any voice name from GET /v1/voices, for example Maitê or Olivia.","required":false,"metadata":{}},{"name":"language","label":"Language","type":"enum","description":"BCP-47 language code. This model covers 15 languages.","required":false,"metadata":{},"default":"en-US","options":["en-US","en-GB","es-ES","es-MX","fr-FR","de-DE","it-IT","pt-BR","pt-PT","nl-NL","pl-PL","ru-RU","ja-JP","ko-KR","zh-CN","hi-IN","ar-EG","he-IL"]},{"name":"output_format","label":"Output format","type":"enum","description":"Audio container/codec. WAV = LINEAR16 inside RIFF (ubiquitous). MP3 / OGG = compressed. PCM = 16-bit PCM in a WAV header on POST /v1/audio/speech, headerless chunks on the stream. FLAC = lossless.","required":false,"metadata":{},"default":"WAV","options":["MP3","WAV","OGG","FLAC","PCM","ALAW","MULAW"]},{"name":"sample_rate","label":"Sample rate","type":"enum","description":"Output sample rate in Hz. 24000 is the default; use 48000 for broadcast quality.","required":false,"metadata":{},"default":"24000","options":["8000","16000","22050","24000","32000","44100","48000"]},{"name":"speed","label":"Speed","type":"number","description":"Speaking rate multiplier. 0.5 = half speed, 1.5 = 50% faster.","required":false,"metadata":{},"default":1,"min":0.5,"max":1.5},{"name":"temperature","label":"Temperature","type":"number","description":"Voice expressiveness / variability. Lower = more consistent / \"flat\"; higher = more expressive but more variation between renders.","required":false,"metadata":{},"default":1,"min":0.1,"max":2},{"name":"bit_rate","label":"Bit rate","type":"number","description":"Bitrate in bps for MP3 / OGG_OPUS. Ignored for other encodings.","required":false,"metadata":{},"default":128000,"min":32000,"max":320000},{"name":"apply_text_normalization","label":"Text normalization","type":"enum","description":"When ON, numbers, abbreviations and dates are expanded into spoken form (\"USD 5\" becomes \"five US dollars\").","required":false,"metadata":{},"default":"ON","options":["ON","OFF"]},{"name":"timestamp_type","label":"Timestamps","type":"enum","description":"If not NONE, the response includes per-word or per-character timestamps in timestamp_info, on POST /v1/audio/speech and on its stream. Useful for captions and highlighting.","required":false,"metadata":{},"default":"NONE","options":["NONE","WORD","CHARACTER"]}],"supported_endpoints":["POST /v1/audio/speech","POST /v1/audio/speech:stream","GET /v1/voices"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per 1M characters","label":"Synthesis","value":"$29.75 (was $35.00)"}],"unit_pricing":[{"unit":"1m_characters","usd":"29.75","label":"Synthesis"}],"limits":{"note":"**Limits**\n\n- Max input: 2,000 characters per request (chunk longer text at sentence boundaries)\n- WebSocket: 20 concurrent connections, 5 contexts/connection\n- Per-WS message: 1,000 characters\n\n**Latency**\n\n- p90 TTFB: under 250 ms (Inworld benchmark)\n\n**Voices**\n\n- 271+ named presets across 15 languages\n- 20 hand-picked presets exposed in the dropdown; pass any other voice ID via `voice_id`"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=tts-1-5-max","api_url":"https://docs.empiriolabs.ai/models/tts-1-5-max","logo":"https://media.empiriolabs.ai/model-logos/tts-1-5-max.png","status":"available"},{"id":"glm-5-1","object":"model","created":1775520000,"owned_by":"zhipu","display_name":"GLM 5.1","author":"zhipu","provider":"zhipu","description":"Long-context Zhipu AI reasoning model with 202K context, 128K output, tool calling, structured output, and cache support.","modality":"text","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","function_calling","cache"],"aliases":[],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":202745,"context_length":202745,"max_output_tokens":128000,"model_released_at":"2026-04-07","is_new":false,"is_featured":true,"discount":{"label":"Save up to 41%","percent":41},"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"slider","section":"Generation"}},"min":1,"max":128000},{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 1.99 = maximum randomness.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":1,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":0.95,"min":0,"max":1},{"name":"top_k","label":"Top K","type":"number","description":"Limits sampling to the top K tokens.","required":false,"metadata":{"ui":{"control":"slider","section":"Generation"}},"default":20,"min":1,"max":100},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Penalizes repeated tokens.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":1,"min":0.1},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Allow the model to reason before answering. With response_format, the model answers without reasoning unless the request sets enable_thinking.","required":false,"metadata":{"ui":{"control":"toggle","section":"Reasoning"}},"default":true},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled.","required":false,"metadata":{"ui":{"control":"slider","section":"Reasoning","show_when":{"enable_thinking":true}}},"default":32768,"min":1,"max":38912},{"name":"tool_stream","label":"Tool Stream","type":"boolean","description":"Stream function-call arguments incrementally when streaming.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function calling tool definitions.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}},"default":[]},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible tool choice control.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}}},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"stop","label":"Stop","type":"string","description":"Optional stop sequences.","required":false,"metadata":{"ui":{"control":"tags","section":"Generation","hide_in_playground":true},"control":"stop-sequences"}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"ui":{"control":"json","section":"Structured Output","hide_in_playground":true},"control":"structured-output","so_tier":"json_object"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/glm-5-1:generateContent"],"pricing":[{"prompt":"0.000000825","completion":"0.000003301","image":"0","request":"0","input_cache_read":"0.000000165"},{"prompt":"0.0000011","completion":"0.000003851","image":"0","request":"0","input_cache_read":"0.00000022","min_context":32000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=32K $0.825 (was $1.40); 32K-200K $1.10 (was $1.40)"},{"spec":"per 1M generated tokens","label":"Output","value":"<=32K $3.301 (was $4.40); 32K-200K $3.851 (was $4.40)"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"<=32K $0.165 (was $0.26); 32K-200K $0.22 (was $0.26)"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":null,"notes":"Rates are tiered by prompt length. Web search, batches, prefix continuation, and fine-tuning are not supported.","chat_url":null,"api_url":"https://docs.empiriolabs.ai/models/glm-5-1","logo":"https://media.empiriolabs.ai/model-logos/glm.png","status":"available"},{"id":"kimi-k2-6","object":"model","created":1776643200,"owned_by":"moonshot","display_name":"Kimi K2.6","author":"moonshot","provider":"moonshot","description":"Kimi K2.6 is a Moonshot multimodal reasoning model with 256K context, strong coding, and text, image, and video inputs.","modality":"multimodal","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","function_calling","cache","multimodal"],"aliases":[],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":262144,"context_length":262144,"max_output_tokens":16000,"model_released_at":"2026-04-20","is_new":false,"is_featured":true,"discount":{"label":"Save up to 7%","percent":7},"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 1.99 = maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":16000},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. With response_format, the model answers without reasoning unless the request sets enable_thinking.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":32768,"min":1,"max":81920},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/kimi-k2-6:generateContent"],"pricing":{"prompt":"0.0000008939","completion":"0.0000037131","image":"0","request":"0","input_cache_read":"0.0000001788"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.8939 (was $0.95)"},{"spec":"per 1M generated tokens","label":"Output","value":"$3.7131 (was $4.00)"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.1788"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.8939","label":"Input"},{"unit":"1m_tokens","usd":"3.7131","label":"Output"},{"unit":"1m_tokens","usd":"0.1788","label":"Implicit cache read"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":null,"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=kimi-k2-6","api_url":"https://docs.empiriolabs.ai/models/kimi-k2-6","logo":"https://media.empiriolabs.ai/model-logos/kimi.png","status":"available"},{"id":"deepseek-v4-pro:variant2","object":"model","created":1776988800,"owned_by":"deepseek","display_name":"DeepSeek V4 Pro (Variant 2)","author":"deepseek","provider":"deepseek","description":"DeepSeek V4 Pro is a flagship MoE reasoning model with 1M context, strong coding, automatic cache reads, and web search.","modality":"text","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","function_calling","web_search","cache"],"aliases":[],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":393216,"model_released_at":"2026-04-24","is_new":false,"is_featured":true,"discount":{"label":"Save up to 5%","percent":5},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 2 = maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":393216},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable step-by-step reasoning before answering. With response_format, the model answers without reasoning unless the request sets enable_thinking.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":32768,"min":1,"max":393216},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable live web search. Adds $0.01 to the request cost when enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/deepseek-v4-pro:variant2:generateContent"],"pricing":{"prompt":"0.00000165","completion":"0.000003301","image":"0","request":"0","input_cache_read":"0.000000138"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.65 (was $1.74)"},{"spec":"per 1M generated tokens","label":"Output","value":"$3.301 (was $3.48)"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.138"},{"spec":"per request when enabled","label":"Web search","value":"$0.01"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.65","label":"Input"},{"unit":"1m_tokens","usd":"3.301","label":"Output"},{"unit":"1m_tokens","usd":"0.138","label":"Implicit cache read"},{"unit":"request","usd":"0.01","label":"Web search"}],"limits":null,"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=deepseek-v4-pro:variant2","api_url":"https://docs.empiriolabs.ai/models/deepseek-v4-pro#variant2","logo":"https://media.empiriolabs.ai/model-logos/deepseek.png","status":"available"},{"id":"deepseek-v4-flash-0731","object":"model","created":1785456000,"owned_by":"deepseek","display_name":"DeepSeek V4 Flash 0731","author":"deepseek","provider":"deepseek","description":"Post-trained 0731 release with major gains across coding, repository work, tool use, and full-stack tasks, plus a 1M context window.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","function_calling","structured_output","agentic_coding"],"aliases":["deepseek/deepseek-v4-flash-0731","deepseek-ai/deepseek-v4-flash-0731"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":393216,"model_released_at":"2026-07-31","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 2 = maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":393216},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable step-by-step reasoning before answering.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":32768,"min":1,"max":393216},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"control":"structured-output","so_tier":"json_object"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/deepseek-v4-flash-0731:generateContent"],"pricing":{"prompt":"0.000000424","completion":"0.000001272","image":"0","request":"0","input_cache_read":"0.000000424"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.424"},{"spec":"per 1M generated tokens","label":"Output","value":"$1.272"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.424","label":"Input"},{"unit":"1m_tokens","usd":"1.272","label":"Output"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Thinking is enabled by default and can be disabled. Reasoning tokens are billed as output tokens. Optional Linkup web search is billed only when invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=deepseek-v4-flash-0731","api_url":"https://docs.empiriolabs.ai/models/deepseek-v4-flash-0731","logo":"https://media.empiriolabs.ai/model-logos/deepseek.png","status":"available"},{"id":"minimax-music-3","object":"model","created":1786579200,"owned_by":"minimax","display_name":"MiniMax Music 3","author":"minimax","provider":"minimax","description":"Generates complete stereo songs from lyrics and a style prompt, with duration, seed, and format controls up to 5 minutes.","modality":"audio","type":"generation","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["music_generation","lyrics","text_to_music","seed_control"],"aliases":["minimax-music3","minimax-music3.0","minimax/music3","minimax/minimax-music3","minimaxai/minimax-music3","MiniMax-Music3"],"structured_output":null,"native_inference":true,"weight_precision":"INT8","hugging_face_id":"MiniMaxAI/MiniMax-Music3","batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-08-13","is_new":false,"is_featured":true,"discount":{"label":"Save up to 10%","percent":10},"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Style and arrangement instructions for MiniMax Music 3. Describe genre, mood, vocal character, and instrumentation.","required":true,"metadata":{"ui":{"control":"text_area","section":"Input"},"aliases":["description","instructions"]}},{"name":"lyrics","label":"Lyrics","type":"string","description":"Song lyrics. Required for a vocal track. Hidden when Instrumental is on. Put one structure tag on its own line before each section. Supported tags: [Intro], [Verse], [Pre Chorus], [Chorus], [Interlude], [Bridge], [Outro], [Post Chorus], [Transition], [Break], [Hook], [Build Up], [Inst], [Solo]. Lowercase is fine.","required":false,"metadata":{"ui":{"control":"textarea","section":"Input"},"visible_when":{"op":"eq","field":"instrumental","value":false},"required_when":{"op":"eq","field":"instrumental","value":false},"clear_when_hidden":true}},{"name":"instrumental","label":"Instrumental","type":"boolean","description":"When on, the model writes an instrumental track and lyrics stay hidden. Turn this off to write a vocal song. When omitted, a request with lyrics writes a vocal song.","required":false,"metadata":{"ui":{"control":"toggle","section":"Settings"}},"default":true},{"name":"audio_duration","label":"Duration","type":"number","description":"Length of the generated song in seconds. MiniMax Music 3 accepts 10 to 300 seconds and bills a 10 second minimum.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Settings"},"aliases":["duration","duration_seconds"]},"default":10,"min":10,"max":300},{"name":"seed","label":"Seed","type":"number","description":"Random seed for reproducibility. Same seed and identical params produce the same song.","required":false,"metadata":{"ui":{"section":"Settings"}}},{"name":"format","label":"Format","type":"enum","description":"Audio container format. WAV is uncompressed, FLAC is lossless, MP3 is a smaller file.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Output"},"aliases":["output_format"]},"default":"wav","options":["wav","flac","mp3"]},{"name":"response_format","label":"Response Format","type":"enum","description":"Return a signed media URL by default, or base64 JSON when requested.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Output"}},"default":"url","options":["url","b64_json"]},{"name":"return_base64","label":"Return Base64","type":"boolean","description":"Compatibility alias for response_format=b64_json.","required":false,"metadata":{"ui":{"hidden":true},"aliases":["b64_json"]},"default":false}],"supported_endpoints":["POST /v1/audio/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per generated second","label":"Music generation","value":"$0.0018 (was $0.002)"}],"unit_pricing":[{"unit":"second","usd":"0.0018","label":"Music generation"}],"limits":{"note":"**Defaults**\n\n- Instrumental is on by default. Pass lyrics and set instrumental to false for a vocal track\n- 10 second songs, billed at a 10 second minimum\n- WAV output\n- Pinned at 30 steps and guidance 1.7\n\n**Controls**\n\nSupports prompt (style and arrangement), lyrics with structure tags, instrumental mode, 10-300s duration, seed, and WAV, FLAC, or MP3 output. URL or base64 response format.\n\n**Limits**\n\n- Duration 10 to 300 seconds\n- Songs are billed per generated second with a 10 second floor\n\n**Billing**\n\n- Charged per generated second at the catalog rate. A 10 second request that returns a 10 second song bills 10 seconds.\n- A request rejected before generation is not billed."},"notes":"**Defaults**\n\n- Instrumental is on by default. Pass lyrics and set instrumental to false for a vocal track\n- 10 second songs, billed at a 10 second minimum\n- WAV output\n- Pinned at 30 steps and guidance 1.7\n\n**Controls**\n\nSupports prompt (style and arrangement), lyrics with structure tags, instrumental mode, 10-300s duration, seed, and WAV, FLAC, or MP3 output. URL or base64 response format.\n\n**Limits**\n\n- Duration 10 to 300 seconds\n- Songs are billed per generated second with a 10 second floor\n\n**Billing**\n\n- Charged per generated second at the catalog rate. A 10 second request that returns a 10 second song bills 10 seconds.\n- A request rejected before generation is not billed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=minimax-music-3","api_url":"https://docs.empiriolabs.ai/models/minimax-music-3","logo":"https://media.empiriolabs.ai/model-logos/minimax.png","status":"available"},{"id":"deepseek-v4-pro-0813","object":"model","created":1786579200,"owned_by":"deepseek","display_name":"DeepSeek V4 Pro 0813","author":"deepseek","provider":"deepseek","description":"Official 0813 Pro release with major gains across coding, repository work, tool use, and agent tasks, plus hybrid thinking and a 1M context window.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","function_calling","structured_output","agentic_coding"],"aliases":["deepseek/deepseek-v4-pro-0813","deepseek-ai/deepseek-v4-pro-0813"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":393216,"model_released_at":"2026-08-13","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 2 = maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":393216},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable step-by-step reasoning before answering.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":32768,"min":1,"max":393216},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/deepseek-v4-pro-0813:generateContent"],"pricing":{"prompt":"0.00000132","completion":"0.00000396","image":"0","request":"0","input_cache_read":"0.00000132"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.32"},{"spec":"per 1M generated tokens","label":"Output","value":"$3.96"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.32","label":"Input"},{"unit":"1m_tokens","usd":"3.96","label":"Output"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Thinking is enabled by default and can be disabled. Reasoning tokens are billed as output tokens. Optional Linkup web search is billed only when invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=deepseek-v4-pro-0813","api_url":"https://docs.empiriolabs.ai/models/deepseek-v4-pro-0813","logo":"https://media.empiriolabs.ai/model-logos/deepseek.png","status":"available"},{"id":"deepseek-v4-flash-0731:variant1","object":"model","created":1785456000,"owned_by":"deepseek","display_name":"DeepSeek V4 Flash 0731 (Variant 1)","author":"deepseek","provider":"deepseek","description":"Post-trained 0731 release with major gains across coding, repository work, tool use, and full-stack tasks, plus a 1M context window.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","function_calling","structured_output","agentic_coding"],"aliases":[],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":393216,"model_released_at":"2026-07-31","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 2 = maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":393216},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable step-by-step reasoning before answering.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":32768,"min":1,"max":393216},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/deepseek-v4-flash-0731:variant1:generateContent"],"pricing":{"prompt":"0.00000044","completion":"0.00000132","image":"0","request":"0","input_cache_read":"0.00000044"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.44"},{"spec":"per 1M generated tokens","label":"Output","value":"$1.32"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.44","label":"Input"},{"unit":"1m_tokens","usd":"1.32","label":"Output"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":null,"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=deepseek-v4-flash-0731:variant1","api_url":"https://docs.empiriolabs.ai/models/deepseek-v4-flash-0731#variant1","logo":"https://media.empiriolabs.ai/model-logos/deepseek.png","status":"available"},{"id":"deepseek-v4-pro:variant3","object":"model","created":1776988800,"owned_by":"deepseek","display_name":"DeepSeek V4 Pro (Variant 3)","author":"deepseek","provider":"deepseek","description":"Flagship MoE LLM with 1.6T total / 49B active parameters and native 1M context for advanced math, logical inference, and specialized coding.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","function_calling","structured_output"],"aliases":[],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":393216,"model_released_at":"2026-04-24","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 2 = maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":393216},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable step-by-step reasoning before answering.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":32768,"min":1,"max":393216},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/deepseek-v4-pro:variant3:generateContent"],"pricing":{"prompt":"0.0000024","completion":"0.0000048","image":"0","request":"0","input_cache_read":"0.0000024"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$2.40"},{"spec":"per 1M generated tokens","label":"Output","value":"$4.80"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"2.4","label":"Input"},{"unit":"1m_tokens","usd":"4.8","label":"Output"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":null,"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=deepseek-v4-pro:variant3","api_url":"https://docs.empiriolabs.ai/models/deepseek-v4-pro#variant3","logo":"https://media.empiriolabs.ai/model-logos/deepseek.png","status":"available"},{"id":"glm-5-2:variant2","object":"model","created":1781568000,"owned_by":"zhipu","display_name":"GLM 5.2 (Variant 2)","author":"zhipu","provider":"zhipu","description":"Reasoning and coding model with a 1M token context, 128K output, adjustable reasoning effort, and tool calling.","modality":"text","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","function_calling","structured_output","web_search"],"aliases":[],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1048576,"context_length":1048576,"max_output_tokens":131072,"model_released_at":"2026-06-16","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 1.99 = maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable step-by-step reasoning before answering.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":32768,"min":1,"max":131071},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/glm-5-2:variant2:generateContent"],"pricing":{"prompt":"0.0000014","completion":"0.0000044","image":"0","request":"0","input_cache_read":"0.0000014"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.40"},{"spec":"per 1M generated tokens","label":"Output","value":"$4.40"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.4","label":"Input"},{"unit":"1m_tokens","usd":"4.4","label":"Output"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":null,"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=glm-5-2:variant2","api_url":"https://docs.empiriolabs.ai/models/glm-5-2#variant2","logo":"https://media.empiriolabs.ai/model-logos/glm.png","status":"available"},{"id":"muse-spark-1-3","object":"model","created":1788307200,"owned_by":"meta","display_name":"Muse Spark 1.3","author":"meta","provider":"meta","description":"Meta's long-horizon agentic reasoning model with a 1,048,576-token context, image, video, and PDF understanding, web search, and tool calling.","modality":"multimodal","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video","document"],"input_modalities":["text","image","video","document"],"output_modalities":["text"],"features":["reasoning","multimodal","video_understanding","function_calling","structured_output","web_search","cache","document_understanding"],"aliases":["muse-spark-1.3","meta/muse-spark-1-3","meta/muse-spark-1.3"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1048576,"context_length":1048576,"max_output_tokens":131072,"model_released_at":"2026-09-02","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum number of output tokens to generate, at least 16. Reasoning tokens count against this budget.","required":false,"metadata":{"ui":{"control":"slider","section":"Generation"}},"default":16384,"min":16,"max":131072},{"name":"temperature","label":"Temperature","type":"number","description":"Controls randomness. Lower values make responses more deterministic.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":1,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling cutoff.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Generation"}},"default":1,"min":0.01,"max":1},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning is always on; this sets how much effort the model spends before answering. Higher effort uses more reasoning tokens.","required":false,"metadata":{"ui":{"control":"segmented","section":"Reasoning"}},"default":"medium","options":["minimal","low","medium","high","xhigh"]},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable built-in web search with cited sources. Adds $0.00825 per executed search query; a single request can run more than one search.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function and custom tool definitions. On /v1/responses, tool_search and defer_loading can discover deferred tools.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}},"default":[]},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible tool choice control. This model supports auto and none.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}}},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow the model to request multiple function tools in one response. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools","hide_in_playground":true}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return structured JSON output. JSON mode returns any valid JSON object; JSON Schema mode enforces an exact schema.","required":false,"metadata":{"ui":{"control":"json","section":"Structured Output","hide_in_playground":true},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/muse-spark-1-3:generateContent"],"pricing":{"prompt":"0.00000125","completion":"0.00000425","image":"0","request":"0","input_cache_read":"0.000001"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.25"},{"spec":"per 1M generated tokens","label":"Output","value":"$4.25"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$1.00"},{"spec":"per search query","label":"Web search","value":"$0.00825"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.25","label":"Input"},{"unit":"1m_tokens","usd":"4.25","label":"Output"},{"unit":"1m_tokens","usd":"1","label":"Implicit cache read"},{"unit":"search","usd":"0.00825","label":"Web search"}],"limits":{"note":"Reasoning is always on and cannot be disabled. reasoning_effort accepts minimal through xhigh. On /v1/chat/completions the reasoning text is not returned; on /v1/responses you can request reasoning summaries with reasoning.summary, and reasoning tokens are billed as output tokens and count against the output budget either way. Text, image, MP4 video, and PDF inputs are supported; up to 50 images can be attached. Audio input is not supported on this checkpoint; the Muse Spark 1.1 and 1.2 checkpoints accept audio. PDFs use text from the first 100 pages and page images from the first 50 pages. Built-in web search adds $0.00825 per executed search query and reports the count in usage.tool_usage. OpenAI Responses requests also support custom tools and deferred tool search. tool_choice supports auto and none. Prompts and completions sent to this Standard checkpoint are not used by Meta to train its models.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape. Exact field names, units, and which tools appear can vary by tool:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3}\n}\n```\n\nThe tool counts are already factored into `cost_usd` and are surfaced so you can audit per-tool billing. The field is omitted when no billed tool was invoked."},"notes":"Reasoning is always on and cannot be disabled. reasoning_effort accepts minimal through xhigh. On /v1/chat/completions the reasoning text is not returned; on /v1/responses you can request reasoning summaries with reasoning.summary, and reasoning tokens are billed as output tokens and count against the output budget either way. Text, image, MP4 video, and PDF inputs are supported; up to 50 images can be attached. Audio input is not supported on this checkpoint; the Muse Spark 1.1 and 1.2 checkpoints accept audio. PDFs use text from the first 100 pages and page images from the first 50 pages. Built-in web search adds $0.00825 per executed search query and reports the count in usage.tool_usage. OpenAI Responses requests also support custom tools and deferred tool search. tool_choice supports auto and none. Prompts and completions sent to this Standard checkpoint are not used by Meta to train its models.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=muse-spark-1-3","api_url":"https://docs.empiriolabs.ai/models/muse-spark-1-3","logo":"https://media.empiriolabs.ai/model-logos/muse-spark-1-1.png","status":"available"},{"id":"tts-2-flash","object":"model","created":1788307200,"owned_by":"inworld","display_name":"TTS 2 Flash","author":"inworld","provider":"inworld","description":"Latency-first realtime voice synthesis holding one voice identity across 200+ languages, tuned for high-volume streaming workloads.","modality":"audio","type":"tts","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["multi_speaker","real_time","low_latency","streaming","word_timestamps","character_timestamps","multilingual"],"aliases":["inworld-tts-2-flash"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-09-02","is_new":false,"is_featured":true,"discount":{"label":"Save up to 30%","percent":30},"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Text to synthesize. Max 2,000 characters per request; chunk longer copy at sentence boundaries on the client. This model does not apply bracketed delivery direction; use TTS 2 when you need it.","required":true,"metadata":{},"max":2000},{"name":"voice","label":"Voice","type":"enum","description":"Voice preset. 20 hand-picked voices covering English, Spanish, Portuguese, Hindi, and various accents. For the full voice catalog, use voice_id instead.","required":false,"metadata":{},"default":"Sarah","options":["Sarah","Olivia","Elizabeth","Ashley","Wendy","Julia","Priya","Pixie","Deborah","Alex","Mark","Edward","Theodore","Ronald","Dennis","Timothy","Shaun","Craig","Hades","Heitor"]},{"name":"voice_id","label":"Voice ID","type":"string","description":"Free-form voice ID. Overrides voice when set. Use this to address any voice beyond the curated 20-preset list, including regional voices. Pass any voice name from GET /v1/voices. Example: Ashley, Mark.","required":false,"metadata":{}},{"name":"language","label":"Language","type":"enum","description":"BCP-47 language code. This model holds one voice identity across 200+ languages and locales, so you can pass any supported code here even if it is not in the dropdown.","required":false,"metadata":{},"default":"en-US","options":["en-US","en-GB","es-ES","es-MX","fr-FR","de-DE","it-IT","pt-BR","pt-PT","nl-NL","pl-PL","ru-RU","ja-JP","ko-KR","zh-CN","hi-IN","ar-EG","he-IL","tr-TR","vi-VN","th-TH","id-ID","uk-UA","el-GR","cs-CZ","sv-SE"]},{"name":"output_format","label":"Output format","type":"enum","description":"Audio container/codec. WAV = LINEAR16 inside RIFF (ubiquitous). MP3 / OGG = compressed. PCM = 16-bit PCM in a WAV header on POST /v1/audio/speech, headerless chunks on the stream. FLAC = lossless.","required":false,"metadata":{},"default":"WAV","options":["MP3","WAV","OGG","FLAC","PCM","ALAW","MULAW"]},{"name":"sample_rate","label":"Sample rate","type":"enum","description":"Output sample rate in Hz. 24000 is the default; use 48000 for broadcast quality.","required":false,"metadata":{},"default":"24000","options":["8000","16000","22050","24000","32000","44100","48000"]},{"name":"speed","label":"Speed","type":"number","description":"Speaking rate multiplier. 0.5 = half speed, 1.5 = 50% faster.","required":false,"metadata":{},"default":1,"min":0.5,"max":1.5},{"name":"temperature","label":"Temperature","type":"number","description":"Voice expressiveness / variability. Lower = more consistent / \"flat\"; higher = more expressive but more variation between renders.","required":false,"metadata":{},"default":1,"min":0.1,"max":2},{"name":"bit_rate","label":"Bit rate","type":"number","description":"Bitrate in bps for MP3 / OGG_OPUS. Ignored for other encodings.","required":false,"metadata":{},"default":128000,"min":32000,"max":320000},{"name":"apply_text_normalization","label":"Text normalization","type":"enum","description":"When ON, numbers, abbreviations and dates are expanded into spoken form (\"USD 5\" becomes \"five US dollars\").","required":false,"metadata":{},"default":"ON","options":["ON","OFF"]},{"name":"timestamp_type","label":"Timestamps","type":"enum","description":"If not NONE, the response includes per-word or per-character timestamps in timestamp_info, on POST /v1/audio/speech and on its stream. Useful for captions and highlighting.","required":false,"metadata":{},"default":"NONE","options":["NONE","WORD","CHARACTER"]}],"supported_endpoints":["POST /v1/audio/speech","POST /v1/audio/speech:stream","GET /v1/voices"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per 1M characters","label":"Synthesis","value":"$10.50 (was $15.00)"}],"unit_pricing":[{"unit":"1m_characters","usd":"10.5","label":"Synthesis"}],"limits":{"note":"**Limits**\n\n- Max input: 2,000 characters per request (chunk longer text at sentence boundaries)\n- WebSocket: 20 concurrent connections, 5 contexts/connection\n- Per-WS message: 1,000 characters\n\n**Voice direction**\n\n- This model does not apply bracketed plain-English delivery direction. Use TTS 2 when you need it, or shape delivery here with the `speed` and `temperature` controls.\n\n**Latency**\n\n- p90 TTFB: under 25 ms (Inworld benchmark)\n\n**Voices**\n\n- One voice identity held across 200+ languages and locales, including switching language mid-generation\n- Curated presets in the dropdown; pass any other voice ID via `voice_id`"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=tts-2-flash","api_url":"https://docs.empiriolabs.ai/models/tts-2-flash","logo":"https://media.empiriolabs.ai/model-logos/tts-2-flash.png","status":"available"},{"id":"deepseek-v4-1-flash-1017","object":"model","created":1792195200,"owned_by":"deepseek","display_name":"DeepSeek V4.1 Flash 1017","author":"deepseek","provider":"deepseek","description":"Post-trained 1017 release with stronger coding and agent results, faster task completion, shorter outputs, image input, and a 1M context window.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image"],"input_modalities":["text","image"],"output_modalities":["text"],"features":["reasoning","vision","function_calling","agentic_coding","cache"],"aliases":["deepseek-v4.1-flash-1017","deepseek/deepseek-v4-1-flash-1017","deepseek-ai/deepseek-v4-1-flash-1017","deepseek-v4-1-flash","deepseek-v4.1-flash","deepseek/deepseek-v4-1-flash","deepseek-ai/deepseek-v4-1-flash"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":393216,"model_released_at":"2026-10-17","is_new":true,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 2 = maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":393216},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable step-by-step reasoning before answering.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":32768,"min":1,"max":393216},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"control":"structured-output","so_tier":"json_object"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/deepseek-v4-1-flash-1017:generateContent"],"pricing":{"prompt":"0.0000002","completion":"0.0000008","image":"0","request":"0","input_cache_read":"0.00000002"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.20"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.80"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.02"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.2","label":"Input"},{"unit":"1m_tokens","usd":"0.8","label":"Output"},{"unit":"1m_tokens","usd":"0.02","label":"Implicit cache read"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Thinking is enabled by default and can be disabled. Reasoning tokens are billed as output tokens. Image input is accepted alongside text. JSON mode is supported. Strict JSON Schema output is not available on this model. Optional Linkup web search is billed only when invoked. From October 27, 2026, the deepseek-v4-1-flash model IDs are served by this model."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=deepseek-v4-1-flash-1017","api_url":"https://docs.empiriolabs.ai/models/deepseek-v4-1-flash-1017","logo":"https://media.empiriolabs.ai/model-logos/deepseek.png","status":"available"},{"id":"trellis-2-4b","object":"model","created":1735689600,"owned_by":"microsoft","display_name":"TRELLIS.2 4B","author":"microsoft","provider":"microsoft","description":"TRELLIS.2 image-to-3D model that turns a reference image into a textured GLB asset with resolution, seed, mesh, texture, and export controls.","modality":"3D","type":"generation","category":"3d","category_label":"3D","modality_label":"3D","modalities":["3D","image"],"input_modalities":["image"],"output_modalities":["3D"],"features":["image_to_3d","glb_output","pbr_materials","seed_control","commercial_ready"],"aliases":["microsoft/trellis.2-4b","trellis-2"],"structured_output":null,"native_inference":true,"weight_precision":"Mixed BF16/FP16","hugging_face_id":"microsoft/TRELLIS.2-4B","batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":true,"discount":{"label":"Save up to 90%","percent":90},"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":true,"reasoning":false},"supported_parameters":[{"name":"image","label":"Image","type":"string","description":"Reference image URL, data URI, or uploaded image object.","required":true,"metadata":{"ui":{"accept":"image/*","control":"file","section":"Input","hide_in_playground":true}}},{"name":"resolution","label":"Resolution","type":"enum","description":"Voxel grid resolution. Higher values are slower and more detailed. Ignored when pipeline_type is set.","required":false,"metadata":{"ui":{"control":"segmented","section":"Generation"}},"default":"1024","options":["512","1024","1536"]},{"name":"pipeline_type","label":"Pipeline Type","type":"enum","description":"Generation path. When set, it overrides resolution.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Generation"}},"default":"1024_cascade","options":["512","1024_cascade","1536_cascade"]},{"name":"seed","label":"Seed","type":"number","description":"Random seed for reproducible generations.","required":false,"metadata":{"ui":{"control":"number","section":"Generation"}},"default":42,"min":0,"max":2147483647},{"name":"preprocess_image","label":"Preprocess Image","type":"boolean","description":"Remove background and normalize the reference image before generation.","required":false,"metadata":{"ui":{"control":"toggle","section":"Input"}},"default":true},{"name":"max_num_tokens","label":"Max Sparse Tokens","type":"number","description":"Maximum sparse tokens used for cascade generation.","required":false,"metadata":{"ui":{"step":1024,"control":"slider","section":"Advanced generation"}},"default":49152,"min":1024,"max":131072},{"name":"ss_sampling_steps","label":"Sparse Structure Steps","type":"number","description":"Sampler steps for sparse structure generation.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Sparse structure"}},"default":12,"min":1,"max":64},{"name":"ss_guidance_strength","label":"Sparse Structure Guidance","type":"number","description":"Guidance strength for sparse structure generation.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Sparse structure"}},"default":7.5,"min":0,"max":20},{"name":"ss_guidance_rescale","label":"Sparse Structure Rescale","type":"number","description":"Guidance rescale for sparse structure generation.","required":false,"metadata":{"ui":{"step":0.05,"control":"slider","section":"Sparse structure"}},"default":0.7,"min":0,"max":2},{"name":"ss_guidance_interval_start","label":"Sparse Guidance Start","type":"number","description":"Start of the sparse-structure guidance interval.","required":false,"metadata":{"ui":{"step":0.05,"control":"slider","section":"Sparse structure"}},"default":0.6,"min":0,"max":1},{"name":"ss_guidance_interval_end","label":"Sparse Guidance End","type":"number","description":"End of the sparse-structure guidance interval.","required":false,"metadata":{"ui":{"step":0.05,"control":"slider","section":"Sparse structure"}},"default":1,"min":0,"max":1},{"name":"ss_rescale_t","label":"Sparse Rescale T","type":"number","description":"Rescale temperature for sparse structure generation.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Sparse structure"}},"default":5,"min":0,"max":20},{"name":"shape_slat_sampling_steps","label":"Shape SLat Steps","type":"number","description":"Sampler steps for shape structured latent generation.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Shape SLat"}},"default":12,"min":1,"max":64},{"name":"shape_slat_guidance_strength","label":"Shape SLat Guidance","type":"number","description":"Guidance strength for shape structured latent generation.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Shape SLat"}},"default":7.5,"min":0,"max":20},{"name":"shape_slat_guidance_rescale","label":"Shape SLat Rescale","type":"number","description":"Guidance rescale for shape structured latent generation.","required":false,"metadata":{"ui":{"step":0.05,"control":"slider","section":"Shape SLat"}},"default":0.5,"min":0,"max":2},{"name":"shape_slat_guidance_interval_start","label":"Shape Guidance Start","type":"number","description":"Start of the shape SLat guidance interval.","required":false,"metadata":{"ui":{"step":0.05,"control":"slider","section":"Shape SLat"}},"default":0.6,"min":0,"max":1},{"name":"shape_slat_guidance_interval_end","label":"Shape Guidance End","type":"number","description":"End of the shape SLat guidance interval.","required":false,"metadata":{"ui":{"step":0.05,"control":"slider","section":"Shape SLat"}},"default":1,"min":0,"max":1},{"name":"shape_slat_rescale_t","label":"Shape Rescale T","type":"number","description":"Rescale temperature for shape structured latent generation.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Shape SLat"}},"default":3,"min":0,"max":20},{"name":"tex_slat_sampling_steps","label":"Texture SLat Steps","type":"number","description":"Sampler steps for texture structured latent generation.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Texture SLat"}},"default":12,"min":1,"max":64},{"name":"tex_slat_guidance_strength","label":"Texture SLat Guidance","type":"number","description":"Guidance strength for texture structured latent generation.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Texture SLat"}},"default":1,"min":0,"max":20},{"name":"tex_slat_guidance_rescale","label":"Texture SLat Rescale","type":"number","description":"Guidance rescale for texture structured latent generation.","required":false,"metadata":{"ui":{"step":0.05,"control":"slider","section":"Texture SLat"}},"default":0,"min":0,"max":2},{"name":"tex_slat_guidance_interval_start","label":"Texture Guidance Start","type":"number","description":"Start of the texture SLat guidance interval.","required":false,"metadata":{"ui":{"step":0.05,"control":"slider","section":"Texture SLat"}},"default":0.6,"min":0,"max":1},{"name":"tex_slat_guidance_interval_end","label":"Texture Guidance End","type":"number","description":"End of the texture SLat guidance interval.","required":false,"metadata":{"ui":{"step":0.05,"control":"slider","section":"Texture SLat"}},"default":0.9,"min":0,"max":1},{"name":"tex_slat_rescale_t","label":"Texture Rescale T","type":"number","description":"Rescale temperature for texture structured latent generation.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Texture SLat"}},"default":3,"min":0,"max":20},{"name":"texture_size","label":"Texture Size","type":"enum","description":"Texture resolution baked onto the GLB material.","required":false,"metadata":{"ui":{"control":"segmented","section":"Export"}},"default":"2048","options":["1024","2048","4096"]},{"name":"decimation_target","label":"Decimation Target","type":"number","description":"Approximate target vertex count for the exported mesh.","required":false,"metadata":{"ui":{"step":10000,"control":"slider","section":"Export"}},"default":500000,"min":10000,"max":1000000},{"name":"remesh","label":"Remesh","type":"boolean","description":"Rebuild mesh topology before UV unwrapping and texture baking.","required":false,"metadata":{"ui":{"control":"toggle","section":"Export"}},"default":true},{"name":"remesh_band","label":"Remesh Band","type":"number","description":"Remeshing band size.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Advanced export"},"visible_when":{"op":"eq","field":"remesh","value":true}},"default":1,"min":0,"max":5},{"name":"remesh_project","label":"Remesh Project","type":"number","description":"Projection factor used during remeshing.","required":false,"metadata":{"ui":{"step":0.05,"control":"slider","section":"Advanced export"},"visible_when":{"op":"eq","field":"remesh","value":true}},"default":0.9,"min":0,"max":1},{"name":"uv_unwrap_angle_threshold_deg","label":"UV Angle Threshold","type":"number","description":"Cone half-angle threshold used for UV unwrap clustering.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Advanced export"}},"default":90,"min":1,"max":180},{"name":"uv_unwrap_refine_iterations","label":"UV Refine Iterations","type":"number","description":"UV clustering refinement iterations.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Advanced export"}},"default":0,"min":0,"max":10},{"name":"uv_unwrap_global_iterations","label":"UV Global Iterations","type":"number","description":"Global UV clustering iterations.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Advanced export"}},"default":1,"min":0,"max":10},{"name":"uv_unwrap_smooth_strength","label":"UV Smooth Strength","type":"number","description":"UV cluster smoothing strength.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Advanced export"}},"default":1,"min":0,"max":10},{"name":"response_format","label":"Response Format","type":"enum","description":"Return a signed media URL by default, or base64 JSON when requested.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Output"}},"default":"url","options":["url","b64_json"]},{"name":"return_base64","label":"Return Base64","type":"boolean","description":"Compatibility alias for response_format=b64_json.","required":false,"metadata":{"aliases":["b64_json"],"visible_when":{"op":"eq","field":"response_format","value":"b64_json"}},"default":false}],"supported_endpoints":["POST /v1/3d/generations"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0.025","input_cache_read":"0"},"pricing_rows":[{"spec":"per request","label":"512 asset","value":"$0.025 (was $0.25)"},{"spec":"per request","label":"1024 asset","value":"$0.249 (was $0.30)"},{"spec":"per request","label":"1536 asset","value":"$0.499"}],"unit_pricing":[{"unit":"request","usd":"0.025","label":"512 asset"},{"unit":"request","usd":"0.249","label":"1024 asset"},{"unit":"request","usd":"0.499","label":"1536 asset"}],"limits":{"note":"**Defaults**\n\n- 1024 cascade pipeline\n- 12 sampler steps per stage\n- 2048 texture size\n- 500k decimation target\n- GLB output\n\n**Controls**\n\nSupports image URL or upload, 512/1024/1536 resolution, seed, pipeline type, sampler guidance/interval/rescale controls, texture size, mesh decimation, remeshing, UV unwrap tuning, and URL or base64 output. Billing is per generated 3D asset."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=trellis-2-4b","api_url":"https://docs.empiriolabs.ai/models/trellis-2-4b","logo":"https://media.empiriolabs.ai/model-logos/trellis-2-4b.png","status":"available"},{"id":"qwen3-5-122b-a10b","object":"model","created":1771891200,"owned_by":"alibaba","display_name":"Qwen3.5 122B-A10B","author":"alibaba","provider":"alibaba","description":"Qwen3.5 122B-A10B is a multimodal reasoning model with 256K context, efficient sparse MoE inference, and text, image, and video input.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","web_search","function_calling","multimodal"],"aliases":["qwen3.5-122b-a10b"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":258048,"context_length":258048,"max_output_tokens":64000,"model_released_at":"2026-02-24","is_new":false,"is_featured":false,"discount":{"label":"Save up to 71%","percent":71},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":64000},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":81920},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"}},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.01 to the request cost when enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_request":0.01}},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-5-122b-a10b:generateContent"],"pricing":[{"prompt":"0.000000115","completion":"0.000000917","image":"0","request":"0","input_cache_read":"0.000000115"},{"prompt":"0.000000287","completion":"0.000002294","image":"0","request":"0","input_cache_read":"0.000000287","min_context":128000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=128K $0.115 (was $0.40); 128K-256K $0.287 (was $0.40)"},{"spec":"per 1M generated tokens","label":"Output","value":"<=128K $0.917 (was $3.20); 128K-256K $2.294 (was $3.20)"},{"spec":"per request when enabled","label":"Web search","value":"$0.01"}],"unit_pricing":[{"unit":"request","usd":"0.01","label":"Web search"}],"limits":{"note":"Supports text, image, and video input. Web search is available through tool_web_search and adds $0.01 per request when enabled. Thinking tokens are billed as output tokens."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-5-122b-a10b","api_url":"https://docs.empiriolabs.ai/models/qwen3-5-122b-a10b","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-5-397b-a17b","object":"model","created":1771200000,"owned_by":"alibaba","display_name":"Qwen3.5 397B-A17B","author":"alibaba","provider":"alibaba","description":"Qwen3.5 397B-A17B is a flagship multimodal reasoning model for language, code, agents, GUI tasks, and image and video understanding.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","web_search","function_calling","multimodal"],"aliases":["qwen3.5-397b-a17b"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":258048,"context_length":258048,"max_output_tokens":64000,"model_released_at":"2026-02-16","deprecation_date":"2027-01-18","deprecated":true,"is_new":false,"is_featured":false,"discount":{"label":"Save up to 71%","percent":71},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":64000},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":81920},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"}},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.01 to the request cost when enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_request":0.01}},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-5-397b-a17b:generateContent"],"pricing":[{"prompt":"0.000000172","completion":"0.000001032","image":"0","request":"0","input_cache_read":"0.000000172"},{"prompt":"0.00000043","completion":"0.00000258","image":"0","request":"0","input_cache_read":"0.00000043","min_context":128000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=128K $0.172 (was $0.60); 128K-256K $0.43 (was $0.60)"},{"spec":"per 1M generated tokens","label":"Output","value":"<=128K $1.032 (was $3.60); 128K-256K $2.58 (was $3.60)"},{"spec":"per request when enabled","label":"Web search","value":"$0.01"}],"unit_pricing":[{"unit":"request","usd":"0.01","label":"Web search"}],"limits":{"note":"Supports text, image, and video input. Web search is available through tool_web_search and adds $0.01 per request when enabled. Thinking tokens are billed as output tokens."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-5-397b-a17b","api_url":"https://docs.empiriolabs.ai/models/qwen3-5-397b-a17b","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-5-35b-a3b","object":"model","created":1771891200,"owned_by":"alibaba","display_name":"Qwen3.5 35B-A3B","author":"alibaba","provider":"alibaba","description":"Qwen3.5 35B-A3B is an efficient native vision-language model with sparse MoE routing, deep thinking, and text, image, and video input.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","web_search","function_calling","multimodal"],"aliases":["qwen3.5-35b-a3b"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":258048,"context_length":258048,"max_output_tokens":64000,"model_released_at":"2026-02-24","is_new":false,"is_featured":false,"discount":{"label":"Save up to 77%","percent":77},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":64000},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":81920},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"}},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.01 to the request cost when enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_request":0.01}},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-5-35b-a3b:generateContent"],"pricing":[{"prompt":"0.000000057","completion":"0.000000459","image":"0","request":"0","input_cache_read":"0.000000057"},{"prompt":"0.000000229","completion":"0.000001835","image":"0","request":"0","input_cache_read":"0.000000229","min_context":128000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=128K $0.057 (was $0.25); 128K-256K $0.229 (was $0.25)"},{"spec":"per 1M generated tokens","label":"Output","value":"<=128K $0.459 (was $2.00); 128K-256K $1.835 (was $2.00)"},{"spec":"per request when enabled","label":"Web search","value":"$0.01"}],"unit_pricing":[{"unit":"request","usd":"0.01","label":"Web search"}],"limits":{"note":"Supports text, image, and video input. Web search is available through tool_web_search and adds $0.01 per request when enabled. Thinking tokens are billed as output tokens."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-5-35b-a3b","api_url":"https://docs.empiriolabs.ai/models/qwen3-5-35b-a3b","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-5-27b","object":"model","created":1771891200,"owned_by":"alibaba","display_name":"Qwen3.5 27B","author":"alibaba","provider":"alibaba","description":"Qwen3.5 27B is a dense multimodal reasoning model with fast responses, 256K context, and text, image, and video understanding.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","web_search","function_calling","multimodal"],"aliases":["qwen3.5-27b"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":258048,"context_length":258048,"max_output_tokens":64000,"model_released_at":"2026-02-24","is_new":false,"is_featured":false,"discount":{"label":"Save up to 71%","percent":71},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":64000},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":81920},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"}},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.01 to the request cost when enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_request":0.01}},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-5-27b:generateContent"],"pricing":[{"prompt":"0.000000086","completion":"0.000000688","image":"0","request":"0","input_cache_read":"0.000000086"},{"prompt":"0.000000258","completion":"0.000002064","image":"0","request":"0","input_cache_read":"0.000000258","min_context":128000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=128K $0.086 (was $0.30); 128K-256K $0.258 (was $0.30)"},{"spec":"per 1M generated tokens","label":"Output","value":"<=128K $0.688 (was $2.40); 128K-256K $2.064 (was $2.40)"},{"spec":"per request when enabled","label":"Web search","value":"$0.01"}],"unit_pricing":[{"unit":"request","usd":"0.01","label":"Web search"}],"limits":{"note":"Supports text, image, and video input. Web search is available through tool_web_search and adds $0.01 per request when enabled. Thinking tokens are billed as output tokens."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-5-27b","api_url":"https://docs.empiriolabs.ai/models/qwen3-5-27b","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-8-27b","object":"model","created":1786665600,"owned_by":"alibaba","display_name":"Qwen3.8 27B","author":"alibaba","provider":"alibaba","description":"Multimodal reasoner with 256K context, image and video input, function tools, structured JSON, and thinking on by default.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","video","function_calling","cache","multimodal","json_mode","logprobs"],"aliases":["qwen3.8-27b","qwen/qwen3-8-27b","qwen/qwen3.8-27b"],"structured_output":"json_schema","native_inference":true,"weight_precision":"NVFP4 weights + FP8 KV","hugging_face_id":"Inferact/Qwen3.8-27B-NVFP4","batch_supported":null,"batch_discount_pct":null,"context_window":262144,"context_length":262144,"max_output_tokens":32768,"model_released_at":"2026-08-14","is_new":false,"is_featured":true,"discount":{"label":"Save up to 84%","percent":84},"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 2 is maximum randomness.","required":false,"metadata":{},"default":1,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.95,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":32768,"min":1,"max":32768},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, and xhigh select discrete thinking depths. There is no token budget control.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"}},"default":"xhigh","options":["none","low","medium","xhigh"]},{"name":"top_k","label":"Top K","type":"number","description":"Limit sampling to the top K candidate tokens when supported.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"default":20,"min":1},{"name":"min_p","label":"Min P","type":"number","description":"Minimum probability threshold for token sampling.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":0,"min":0,"max":1},{"name":"frequency_penalty","label":"Frequency Penalty","type":"number","description":"Penalty based on how often a token has already appeared.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":0,"min":-2,"max":2},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":0,"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":1,"min":0.1},{"name":"seed","label":"Seed","type":"number","description":"Optional random seed for reproducible sampling.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return token log probabilities when supported.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"}},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many top token log probabilities.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"min":0,"max":20},{"name":"logit_bias","label":"Logit Bias","type":"string","description":"Bias token IDs by adding positive or negative values before sampling.","required":false,"metadata":{"ui":{"control":"json","section":"Sampling"}}},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function tool definitions.","required":false,"metadata":{"ui":{"control":"json","section":"Tools"}}},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible function tool selection.","required":false,"metadata":{"ui":{"control":"json","section":"Tools"}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1/completions","POST /v1beta/models/qwen3-8-27b:generateContent"],"pricing":{"prompt":"0.00000017","completion":"0.0000005","image":"0","request":"0","input_cache_read":"0.00000008"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.17 (was $0.45)"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.50 (was $3.20)"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.08"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.17","label":"Input"},{"unit":"1m_tokens","usd":"0.5","label":"Output"},{"unit":"1m_tokens","usd":"0.08","label":"Implicit cache read"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Supports text, image, and video input, streaming, function tools, structured JSON output, seed control, and thinking mode on by default. Use reasoning_effort (xhigh, medium, low) or enable_thinking=false for direct answers. Automatic cache reads are billed at the cached-input rate when reported by the model service. Explicit cache controls are not supported. Open-weight context is 256K; hosted 1M context and official built-in tools are not included."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-8-27b","api_url":"https://docs.empiriolabs.ai/models/qwen3-8-27b","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available","datacenters":[{"country_code":"DE"}]},{"id":"qwen3-6-27b","object":"model","created":1776816000,"owned_by":"alibaba","display_name":"Qwen3.6 27B","author":"alibaba","provider":"alibaba","description":"Qwen3.6 27B improves agentic coding, STEM reasoning, spatial vision, OCR, and text, image, and video understanding on 256K context.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","web_search","function_calling","multimodal"],"aliases":["qwen3.6-27b"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":229376,"context_length":229376,"max_output_tokens":64000,"model_released_at":"2026-04-22","is_new":false,"is_featured":false,"discount":{"label":"Save up to 31%","percent":31},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":64000},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":131072},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"}},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.01 to the request cost when enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_request":0.01}},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-6-27b:generateContent"],"pricing":{"prompt":"0.000000412564","completion":"0.000002475384","image":"0","request":"0","input_cache_read":"0.000000412564"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.412564 (was $0.60)"},{"spec":"per 1M generated tokens","label":"Output","value":"$2.475384 (was $3.60)"},{"spec":"per request when enabled","label":"Web search","value":"$0.01"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.412564","label":"Input"},{"unit":"1m_tokens","usd":"2.475384","label":"Output"},{"unit":"request","usd":"0.01","label":"Web search"}],"limits":{"note":"Supports text, image, and video input. Web search is available through tool_web_search and adds $0.01 per request when enabled. Thinking tokens are billed as output tokens."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-6-27b","api_url":"https://docs.empiriolabs.ai/models/qwen3-6-27b","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-6-flash","object":"model","created":1776297600,"owned_by":"alibaba","display_name":"Qwen3.6 Flash","author":"alibaba","provider":"alibaba","description":"Fast Qwen3.6 vision-language model for agentic coding, math reasoning, spatial understanding, OCR, and text, image, and video input.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","video","web_search","function_calling","agentic_coding"],"aliases":["qwen3.6-flash"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":983616,"context_length":983616,"max_output_tokens":65536,"model_released_at":"2026-04-16","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":65536},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. With response_format, the model answers without reasoning unless the request sets enable_thinking. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":32768,"min":1,"max":64000},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"}},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}}},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.02 to the request cost when enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_query":0.02}},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-6-flash:generateContent"],"pricing":[{"prompt":"0.00000025","completion":"0.0000015","image":"0","request":"0","input_cache_read":"0.00000025"},{"prompt":"0.000001","completion":"0.000004","image":"0","request":"0","input_cache_read":"0.000001","min_context":256000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=256K $0.25; 256K-1M $1.00"},{"spec":"per 1M generated tokens","label":"Output","value":"<=256K $1.50; 256K-1M $4.00"},{"spec":"per request when enabled","label":"Web search","value":"$0.02"}],"unit_pricing":[{"unit":"request","usd":"0.02","label":"Web search"}],"limits":{"note":"Supports text, image, and video input. Web search is available through tool_web_search and adds $0.02 per request when enabled. Thinking tokens are billed as output tokens. Explicit cache controls are not supported."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-6-flash","api_url":"https://docs.empiriolabs.ai/models/qwen3-6-flash","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-6-flash:variant1","object":"model","created":1776297600,"owned_by":"alibaba","display_name":"Qwen3.6 Flash (Variant 1)","author":"alibaba","provider":"alibaba","description":"China-region Qwen3.6 Flash keeps the same vision, coding, reasoning, and video capabilities with lower token pricing than the Singapore standard route.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","video","web_search","function_calling","agentic_coding"],"aliases":[],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":"batch","batch_discount_pct":35,"context_window":983616,"context_length":983616,"max_output_tokens":65536,"model_released_at":"2026-04-16","is_new":false,"is_featured":true,"discount":{"label":"Save up to 34%","percent":34},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":65536},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. With response_format, the model answers without reasoning unless the request sets enable_thinking. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":32768,"min":1,"max":128000},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"}},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}}},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.01 to the request cost when enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_query":0.01}},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-6-flash:variant1:generateContent"],"pricing":[{"prompt":"0.000000165","completion":"0.00000099","image":"0","request":"0","input_cache_read":"0.000000165"},{"prompt":"0.00000066","completion":"0.000003961","image":"0","request":"0","input_cache_read":"0.00000066","min_context":256000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=256K $0.165 (was $0.25); 256K-1M $0.66 (was $1.00)"},{"spec":"per 1M generated tokens","label":"Output","value":"<=256K $0.99 (was $1.50); 256K-1M $3.961 (was $4.00)"},{"spec":"per request when enabled","label":"Web search","value":"$0.01"}],"unit_pricing":[{"unit":"request","usd":"0.01","label":"Web search"}],"limits":{"note":"Supports text, image, and video input. Web search is available through tool_web_search and adds $0.01 per request when enabled. Thinking tokens are billed as output tokens. Explicit cache controls are not supported."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-6-flash:variant1","api_url":"https://docs.empiriolabs.ai/models/qwen3-6-flash#variant1","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-6-plus:variant1","object":"model","created":1775088000,"owned_by":"alibaba","display_name":"Qwen3.6 Plus (Variant 1)","author":"alibaba","provider":"alibaba","description":"Qwen3.6 Plus is a state-of-the-art vision-language model for agentic coding, multimodal recognition, OCR, and object localization.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","video","web_search","function_calling","agentic_coding"],"aliases":[],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":"batch","batch_discount_pct":35,"context_window":983616,"context_length":983616,"max_output_tokens":65536,"model_released_at":"2026-04-02","is_new":false,"is_featured":true,"discount":{"label":"Save up to 45%","percent":45},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":65536},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. With response_format, the model answers without reasoning unless the request sets enable_thinking. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":32768,"min":1,"max":80000},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"}},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}}},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.01 to the request cost when enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_query":0.01}},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-6-plus:variant1:generateContent"],"pricing":[{"prompt":"0.000000276","completion":"0.000001651","image":"0","request":"0","input_cache_read":"0.000000276"},{"prompt":"0.000001101","completion":"0.000006602","image":"0","request":"0","input_cache_read":"0.000001101","min_context":256000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=256K $0.276 (was $0.50); 256K-1M $1.101 (was $2.00)"},{"spec":"per 1M generated tokens","label":"Output","value":"<=256K $1.651 (was $3.00); 256K-1M $6.602"},{"spec":"per request when enabled","label":"Web search","value":"$0.01"}],"unit_pricing":[{"unit":"request","usd":"0.01","label":"Web search"}],"limits":{"note":"Supports text, image, and video input. Web search is available through tool_web_search and adds $0.01 per request when enabled. Thinking tokens are billed as output tokens. Explicit cache controls are not supported."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-6-plus:variant1","api_url":"https://docs.empiriolabs.ai/models/qwen3-6-plus#variant1","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-5-plus:variant1","object":"model","created":1771200000,"owned_by":"alibaba","display_name":"Qwen3.5 Plus (Variant 1)","author":"alibaba","provider":"alibaba","description":"China-region Qwen3.5 Plus is a native vision-language model for efficient text, image, video, coding, and reasoning workloads.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","video","web_search","function_calling","agentic_coding"],"aliases":[],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":"batch","batch_discount_pct":35,"context_window":983616,"context_length":983616,"max_output_tokens":65536,"model_released_at":"2026-02-16","deprecation_date":"2027-01-18","deprecated":true,"is_new":false,"is_featured":true,"discount":{"label":"Save up to 69%","percent":69},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":65536},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. With response_format, the model answers without reasoning unless the request sets enable_thinking. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":32768,"min":1,"max":80000},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"}},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}}},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.01 to the request cost when enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_query":0.01}},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-5-plus:variant1:generateContent"],"pricing":[{"prompt":"0.000000115","completion":"0.000000688","image":"0","request":"0","input_cache_read":"0.000000115"},{"prompt":"0.000000287","completion":"0.00000172","image":"0","request":"0","input_cache_read":"0.000000287","min_context":128000},{"prompt":"0.000000573","completion":"0.00000344","image":"0","request":"0","input_cache_read":"0.000000573","min_context":256000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=128K $0.115 (was $0.36); 128K-256K $0.287 (was $0.36); 256K-1M $0.573"},{"spec":"per 1M generated tokens","label":"Output","value":"<=128K $0.688 (was $2.21); 128K-256K $1.72 (was $2.21); 256K-1M $3.44"},{"spec":"per request when enabled","label":"Web search","value":"$0.01"}],"unit_pricing":[{"unit":"request","usd":"0.01","label":"Web search"}],"limits":{"note":"Supports text, image, and video input. Web search is available through tool_web_search and adds $0.01 per request when enabled. Thinking tokens are billed as output tokens. Explicit cache controls are not supported."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-5-plus:variant1","api_url":"https://docs.empiriolabs.ai/models/qwen3-5-plus#variant1","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-5-flash:variant1","object":"model","created":1771891200,"owned_by":"alibaba","display_name":"Qwen3.5 Flash (Variant 1)","author":"alibaba","provider":"alibaba","description":"China-region Qwen3.5 Flash delivers fast native vision-language inference for text, image, video, coding, and reasoning tasks.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","video","web_search","function_calling","agentic_coding"],"aliases":[],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":"batch","batch_discount_pct":35,"context_window":995904,"context_length":995904,"max_output_tokens":65536,"model_released_at":"2026-02-24","is_new":false,"is_featured":true,"discount":{"label":"Save up to 68%","percent":68},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":65536},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. With response_format, the model answers without reasoning unless the request sets enable_thinking. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":32768,"min":1,"max":80000},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"}},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Vision"}}},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"ui":{"control":"number","section":"Vision"},"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"default":2,"min":0.1,"max":10},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.01 to the request cost when enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_query":0.01}},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-5-flash:variant1:generateContent"],"pricing":[{"prompt":"0.000000029","completion":"0.000000287","image":"0","request":"0","input_cache_read":"0.000000029"},{"prompt":"0.000000115","completion":"0.000001147","image":"0","request":"0","input_cache_read":"0.000000115","min_context":128000},{"prompt":"0.000000172","completion":"0.00000172","image":"0","request":"0","input_cache_read":"0.000000172","min_context":256000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=128K $0.029 (was $0.090); 128K-256K $0.115; 256K-1M $0.172"},{"spec":"per 1M generated tokens","label":"Output","value":"<=128K $0.287 (was $0.368); 128K-256K $1.147; 256K-1M $1.72"},{"spec":"per request when enabled","label":"Web search","value":"$0.01"}],"unit_pricing":[{"unit":"request","usd":"0.01","label":"Web search"}],"limits":{"note":"Supports text, image, and video input. Web search is available through tool_web_search and adds $0.01 per request when enabled. Thinking tokens are billed as output tokens. Explicit cache controls are not supported."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-5-flash:variant1","api_url":"https://docs.empiriolabs.ai/models/qwen3-5-flash#variant1","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"gemma-4-26b-a4b","object":"model","created":1774915200,"owned_by":"google","display_name":"Gemma 4 26B-A4B","author":"google","provider":"google","description":"Gemma 4 26B A4B is a Google open multimodal model with 256K context, text, image, and video input, tools, and structured output.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","video","function_calling","cache","multimodal","json_mode","logprobs"],"aliases":["gemma-4-26b-a4b-it","google/gemma-4-26b-a4b","google/gemma-4-26b-a4b-it"],"structured_output":"json_schema","native_inference":true,"weight_precision":"FP8 weights + FP8 KV","hugging_face_id":"google/gemma-4-26B-A4B-it","batch_supported":null,"batch_discount_pct":null,"context_window":262144,"context_length":262144,"max_output_tokens":32768,"model_released_at":"2026-03-31","is_new":false,"is_featured":false,"discount":{"label":"Save up to 83%","percent":83},"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 2 is maximum randomness.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Model"}},"default":1,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Model"}},"default":0.95,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted: 8,192 at low and medium reasoning effort, 9,216 at high, and 32,768 at max or with thinking off.","required":false,"metadata":{"ui":{"control":"number","section":"Model"}},"default":8192,"min":1,"max":32768},{"name":"stop","label":"Stop","type":"string","description":"One or more stop strings.","required":false,"metadata":{"ui":{"control":"text","section":"Model"},"control":"stop-sequences"}},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"}},"default":"medium","options":["none","low","medium","high","max"]},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. With response_format, the model answers without reasoning unless the request sets enable_thinking.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When max_tokens is lower, room is kept for the answer; a very low max_tokens can be spent entirely on reasoning.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":4096,"min":128,"max":32768},{"name":"top_k","label":"Top K","type":"number","description":"Limit sampling to the top K candidate tokens when supported.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"default":20,"min":1},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":0,"min":-2,"max":2},{"name":"frequency_penalty","label":"Frequency Penalty","type":"number","description":"Penalty based on how often a token has already appeared.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":0,"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":1,"min":0.1},{"name":"seed","label":"Seed","type":"number","description":"Optional random seed for reproducible sampling.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return token log probabilities when supported.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"}},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many top token log probabilities.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"min":0,"max":20},{"name":"logit_bias","label":"Logit Bias","type":"string","description":"Bias token IDs by adding positive or negative values before sampling.","required":false,"metadata":{"ui":{"control":"json","section":"Sampling"}}},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function tool definitions.","required":false,"metadata":{"ui":{"control":"json","section":"Tools"}}},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible function tool selection.","required":false,"metadata":{"ui":{"control":"json","section":"Tools"}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1/completions","POST /v1beta/models/gemma-4-26b-a4b:generateContent"],"pricing":{"prompt":"0.00000005","completion":"0.00000029","image":"0","request":"0","input_cache_read":"0.000000025"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.05 (was $0.15)"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.29 (was $0.50)"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.025 (was $0.15)"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.05","label":"Input"},{"unit":"1m_tokens","usd":"0.29","label":"Output"},{"unit":"1m_tokens","usd":"0.025","label":"Implicit cache read"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Supports text, image, and video input, streaming, function tools, structured JSON output, seed control, and thinking mode on by default. Use reasoning_effort or thinking_budget for bounded thinking, or enable_thinking=false for direct answers. Automatic cache reads are billed at the cached-input rate when reported by the model service. Explicit cache controls are not supported."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=gemma-4-26b-a4b","api_url":"https://docs.empiriolabs.ai/models/gemma-4-26b-a4b","logo":"https://media.empiriolabs.ai/model-logos/gemma.png","status":"available","datacenters":[{"country_code":"AU"}]},{"id":"muse-glimmer-30b","object":"model","created":1786320000,"owned_by":"meta","display_name":"Muse Glimmer 30B","author":"meta","provider":"meta","description":"Meta open 30B agentic model with image understanding, 128K context, tool calling, structured output, and controllable reasoning strength.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image"],"input_modalities":["text","image"],"output_modalities":["text"],"features":["reasoning","vision","multimodal","function_calling","json_mode","cache"],"aliases":["meta/muse-glimmer-30b","muse-glimmer","meta-models/muse-glimmer-30b"],"structured_output":"json_schema","native_inference":true,"weight_precision":"NVFP4 weights + FP8 KV","hugging_face_id":"RadixArk/Muse-Glimmer-NVFP4","batch_supported":null,"batch_discount_pct":null,"context_window":131072,"context_length":131072,"max_output_tokens":32768,"model_released_at":"2026-08-10","is_new":false,"is_featured":false,"discount":{"label":"Save up to 47%","percent":47},"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and higher values are more random.","required":false,"metadata":{},"default":1,"min":0},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.95,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":32768,"min":1,"max":32768},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning strength level. Higher levels think longer before answering. none requests minimal thinking and max maps to the model's xhigh strength.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"}},"default":"high","options":["none","low","medium","high","max"]},{"name":"top_k","label":"Top K","type":"number","description":"Limit sampling to the top K candidate tokens when supported.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"default":64,"min":1},{"name":"min_p","label":"Min P","type":"number","description":"Minimum probability threshold for token sampling.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":0,"min":0,"max":1},{"name":"frequency_penalty","label":"Frequency Penalty","type":"number","description":"Penalty based on how often a token has already appeared.","required":false,"metadata":{"ui":{"control":"slider","section":"Advanced sampling"}},"default":0,"min":-2,"max":2},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text.","required":false,"metadata":{"ui":{"control":"slider","section":"Advanced sampling"}},"default":0,"min":-2,"max":2},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"},"options":["text","json_object","json_schema"]},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1/completions","POST /v1beta/models/muse-glimmer-30b:generateContent"],"pricing":{"prompt":"0.0000002","completion":"0.0000008","image":"0","request":"0","input_cache_read":"0.00000005"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.20 (was $0.35)"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.80 (was $1.50)"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.05"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.2","label":"Input"},{"unit":"1m_tokens","usd":"0.8","label":"Output"},{"unit":"1m_tokens","usd":"0.05","label":"Implicit cache read"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Supports text and image input, streaming, function tools, structured JSON output, and reasoning strength control through reasoning_effort (none, low, medium, high, max). Reasoning defaults to high."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=muse-glimmer-30b","api_url":"https://docs.empiriolabs.ai/models/muse-glimmer-30b","logo":"https://media.empiriolabs.ai/model-logos/muse-spark-1-1.png","status":"available","datacenters":[{"country_code":"TW"}]},{"id":"qwen3-5-9b","object":"model","created":1771804800,"owned_by":"alibaba","display_name":"Qwen3.5 9B","author":"alibaba","provider":"alibaba","description":"Qwen3.5 9B is a compact multimodal reasoning model with 256K context, image and video input, function tools, and structured output.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","video","function_calling","cache","multimodal","json_mode","logprobs"],"aliases":["qwen3.5-9b"],"structured_output":"json_schema","native_inference":true,"weight_precision":"FP8 weights + FP8 KV","hugging_face_id":"Qwen/Qwen3.5-9B","batch_supported":null,"batch_discount_pct":null,"context_window":262144,"context_length":262144,"max_output_tokens":32768,"model_released_at":"2026-02-23","is_new":false,"is_featured":false,"discount":{"label":"Save up to 13%","percent":13},"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 2 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.95,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted: 8,192 at low and medium reasoning effort, 9,216 at high, and 32,768 at max or with thinking off.","required":false,"metadata":{},"default":8192,"min":1,"max":32768},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"}},"default":"medium","options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When max_tokens is lower, room is kept for the answer; a very low max_tokens can be spent entirely on reasoning.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":4096,"min":1024,"max":32768},{"name":"top_k","label":"Top K","type":"number","description":"Limit sampling to the top K candidate tokens when supported.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"default":20,"min":1},{"name":"frequency_penalty","label":"Frequency Penalty","type":"number","description":"Penalty based on how often a token has already appeared.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":0,"min":-2,"max":2},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":0,"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":1,"min":0.1},{"name":"seed","label":"Seed","type":"number","description":"Optional random seed for reproducible sampling.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return token log probabilities when supported.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"}},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many top token log probabilities.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"min":0,"max":20},{"name":"logit_bias","label":"Logit Bias","type":"string","description":"Bias token IDs by adding positive or negative values before sampling.","required":false,"metadata":{"ui":{"control":"json","section":"Sampling"}}},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function tool definitions.","required":false,"metadata":{"ui":{"control":"json","section":"Tools"}}},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible function tool selection.","required":false,"metadata":{"ui":{"control":"json","section":"Tools"}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1/completions","POST /v1beta/models/qwen3-5-9b:generateContent"],"pricing":{"prompt":"0.00000009","completion":"0.00000013","image":"0","request":"0","input_cache_read":"0.000000045"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.09 (was $0.10)"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.13 (was $0.15)"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.045"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.09","label":"Input"},{"unit":"1m_tokens","usd":"0.13","label":"Output"},{"unit":"1m_tokens","usd":"0.045","label":"Implicit cache read"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Supports text, image, and video input, streaming, function tools, structured JSON output, seed control, and thinking mode on by default. Use reasoning_effort or thinking_budget for bounded thinking, or enable_thinking=false for direct answers. Automatic cache reads are billed at the cached-input rate when reported by the model service. Explicit cache controls are not supported."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-5-9b","api_url":"https://docs.empiriolabs.ai/models/qwen3-5-9b","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available","datacenters":[{"country_code":"AU"}]},{"id":"qwen3-5-4b","object":"model","created":1772409600,"owned_by":"alibaba","display_name":"Qwen3.5 4B","author":"alibaba","provider":"alibaba","description":"Qwen3.5 4B is a low-cost multimodal reasoning model with 256K context, image and video input, function tools, and structured output.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","video","function_calling","cache","multimodal","json_mode","logprobs"],"aliases":["qwen3.5-4b"],"structured_output":"json_schema","native_inference":true,"weight_precision":"FP8 weights + FP8 KV","hugging_face_id":"Qwen/Qwen3.5-4B","batch_supported":null,"batch_discount_pct":null,"context_window":262144,"context_length":262144,"max_output_tokens":32768,"model_released_at":"2026-03-02","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 2 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.95,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted: 8,192 at low and medium reasoning effort, 9,216 at high, and 32,768 at max or with thinking off.","required":false,"metadata":{},"default":8192,"min":1,"max":32768},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"}},"default":"medium","options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When max_tokens is lower, room is kept for the answer; a very low max_tokens can be spent entirely on reasoning.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":4096,"min":1024,"max":32768},{"name":"top_k","label":"Top K","type":"number","description":"Limit sampling to the top K candidate tokens when supported.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"default":20,"min":1},{"name":"min_p","label":"Min P","type":"number","description":"Minimum probability threshold for token sampling.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":0,"min":0,"max":1},{"name":"frequency_penalty","label":"Frequency Penalty","type":"number","description":"Penalty based on how often a token has already appeared.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":0,"min":-2,"max":2},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":0,"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":1,"min":0.1},{"name":"seed","label":"Seed","type":"number","description":"Optional random seed for reproducible sampling.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return token log probabilities when supported.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"}},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many top token log probabilities.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"min":0,"max":20},{"name":"logit_bias","label":"Logit Bias","type":"string","description":"Bias token IDs by adding positive or negative values before sampling.","required":false,"metadata":{"ui":{"control":"json","section":"Sampling"}}},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function tool definitions.","required":false,"metadata":{"ui":{"control":"json","section":"Tools"}}},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible function tool selection.","required":false,"metadata":{"ui":{"control":"json","section":"Tools"}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1/completions","POST /v1beta/models/qwen3-5-4b:generateContent"],"pricing":{"prompt":"0.00000004","completion":"0.00000007","image":"0","request":"0","input_cache_read":"0.00000002"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.04"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.07"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.02"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.04","label":"Input"},{"unit":"1m_tokens","usd":"0.07","label":"Output"},{"unit":"1m_tokens","usd":"0.02","label":"Implicit cache read"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Supports text, image, and video input, streaming, function tools, structured JSON output, seed control, and thinking mode on by default. Use reasoning_effort or thinking_budget for bounded thinking, or enable_thinking=false for direct answers. Automatic cache reads are billed at the cached-input rate when reported by the model service. Explicit cache controls are not supported."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-5-4b","api_url":"https://docs.empiriolabs.ai/models/qwen3-5-4b","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available","datacenters":[{"country_code":"EE"}]},{"id":"qwen3-6-35b-a3b","object":"model","created":1776297600,"owned_by":"alibaba","display_name":"Qwen3.6 35B A3B","author":"alibaba","provider":"alibaba","description":"Qwen3.6 35B A3B is a 256-expert mixture-of-experts reasoning model with 128K context, function tools, and strict structured JSON output.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","function_calling","json_mode","cache"],"aliases":["qwen3.6-35b-a3b","qwen/qwen3.6-35b-a3b","EschaLabs/Qwen3.6-35B-A3B-Escha-W2"],"structured_output":"json_schema","native_inference":true,"weight_precision":"eschamoe W2: 2-bit weights + INT8 dense + FP16 KV","hugging_face_id":"EschaLabs/Qwen3.6-35B-A3B-Escha-W2","batch_supported":null,"batch_discount_pct":null,"context_window":131072,"context_length":131072,"max_output_tokens":16384,"model_released_at":"2026-04-16","is_new":false,"is_featured":false,"discount":{"label":"Save up to 72%","percent":72},"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and higher values are more random.","required":false,"metadata":{},"default":0.7,"min":0},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.95,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":16384,"min":1,"max":16384},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort. none disables thinking. Any other value enables it.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"}},"default":"medium","options":["none","low","medium","high","max"]},{"name":"top_k","label":"Top K","type":"number","description":"Limit sampling to the top K candidate tokens when supported.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"default":20,"min":1},{"name":"min_p","label":"Min P","type":"number","description":"Minimum probability threshold for token sampling.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":0,"min":0,"max":1},{"name":"frequency_penalty","label":"Frequency Penalty","type":"number","description":"Penalty based on how often a token has already appeared.","required":false,"metadata":{"ui":{"control":"slider","section":"Advanced sampling"}},"default":0,"min":-2,"max":2},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text.","required":false,"metadata":{"ui":{"control":"slider","section":"Advanced sampling"}},"default":0,"min":-2,"max":2},{"name":"seed","label":"Seed","type":"number","description":"Optional random seed for reproducible sampling.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"},"options":["text","json_object","json_schema"]},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1/completions","POST /v1beta/models/qwen3-6-35b-a3b:generateContent"],"pricing":{"prompt":"0.00000007","completion":"0.00000042","image":"0","request":"0","input_cache_read":"0.000000035"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.07 (was $0.248)"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.42 (was $1.485)"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.035"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.07","label":"Input"},{"unit":"1m_tokens","usd":"0.42","label":"Output"},{"unit":"1m_tokens","usd":"0.035","label":"Implicit cache read"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Text-only. This build does not accept image or video input, unlike the base Qwen3.6 35B A3B.\n\n**Weights**\n\nServed from the 2-bit eschamoe W2 build published by Escha Labs (eschalabs.com) as EschaLabs/Qwen3.6-35B-A3B-Escha-W2 on Hugging Face, under Apache-2.0. The experts are quantized to 2 bits, mixed per projection (gate_up_proj at 2-bit and down_proj at 3-bit), the dense layers are int8, and the KV cache is FP16. Escha Labs publishes the quality comparison against an FP8 baseline of the same model: parity or better on math, graduate science, tool use and long context, about 2 percent lower on broad knowledge, and about 7 percent lower on long-horizon code generation, which is the one clear gap. See the model card for the full benchmark table and protocol.\n\n**Behavior**\n\nSupports streaming, function tools, structured JSON output including strict schemas, and thinking mode on by default. Set enable_thinking=false for direct answers. With thinking on, the reasoning arrives in reasoning_content and the answer in content, so read both. A low max_tokens with thinking on can be spent entirely on reasoning, so allow room for the answer.\n\n**Caching**\n\nAutomatic prefix cache reads are billed at the cached-input rate when reported. Explicit cache controls are not supported. Cancelling a streaming request mid-generation bills only the tokens produced up to that point."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-6-35b-a3b","api_url":"https://docs.empiriolabs.ai/models/qwen3-6-35b-a3b","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available","datacenters":[{"country_code":"CA"}]},{"id":"glm-4-7-flash","object":"model","created":1768780800,"owned_by":"zhipu","display_name":"GLM 4.7 Flash","author":"zhipu","provider":"zhipu","description":"Free lightweight GLM-4.7 text model for coding, reasoning, long-context writing, and general chat.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","function_calling","web_search"],"aliases":["glm-4.7-flash","zai/glm-4.7-flash","zhipu/glm-4.7-flash"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":202752,"context_length":202752,"max_output_tokens":131072,"model_released_at":"2026-01-19","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. Lower values are more deterministic.","required":false,"metadata":{},"default":1,"min":0,"max":1},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling cutoff.","required":false,"metadata":{},"default":0.95,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Stop word list. Z.AI currently supports one stop string in array form.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"do_sample","label":"Sample Output","type":"boolean","description":"Enable sampling. When false, temperature and top_p do not affect generation.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Turns thinking on or off. On by default, and the model thinks; turn it off for simple low-latency turns.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"thinking","label":"Thinking Object","type":"string","description":"Advanced thinking object. Use {\"type\":\"enabled\"} or {\"type\":\"disabled\"}. The model thinks when enabled.","required":false,"metadata":{}},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":false},{"name":"tools","label":"Tools","type":"string","description":"Function tools and the built-in web_search tool are supported.","required":false,"metadata":{}},{"name":"tool_choice","label":"Tool Choice","type":"enum","description":"Only auto is supported. Omit tools to disable tool use.","required":false,"metadata":{},"default":"auto","options":["auto"]},{"name":"tool_stream","label":"Tool streaming","type":"boolean","description":"Stream function-call tool output when stream is true. Z.AI documents tool_stream for GLM-4.6 and newer models.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable built-in web search. Adds $0.033 per request when enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_request":0.033}},"default":false},{"name":"search_result","label":"Return Search Results","type":"boolean","description":"Return structured web search result metadata when web search is enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":true},{"name":"search_prompt","label":"Search Prompt","type":"string","description":"Optional instruction for summarizing retrieved web search results.","required":false,"metadata":{"ui":{"control":"textarea","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}}},{"name":"count","label":"Search Result Count","type":"number","description":"Number of web search results to retrieve.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":10,"min":1,"max":50},{"name":"search_domain_filter","label":"Search Domain Filter","type":"string","description":"Optional domain whitelist for web search results.","required":false,"metadata":{"ui":{"control":"input","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}}},{"name":"search_recency_filter","label":"Search Recency Filter","type":"enum","description":"Optional web search recency window.","required":false,"metadata":{"ui":{"control":"select","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":"noLimit","options":["oneDay","oneWeek","oneMonth","oneYear","noLimit"]},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/glm-4-7-flash:generateContent"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"Free"},{"spec":"per 1M generated tokens","label":"Output","value":"Free"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"Free"},{"spec":"per request when enabled","label":"Web search","value":"$0.033"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0","label":"Input"},{"unit":"1m_tokens","usd":"0","label":"Output"},{"unit":"1m_tokens","usd":"0","label":"Implicit cache read"},{"unit":"request","usd":"0.033","label":"Web search"}],"limits":{"note":"Base token use is free. Built-in web search is optional through tool_web_search and adds $0.033 per request when enabled."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=glm-4-7-flash","api_url":"https://docs.empiriolabs.ai/models/glm-4-7-flash","logo":"https://media.empiriolabs.ai/model-logos/glm.png","status":"available"},{"id":"glm-4-5-flash","object":"model","created":1753660800,"owned_by":"zhipu","display_name":"GLM 4.5 Flash","author":"zhipu","provider":"zhipu","description":"Free lightweight GLM-4.5 text model for reasoning, coding, long-form chat, and general language tasks.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","function_calling","web_search"],"aliases":["glm-4.5-flash","zai/glm-4.5-flash","zhipu/glm-4.5-flash"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":131072,"context_length":131072,"max_output_tokens":98304,"model_released_at":"2025-07-28","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. Lower values are more deterministic.","required":false,"metadata":{},"default":0.6,"min":0,"max":1},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling cutoff.","required":false,"metadata":{},"default":0.95,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":98304},{"name":"stop","label":"Stop","type":"string","description":"Stop word list. Z.AI currently supports one stop string in array form.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"do_sample","label":"Sample Output","type":"boolean","description":"Enable sampling. When false, temperature and top_p do not affect generation.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Turns thinking on or off. On by default; when on, the model decides whether to think.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"thinking","label":"Thinking Object","type":"string","description":"Advanced thinking object. Use {\"type\":\"enabled\"} or {\"type\":\"disabled\"}. When enabled, the model decides whether to think.","required":false,"metadata":{}},{"name":"tools","label":"Tools","type":"string","description":"Function tools and the built-in web_search tool are supported.","required":false,"metadata":{}},{"name":"tool_choice","label":"Tool Choice","type":"enum","description":"Only auto is supported. Omit tools to disable tool use.","required":false,"metadata":{},"default":"auto","options":["auto"]},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable built-in web search. Adds $0.033 per request when enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_request":0.033}},"default":false},{"name":"search_result","label":"Return Search Results","type":"boolean","description":"Return structured web search result metadata when web search is enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":true},{"name":"search_prompt","label":"Search Prompt","type":"string","description":"Optional instruction for summarizing retrieved web search results.","required":false,"metadata":{"ui":{"control":"textarea","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}}},{"name":"count","label":"Search Result Count","type":"number","description":"Number of web search results to retrieve.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":10,"min":1,"max":50},{"name":"search_domain_filter","label":"Search Domain Filter","type":"string","description":"Optional domain whitelist for web search results.","required":false,"metadata":{"ui":{"control":"input","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}}},{"name":"search_recency_filter","label":"Search Recency Filter","type":"enum","description":"Optional web search recency window.","required":false,"metadata":{"ui":{"control":"select","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":"noLimit","options":["oneDay","oneWeek","oneMonth","oneYear","noLimit"]},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/glm-4-5-flash:generateContent"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"Free"},{"spec":"per 1M generated tokens","label":"Output","value":"Free"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"Free"},{"spec":"per request when enabled","label":"Web search","value":"$0.033"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0","label":"Input"},{"unit":"1m_tokens","usd":"0","label":"Output"},{"unit":"1m_tokens","usd":"0","label":"Implicit cache read"},{"unit":"request","usd":"0.033","label":"Web search"}],"limits":{"note":"Base token use is free. Built-in web search is optional through tool_web_search and adds $0.033 per request when enabled."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=glm-4-5-flash","api_url":"https://docs.empiriolabs.ai/models/glm-4-5-flash","logo":"https://media.empiriolabs.ai/model-logos/glm.png","status":"available"},{"id":"glm-4-7-flashx","object":"model","created":1768780800,"owned_by":"zhipu","display_name":"GLM 4.7 FlashX","author":"zhipu","provider":"zhipu","description":"High-speed GLM-4.7 text model for coding, reasoning, long-context writing, and chat, with 200K context, function calling, and web search.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","function_calling","web_search","cache"],"aliases":["glm-4.7-flashx","zai/glm-4.7-flashx","zhipu/glm-4.7-flashx"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":202752,"context_length":202752,"max_output_tokens":131072,"model_released_at":"2026-01-19","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. Lower values are more deterministic.","required":false,"metadata":{},"default":1,"min":0,"max":1},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling cutoff.","required":false,"metadata":{},"default":0.95,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Stop word list. Z.AI currently supports one stop string in array form.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"do_sample","label":"Sample Output","type":"boolean","description":"Enable sampling. When false, temperature and top_p do not affect generation.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Turns thinking on or off. On by default, and the model thinks; turn it off for simple low-latency turns.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"thinking","label":"Thinking Object","type":"string","description":"Advanced thinking object. Use {\"type\":\"enabled\"} or {\"type\":\"disabled\"}. The model thinks when enabled.","required":false,"metadata":{}},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":false},{"name":"tools","label":"Tools","type":"string","description":"Function tools and the built-in web_search tool are supported.","required":false,"metadata":{}},{"name":"tool_choice","label":"Tool Choice","type":"enum","description":"Only auto is supported. Omit tools to disable tool use.","required":false,"metadata":{},"default":"auto","options":["auto"]},{"name":"tool_stream","label":"Tool streaming","type":"boolean","description":"Stream function-call tool output when stream is true. Z.AI documents tool_stream for GLM-4.6 and newer models.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable built-in web search. Adds $0.033 per request when enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_request":0.033}},"default":false},{"name":"search_result","label":"Return Search Results","type":"boolean","description":"Return structured web search result metadata when web search is enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":true},{"name":"search_prompt","label":"Search Prompt","type":"string","description":"Optional instruction for summarizing retrieved web search results.","required":false,"metadata":{"ui":{"control":"textarea","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}}},{"name":"count","label":"Search Result Count","type":"number","description":"Number of web search results to retrieve.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":10,"min":1,"max":50},{"name":"search_domain_filter","label":"Search Domain Filter","type":"string","description":"Optional domain whitelist for web search results.","required":false,"metadata":{"ui":{"control":"input","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}}},{"name":"search_recency_filter","label":"Search Recency Filter","type":"enum","description":"Optional web search recency window.","required":false,"metadata":{"ui":{"control":"select","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":"noLimit","options":["oneDay","oneWeek","oneMonth","oneYear","noLimit"]},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/glm-4-7-flashx:generateContent"],"pricing":{"prompt":"0.00000007","completion":"0.0000004","image":"0","request":"0","input_cache_read":"0.000000063"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.07"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.40"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.063"},{"spec":"per request when enabled","label":"Web search","value":"$0.033"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.07","label":"Input"},{"unit":"1m_tokens","usd":"0.4","label":"Output"},{"unit":"1m_tokens","usd":"0.063","label":"Implicit cache read"},{"unit":"request","usd":"0.033","label":"Web search"}],"limits":{"note":"Built-in web search is optional through tool_web_search and adds $0.033 per request when enabled."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=glm-4-7-flashx","api_url":"https://docs.empiriolabs.ai/models/glm-4-7-flashx","logo":"https://media.empiriolabs.ai/model-logos/glm.png","status":"available"},{"id":"glm-4-6v-flash","object":"model","created":1765152000,"owned_by":"zhipu","display_name":"GLM 4.6V Flash","author":"zhipu","provider":"zhipu","description":"Free multimodal GLM-4.6V model for image, video, file, and text understanding with native function calling.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video","file"],"input_modalities":["text","image","video","file"],"output_modalities":["text"],"features":["vision","video_understanding","document_understanding","function_calling","web_search","reasoning"],"aliases":["glm-4.6v-flash","zai/glm-4.6v-flash","zhipu/glm-4.6v-flash"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":131072,"context_length":131072,"max_output_tokens":32768,"model_released_at":"2025-12-08","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. Lower values are more deterministic.","required":false,"metadata":{},"default":1,"min":0,"max":1},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling cutoff.","required":false,"metadata":{},"default":0.95,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":32768},{"name":"stop","label":"Stop","type":"string","description":"Stop word list. Z.AI currently supports one stop string in array form.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"do_sample","label":"Sample Output","type":"boolean","description":"Enable sampling. When false, temperature and top_p do not affect generation.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Turns thinking on or off. On by default; when on, the model decides whether to think.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"thinking","label":"Thinking Object","type":"string","description":"Advanced thinking object. Use {\"type\":\"enabled\"} or {\"type\":\"disabled\"}. When enabled, the model decides whether to think.","required":false,"metadata":{}},{"name":"tools","label":"Tools","type":"string","description":"Function tools and the built-in web_search tool are supported.","required":false,"metadata":{}},{"name":"tool_choice","label":"Tool Choice","type":"enum","description":"Only auto is supported. Omit tools to disable tool use.","required":false,"metadata":{},"default":"auto","options":["auto"]},{"name":"tool_stream","label":"Tool streaming","type":"boolean","description":"Stream function-call tool output when stream is true. Z.AI documents tool_stream for GLM-4.6 and newer models.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable built-in web search. Adds $0.033 per request when enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_request":0.033}},"default":false},{"name":"search_result","label":"Return Search Results","type":"boolean","description":"Return structured web search result metadata when web search is enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":true},{"name":"search_prompt","label":"Search Prompt","type":"string","description":"Optional instruction for summarizing retrieved web search results.","required":false,"metadata":{"ui":{"control":"textarea","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}}},{"name":"count","label":"Search Result Count","type":"number","description":"Number of web search results to retrieve.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":10,"min":1,"max":50},{"name":"search_domain_filter","label":"Search Domain Filter","type":"string","description":"Optional domain whitelist for web search results.","required":false,"metadata":{"ui":{"control":"input","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}}},{"name":"search_recency_filter","label":"Search Recency Filter","type":"enum","description":"Optional web search recency window.","required":false,"metadata":{"ui":{"control":"select","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":"noLimit","options":["oneDay","oneWeek","oneMonth","oneYear","noLimit"]},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/glm-4-6v-flash:generateContent"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"Free"},{"spec":"per 1M generated tokens","label":"Output","value":"Free"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"Free"},{"spec":"per request when enabled","label":"Web search","value":"$0.033"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0","label":"Input"},{"unit":"1m_tokens","usd":"0","label":"Output"},{"unit":"1m_tokens","usd":"0","label":"Implicit cache read"},{"unit":"request","usd":"0.033","label":"Web search"}],"limits":{"note":"Base token use is free. Built-in web search is optional through tool_web_search and adds $0.033 per request when enabled."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=glm-4-6v-flash","api_url":"https://docs.empiriolabs.ai/models/glm-4-6v-flash","logo":"https://media.empiriolabs.ai/model-logos/glm.png","status":"available"},{"id":"glm-4-6v-flashx","object":"model","created":1735689600,"owned_by":"zhipu","display_name":"GLM 4.6V FlashX","author":"zhipu","provider":"zhipu","description":"High-speed GLM-4.6V vision model for image, video, file, and text understanding, with 128K context and native function calling.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video","file"],"input_modalities":["text","image","video","file"],"output_modalities":["text"],"features":["vision","video_understanding","document_understanding","function_calling","web_search","reasoning","cache"],"aliases":["glm-4.6v-flashx","zai/glm-4.6v-flashx","zhipu/glm-4.6v-flashx"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":131072,"context_length":131072,"max_output_tokens":32768,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. Lower values are more deterministic.","required":false,"metadata":{},"default":1,"min":0,"max":1},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling cutoff.","required":false,"metadata":{},"default":0.95,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":32768},{"name":"stop","label":"Stop","type":"string","description":"Stop word list. Z.AI currently supports one stop string in array form.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"do_sample","label":"Sample Output","type":"boolean","description":"Enable sampling. When false, temperature and top_p do not affect generation.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Turns thinking on or off. On by default; when on, the model decides whether to think.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"thinking","label":"Thinking Object","type":"string","description":"Advanced thinking object. Use {\"type\":\"enabled\"} or {\"type\":\"disabled\"}. When enabled, the model decides whether to think.","required":false,"metadata":{}},{"name":"tools","label":"Tools","type":"string","description":"Function tools and the built-in web_search tool are supported.","required":false,"metadata":{}},{"name":"tool_choice","label":"Tool Choice","type":"enum","description":"Only auto is supported. Omit tools to disable tool use.","required":false,"metadata":{},"default":"auto","options":["auto"]},{"name":"tool_stream","label":"Tool streaming","type":"boolean","description":"Stream function-call tool output when stream is true. Z.AI documents tool_stream for GLM-4.6 and newer models.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable built-in web search. Adds $0.033 per request when enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_request":0.033}},"default":false},{"name":"search_result","label":"Return Search Results","type":"boolean","description":"Return structured web search result metadata when web search is enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":true},{"name":"search_prompt","label":"Search Prompt","type":"string","description":"Optional instruction for summarizing retrieved web search results.","required":false,"metadata":{"ui":{"control":"textarea","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}}},{"name":"count","label":"Search Result Count","type":"number","description":"Number of web search results to retrieve.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":10,"min":1,"max":50},{"name":"search_domain_filter","label":"Search Domain Filter","type":"string","description":"Optional domain whitelist for web search results.","required":false,"metadata":{"ui":{"control":"input","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}}},{"name":"search_recency_filter","label":"Search Recency Filter","type":"enum","description":"Optional web search recency window.","required":false,"metadata":{"ui":{"control":"select","section":"Tools"},"visible_when":{"op":"eq","field":"tool_web_search","value":true}},"default":"noLimit","options":["oneDay","oneWeek","oneMonth","oneYear","noLimit"]},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/glm-4-6v-flashx:generateContent"],"pricing":{"prompt":"0.00000004","completion":"0.0000004","image":"0","request":"0","input_cache_read":"0.000000036"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.04"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.40"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.036"},{"spec":"per request when enabled","label":"Web search","value":"$0.033"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.04","label":"Input"},{"unit":"1m_tokens","usd":"0.4","label":"Output"},{"unit":"1m_tokens","usd":"0.036","label":"Implicit cache read"},{"unit":"request","usd":"0.033","label":"Web search"}],"limits":{"note":"Built-in web search is optional through tool_web_search and adds $0.033 per request when enabled."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=glm-4-6v-flashx","api_url":"https://docs.empiriolabs.ai/models/glm-4-6v-flashx","logo":"https://media.empiriolabs.ai/model-logos/glm.png","status":"available"},{"id":"aplomb-1","object":"model","created":1790640000,"owned_by":"empiriolabs","display_name":"Aplomb 1","author":"empiriolabs","provider":"empiriolabs","description":"Answers yes/no, choice, score and tool questions about text, JSON, images, video and audio in up to 1M tokens, and can tell when the input lacks the answer.","modality":"multimodal","type":"decision","category":"decision","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video","audio","decision"],"input_modalities":["text","image","video","audio"],"output_modalities":["decision"],"features":["classification","calibrated_probabilities","tool_selection","abstain","long_context","vision","video","audio_in","multimodal"],"aliases":["aplomb","empiriolabs/aplomb-1","empiriolabs/aplomb"],"structured_output":null,"native_inference":true,"weight_precision":"BF16 weights","hugging_face_id":"empiriolabsai/aplomb-1","batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":null,"model_released_at":"2026-09-29","is_new":true,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"long_context","label":"Long Context","type":"enum","description":"How a state longer than 131,072 tokens is read: fast (the default) answers in seconds, full reads every token. Shorter states are always read in full.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"fast","options":["fast","full"]}],"supported_endpoints":["POST /v1/decisions","POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/aplomb-1:generateContent"],"pricing":{"prompt":"0.00000002","completion":"0","image":"0","request":"0","input_cache_read":"0.00000002"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.02"},{"spec":"per 1M generated tokens","label":"Output","value":"Free"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.02","label":"Input"},{"unit":"1m_tokens","usd":"0","label":"Output"}],"limits":{"note":"**Requests**\n\nSend content in `state` (a string, a JSON object, or an array) and 1 to 128 questions in `questions` to `POST /v1/decisions`. Each question is answered on its own, with probabilities and a confidence value. No text is generated. The [Decisions API guide](https://docs.empiriolabs.ai/decisions) documents every question option, and its [Chat formats](https://docs.empiriolabs.ai/decisions#chat-formats) section covers requests through `/v1/chat/completions`, `/v1/responses`, `/v1/messages` and Gemini `generateContent`.\n\n**Question types**\n\n- `noul`: yes or no, answered with the probability of yes.\n- `choice`: one of 2 to 255 options, answered with the chosen option and the full distribution.\n- `score`: 2 to 10 ordered levels, answered with the expected level and the distribution.\n- `tool`: which of 1 to 254 function tools to call, with distributions over its enum and boolean arguments.\n\n**Not in the `state`**\n\nAdd `\"abstain\": true` to a `noul`, `choice` or `score` question to let the model say the state does not contain the answer. The answer then includes `abstain`, the probability of that outcome, and the rest of the answer assumes the state does contain it.\n\n**Limits**\n\n- The state plus the longest question: up to 1,000,000 tokens.\n- At most 512 evaluated questions per request. A tool question counts as one plus one per enum or boolean argument.\n- Media: up to 16 images (20 MB each), 8 audio clips (25 MB and 10 minutes each) and 4 videos (100 MB and 10 minutes each), as public HTTPS URLs or inline base64.\n\n**Benchmarks**\n\nBenchmark results are in the [launch post](https://empiriolabs.ai/blog/introducing-aplomb-1).\n\n**Billing**\n\nInput tokens only: the state once per request, each question's own text, and each media item's tokens. Output is always zero."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=aplomb-1","api_url":"https://docs.empiriolabs.ai/models/aplomb-1","logo":"https://media.empiriolabs.ai/model-logos/empiriolabs.png","status":"available","datacenters":[{"country_code":"US"}]},{"id":"deepgram-nova-3","object":"model","created":1739318400,"owned_by":"deepgram","display_name":"Deepgram Nova-3","author":"deepgram","provider":"deepgram","description":"Speech-to-text transcription using the Nova-3 model with multi-language support and advanced customizable settings for production workloads.","modality":"audio","type":"stt","category":"transcription","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio"],"output_modalities":["text"],"features":["transcription","speech_to_text"],"aliases":["deepgram/nova-3","nova-3"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-02-12","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"file","label":"File","type":"string","description":"Audio file (mp3, wav, m4a, ogg, etc.) uploaded as multipart/form-data.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"file_url","label":"File Url","type":"string","description":"URL of the audio to transcribe. Mutually exclusive with `file`.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"smart_format","label":"Smart Format","type":"boolean","description":"Apply smart formatting (capitalize, punctuate, format numbers/dates).","required":false,"metadata":{},"default":true},{"name":"profanity_filter","label":"Profanity Filter","type":"boolean","description":"Mask profane words in the transcript with ****.","required":false,"metadata":{},"default":false},{"name":"numerals","label":"Numerals","type":"boolean","description":"Convert spoken numbers to digits (e.g. \"five\" → \"5\").","required":false,"metadata":{},"default":true},{"name":"measurements","label":"Measurements","type":"boolean","description":"Convert measurement words to abbreviations (e.g. \"kilograms\" → \"kg\").","required":false,"metadata":{},"default":false},{"name":"language","label":"Language","type":"enum","description":"ISO 639-1 language code. Auto-detect if omitted.","required":false,"metadata":{},"default":"auto","options":["auto","en","es","fr","de","it","pt","ja","zh","hi","ru","nl"]},{"name":"redact_pii","label":"Redact Pii","type":"boolean","description":"Mask personally-identifiable information in the transcript.","required":false,"metadata":{},"default":false},{"name":"redact_pci","label":"Redact Pci","type":"boolean","description":"Mask payment card numbers in the transcript.","required":false,"metadata":{},"default":false},{"name":"keyterm","label":"Keyterm","type":"string","description":"Comma-separated key terms to boost recognition accuracy for (jargon, names).","required":false,"metadata":{}},{"name":"diarize","label":"Diarize","type":"boolean","description":"Identify different speakers and tag each utterance with a speaker label.","required":false,"metadata":{},"default":false},{"name":"paragraphs","label":"Paragraphs","type":"boolean","description":"Group output into paragraphs based on pauses and speaker turns.","required":false,"metadata":{},"default":true},{"name":"dictation","label":"Dictation","type":"boolean","description":"Interpret commands like \"period\", \"comma\", \"new line\" as punctuation/formatting.","required":false,"metadata":{},"default":false},{"name":"punctuate","label":"Punctuate","type":"boolean","description":"Add punctuation to the transcript.","required":false,"metadata":{},"default":true},{"name":"utterances","label":"Utterances","type":"boolean","description":"Return each utterance separately with timing and confidence.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/audio/transcriptions"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per minute of audio","label":"Transcription","value":"$0.014"}],"unit_pricing":[{"unit":"minute","usd":"0.014","label":"Transcription"}],"limits":{"note":"**Auto-detected languages**\n\nEnglish, Spanish, French, German, Italian, Portuguese, Japanese, Chinese, Hindi, Russian, Dutch.\n\n**Custom Key Terms**\n\n- English only, ≤500 tokens total\n- Improves recognition of domain-specific vocabulary\n\n**Feature interactions**\n\n- Diarization auto-enables utterances\n- Smart format and paragraphs auto-enable punctuation\n- PCI/PII redaction and profanity filter are off by default"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=deepgram-nova-3","api_url":"https://docs.empiriolabs.ai/models/deepgram-nova-3","logo":"https://media.empiriolabs.ai/model-logos/deepgram-nova-3.png","status":"available"},{"id":"deepreasoning","object":"model","created":1737849600,"owned_by":"winfunc","display_name":"DeepReasoning","author":"winfunc","provider":"winfunc","description":"Pairs DeepSeek R1 chain-of-thought reasoning with Anthropic Claude creative and code generation behind a unified, data-controlled interface.","modality":"text","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","thinking"],"aliases":[],"structured_output":"none","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":163840,"context_length":163840,"max_output_tokens":32000,"model_released_at":"2025-01-26","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. Applies to the R1 reasoning stage.","required":false,"metadata":{},"default":0.7,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling. Applies to the R1 reasoning stage.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens for the Claude synthesis stage.","required":false,"metadata":{},"default":8192,"min":1,"max":32000},{"name":"anthropic_model","label":"Claude Model","type":"enum","description":"Choose the Claude model to pair with DeepSeek R1 0528 reasoning. The R1 model produces the chain-of-thought; the Claude model synthesizes the final answer. Claude Opus 5.5 also thinks before it answers, and its thinking counts toward max_tokens. An unknown or retired model returns a 400 error that lists the models you can use.","required":false,"metadata":{},"default":"claude-sonnet-5-5","options":["claude-sonnet-5-5","claude-haiku-5-5","claude-opus-5-5"]},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/deepreasoning:generateContent"],"pricing":{"prompt":"0.0000048","completion":"0.000023","image":"0","request":"0","input_cache_read":"0.0000048"},"pricing_rows":[{"spec":"per 1K tokens","label":"R1-0528 + Claude Sonnet 5.5 (Default)","value":"In $0.012 / Out $0.058"},{"spec":"per 1K tokens","label":"R1-0528 + Claude Haiku 5.5","value":"In $0.0048 / Out $0.023"},{"spec":"per 1K tokens","label":"R1-0528 + Claude Opus 5.5","value":"In $0.019 / Out $0.092"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"R1-0528 reasoning paired with one of: Claude Sonnet 5.5 (default), Haiku 5.5, Opus 5.5."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=deepreasoning","api_url":"https://docs.empiriolabs.ai/models/deepreasoning","logo":"https://media.empiriolabs.ai/model-logos/deepreasoning.png","status":"available"},{"id":"deepseek-v4-pro","object":"model","created":1776988800,"owned_by":"deepseek","display_name":"DeepSeek V4 Pro","author":"deepseek","provider":"deepseek","description":"Flagship MoE LLM with 1.6T total / 49B active parameters and native 1M context for advanced math, logical inference, and specialized coding.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","function_calling"],"aliases":["deepseek/deepseek-v4-pro"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":393216,"model_released_at":"2026-04-24","is_new":false,"is_featured":true,"discount":{"label":"Save up to 5%","percent":5},"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 2 = maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":393216},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable step-by-step reasoning before answering.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":32768,"min":1,"max":393216},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/deepseek-v4-pro:generateContent"],"pricing":{"prompt":"0.00000165","completion":"0.0000033","image":"0","request":"0","input_cache_read":"0.00000165"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.65 (was $1.74)"},{"spec":"per 1M generated tokens","label":"Output","value":"$3.30 (was $3.48)"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.65","label":"Input"},{"unit":"1m_tokens","usd":"3.3","label":"Output"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":null,"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=deepseek-v4-pro","api_url":"https://docs.empiriolabs.ai/models/deepseek-v4-pro","logo":"https://media.empiriolabs.ai/model-logos/deepseek.png","status":"available"},{"id":"exa-answer","object":"model","created":1735689600,"owned_by":"exa","display_name":"Exa Answer","author":"exa","provider":"exa","description":"Quick LLM-style answer to a natural-language question, grounded in fresh Exa web search results with inline citations and source links.","modality":"text","type":"search","category":"research","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["web_search","answer_engine"],"aliases":[],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"query","label":"Query","type":"string","description":"The natural-language query to search/research/answer.","required":true,"metadata":{}},{"name":"text","label":"Source Text Snippets","type":"boolean","description":"Show short source text snippets in the answer.","required":false,"metadata":{},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added. The citations array is still returned.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/answer","POST /v1/search","POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/exa-answer:generateContent"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0.01","input_cache_read":"0"},"pricing_rows":[{"spec":"per request","label":"Answer","value":"$0.01"}],"unit_pricing":[{"unit":"request","usd":"0.01","label":"Answer"}],"limits":{"note":"LLM-style answer informed by Exa search results. For deeper analysis use Exa Research."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=exa-answer","api_url":"https://docs.empiriolabs.ai/models/exa-answer","logo":"https://media.empiriolabs.ai/model-logos/exa-answer.png","status":"available"},{"id":"exa-search","object":"model","created":1735689600,"owned_by":"exa","display_name":"Exa Search","author":"exa","provider":"exa","description":"Web search engine for finding pages, retrieving similar pages, crawling, and dedicated code search across the open web for AI agents.","modality":"text","type":"search","category":"research","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["web_search","semantic_search"],"aliases":[],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"query","label":"Query","type":"string","description":"Search query (or URL for ``similar``)","required":true,"metadata":{}},{"name":"operation","label":"Operation","type":"enum","description":"search runs a web search, similar finds pages like a given URL, contents returns the text of given URLs, and code returns code context for a query.","required":false,"metadata":{},"default":"search","options":["search","similar","contents","code"]},{"name":"search_type","label":"Search Type","type":"enum","description":"Search mode: auto, lite, deep-lite or deep. auto balances quality and speed, lite is the fastest and lowest priced, deep-lite runs a light multi-step search and deep a thorough one. lite takes only num_results, category, the domain and published-date filters, user_location, moderation, objective and the text and highlights options, and with text or highlights on it can return fewer results. Alias of type.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"search"},"clear_when_hidden":true},"default":"auto","options":["auto","lite","deep-lite","deep"]},{"name":"type","label":"Type","type":"enum","description":"Search mode: auto, lite, deep-lite or deep. auto balances quality and speed, lite is the fastest and lowest priced, deep-lite runs a light multi-step search and deep a thorough one. lite takes only num_results, category, the domain and published-date filters, user_location, moderation, objective and the text and highlights options, and with text or highlights on it can return fewer results.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"search"},"clear_when_hidden":true},"default":"auto","options":["auto","lite","deep-lite","deep"]},{"name":"num_results","label":"Num Results","type":"number","description":"How many results to return (1-100).","required":false,"metadata":{"visible_when":{"op":"in","field":"operation","values":["search","similar"]},"clear_when_hidden":true},"default":10,"min":1,"max":100},{"name":"category","label":"Category","type":"enum","description":"Restrict results to a category. company and people take no start_published_date or end_published_date, and people takes no exclude_domains.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"search"},"clear_when_hidden":true},"options":["company","publication","news","personal site","financial report","people"]},{"name":"include_domains","label":"Include Domains","type":"string","description":"Comma-separated allowlist of domains. Only results from these domains are returned (e.g. arxiv.org, github.com).","required":false,"metadata":{"visible_when":{"op":"in","field":"operation","values":["search","similar"]},"clear_when_hidden":true}},{"name":"exclude_domains","label":"Exclude Domains","type":"string","description":"Comma-separated denylist of domains to filter out of results. Not available with category people.","required":false,"metadata":{"hidden_when":{"op":"eq","field":"category","value":"people"},"visible_when":{"op":"in","field":"operation","values":["search","similar"]},"clear_when_hidden":true}},{"name":"user_location","label":"User Location","type":"string","description":"The end user's location, to localize results: a two-letter ISO 3166-1 country code such as US, or an object with country, latitude and longitude (decimal degrees). Coordinates apply to queries that depend on where the user is, such as nearby places, and set no country, so send country with them. Available with operation search.","required":false,"metadata":{"ui":{"placeholder":"US"},"visible_when":{"op":"eq","field":"operation","value":"search"},"clear_when_hidden":true}},{"name":"moderation","label":"Moderation","type":"boolean","description":"Filter unsafe content out of the results. Available with operation search.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"search"},"clear_when_hidden":true},"default":false},{"name":"start_published_date","label":"Start Published Date","type":"string","description":"Only return results published after this date. ISO 8601. Not available with category company or people.","required":false,"metadata":{"hidden_when":{"op":"in","field":"category","values":["company","people"]},"visible_when":{"op":"in","field":"operation","values":["search","similar"]},"clear_when_hidden":true}},{"name":"end_published_date","label":"End Published Date","type":"string","description":"Only return results published before this date. ISO 8601. Not available with category company or people.","required":false,"metadata":{"hidden_when":{"op":"in","field":"category","values":["company","people"]},"visible_when":{"op":"in","field":"operation","values":["search","similar"]},"clear_when_hidden":true}},{"name":"return_text","label":"Return Text","type":"boolean","description":"Return each result's full page text. Alias of text.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":true},{"name":"show_content","label":"Show Content","type":"boolean","description":"Return each result's full page text. Alias of text.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":true},{"name":"text","label":"Text","type":"boolean","description":"Return each result's full page text.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":true},{"name":"text_max_chars","label":"Text Max Chars","type":"number","description":"Cap on the cleaned-text length per result.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":2000,"min":100,"max":100000},{"name":"include_html_tags","label":"Include Html Tags","type":"boolean","description":"Keep HTML tags in the extracted text.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":false},{"name":"return_highlights","label":"Return Highlights","type":"boolean","description":"Get AI-selected key snippets from each result. Alias of highlights. Not used by operation code.","required":false,"metadata":{"visible_when":{"op":"in","field":"operation","values":["search","similar","contents"]},"clear_when_hidden":true},"default":false},{"name":"highlights","label":"Highlights","type":"boolean","description":"Include relevant text snippets (\"highlights\") per result. Not used by operation code.","required":false,"metadata":{"visible_when":{"op":"in","field":"operation","values":["search","similar","contents"]},"clear_when_hidden":true},"default":false},{"name":"highlights_query","label":"Highlights Query","type":"string","description":"Query used to score which sentences become highlights.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true}},{"name":"highlights_max_chars","label":"Highlights Max Chars","type":"number","description":"Maximum length of the highlights returned for each result, in characters.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":4000,"min":100,"max":100000},{"name":"return_summary","label":"Return Summary","type":"boolean","description":"Get an AI-generated summary of each result. Alias of summary. Not used by operation code, and not available with search_type lite.","required":false,"metadata":{"hidden_when":{"op":"eq","field":"search_type","value":"lite"},"visible_when":{"op":"in","field":"operation","values":["search","similar","contents"]},"clear_when_hidden":true},"default":false},{"name":"summary","label":"Summary","type":"boolean","description":"Return an LLM-generated summary of each result. Not used by operation code, and not available with search_type lite.","required":false,"metadata":{"hidden_when":{"op":"eq","field":"search_type","value":"lite"},"visible_when":{"op":"in","field":"operation","values":["search","similar","contents"]},"clear_when_hidden":true},"default":false},{"name":"summary_query","label":"Summary Query","type":"string","description":"Custom summary prompt (only when summary=True)","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true}},{"name":"max_age_hours","label":"Max Age Hours","type":"number","description":"Maximum age in hours of the page content returned, up to 720: an older cached copy is fetched again. 0 always fetches pages live and -1 uses only cached copies. When omitted, a cached copy is used where one exists and other pages are fetched live. Not available with search_type lite.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"min":-1,"max":720},{"name":"subpages","label":"Subpages","type":"number","description":"Number of related subpages to fetch alongside each main result.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":0,"min":0,"max":10},{"name":"subpage_target","label":"Subpage Target","type":"string","description":"Keyword guiding which subpages to fetch (e.g. \"pricing\").","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true}},{"name":"code_tokens","label":"Code Tokens","type":"enum","description":"Max tokens of code to include when scraping code-heavy pages.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"code"},"clear_when_hidden":true},"default":"dynamic","options":["dynamic","5000","10000","20000"]},{"name":"objective","label":"Objective","type":"string","description":"The goal this search serves, beyond the query: which documents should rank first, which to exclude and which facts or figures to pull from them. Up to 4,096 characters. Available with operation search.","required":false,"metadata":{"control":"textarea","visible_when":{"op":"eq","field":"operation","value":"search"},"clear_when_hidden":true}},{"name":"system_prompt","label":"System Prompt","type":"string","description":"Instructions for the search and its synthesized output, such as source preferences or how to treat duplicates. It guides the output of output_schema and the research steps of search_type deep-lite and deep. Available with operation search, and not with search_type lite.","required":false,"metadata":{"control":"textarea","hidden_when":{"op":"eq","field":"search_type","value":"lite"},"visible_when":{"op":"eq","field":"operation","value":"search"},"clear_when_hidden":true}},{"name":"additional_queries","label":"Additional Queries","type":"string","description":"Up to 10 more queries that search_type deep-lite and deep run beside the main query, each a distinct search direction, as a list or as text with one query per line. Available with search_type deep-lite and deep.","required":false,"metadata":{"control":"textarea","visible_when":[{"op":"eq","field":"operation","value":"search"},{"op":"in","field":"search_type","values":["deep-lite","deep"]}],"clear_when_hidden":true}},{"name":"output_schema","label":"Output Schema","type":"string","description":"Returns a synthesized output from the results: a JSON Schema of type text for prose, guided by its description, or of type object for JSON with the properties you define. The response's output carries the content and, for each field, its sources and confidence, and a text output is also returned as answer. An object schema takes at most 10 properties in all (nested and array item properties count) and 2 levels of nesting, and each array defines items. Available with operation search, and not with search_type lite.","required":false,"metadata":{"control":"textarea","hidden_when":{"op":"eq","field":"search_type","value":"lite"},"visible_when":{"op":"eq","field":"operation","value":"search"},"clear_when_hidden":true}},{"name":"summary_schema","label":"Summary Schema","type":"string","description":"A JSON Schema for each result's summary, which is then returned as a JSON string that matches it. Applies when summary is on. Not used by operation code, and not available with search_type lite.","required":false,"metadata":{"control":"textarea","visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true}},{"name":"text_verbosity","label":"Text Verbosity","type":"enum","description":"How much of each page the text returns: compact keeps the main content, standard adds more of the surrounding page, and full returns the most complete text. It applies to pages fetched live; set max_age_hours to 0 to fetch every page live. Not used by operation code.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":"compact","options":["compact","standard","full"]},{"name":"text_include_sections","label":"Text Include Sections","type":"string","description":"Return only the text of these page sections: header, navigation, banner, body, sidebar, footer or metadata, as a list or comma-separated. Section detection is best effort and applies to pages fetched live. Not used by operation code.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true}},{"name":"text_exclude_sections","label":"Text Exclude Sections","type":"string","description":"Leave the text of these page sections out: header, navigation, banner, body, sidebar, footer or metadata, as a list or comma-separated. Section detection is best effort and applies to pages fetched live. Not used by operation code.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true}},{"name":"extras_links","label":"Extras Links","type":"number","description":"Number of links to return from each result's page, from 0 to 1,000. Not used by operation code, and not available with search_type lite.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":0,"min":0,"max":1000},{"name":"extras_image_links","label":"Extras Image Links","type":"number","description":"Number of image URLs to return from each result's page, from 0 to 1,000. Not used by operation code, and not available with search_type lite.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":0,"min":0,"max":1000},{"name":"extras_rich_image_links","label":"Extras Rich Image Links","type":"number","description":"Number of images to return from each result's page with their alt text, in page order, from 0 to 1,000. Not used by operation code, and not available with search_type lite.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":0,"min":0,"max":1000},{"name":"extras_rich_links","label":"Extras Rich Links","type":"number","description":"Number of links to return from each page with their anchor text, in page order, from 0 to 1,000. Available with operation contents.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":0,"min":0,"max":1000},{"name":"extras_code_blocks","label":"Extras Code Blocks","type":"number","description":"Number of code blocks to return from each page, each with the language it is marked with, from 0 to 1,000. Available with operation contents.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":0,"min":0,"max":1000},{"name":"livecrawl_timeout","label":"Livecrawl Timeout","type":"number","description":"How long to wait for each page fetched live, in milliseconds, from 1 to 90,000. Not used by operation code, and not available with search_type lite.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":10000,"min":1,"max":90000},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the results as JSON instead of formatted Markdown.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/search"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per search","label":"Search, Auto (up to 10 results)","value":"$0.0084"},{"spec":"per search","label":"Search, Lite (up to 10 results)","value":"$0.0048"},{"spec":"per search","label":"Search, Deep Lite (up to 10 results)","value":"$0.0144"},{"spec":"per search","label":"Search, Deep (up to 10 results)","value":"$0.0144"},{"spec":"per search","label":"Find Similar (up to 10 results)","value":"$0.0048"},{"spec":"per page","label":"Each Result Above 10","value":"$0.0012"},{"spec":"per page","label":"Result Summary","value":"$0.0012"},{"spec":"per page","label":"Contents: Text, Highlights or Summary (each)","value":"$0.0012"},{"spec":"per code search","label":"Code Search","value":"$0.0048"}],"unit_pricing":[{"unit":"search","usd":"0.0084","label":"Search, Auto (up to 10 results)"},{"unit":"search","usd":"0.0048","label":"Search, Lite (up to 10 results)"},{"unit":"search","usd":"0.0144","label":"Search, Deep Lite (up to 10 results)"},{"unit":"search","usd":"0.0144","label":"Search, Deep (up to 10 results)"},{"unit":"search","usd":"0.0048","label":"Find Similar (up to 10 results)"},{"unit":"page","usd":"0.0012","label":"Each Result Above 10"},{"unit":"page","usd":"0.0012","label":"Result Summary"},{"unit":"page","usd":"0.0012","label":"Contents: Text, Highlights or Summary (each)"}],"limits":{"note":"**Operations**\n\n- search, similar pages, contents, code search\n\n**Search types**\n\n- Auto (default), Lite (fastest, lowest price), Deep Lite, Deep\n\n**Categories**\n\n- Company, Publication, News, Personal Site, Financial Report, People"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=exa-search","api_url":"https://docs.empiriolabs.ai/models/exa-search","logo":"https://media.empiriolabs.ai/model-logos/exa-search.png","status":"available"},{"id":"gemini-2-5-flash-tts","object":"model","created":1747699200,"owned_by":"google","display_name":"Gemini 2.5 Flash TTS","author":"google","provider":"google","description":"Low-latency text-to-speech with single- and multi-speaker voices and controllable style, accent, and expressive tone for production apps.","modality":"audio","type":"tts","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["text_to_speech","multi_speaker","multilingual"],"aliases":["gemini-2.5-flash-tts","google/gemini-2.5-flash-tts"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":19661,"model_released_at":"2025-05-20","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Text to convert to speech. For multi-speaker mode, prefix lines with Speaker1: / Speaker2:.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"single = one voice, multi = two-voice dialogue (uses voice + voice2 + speaker names).","required":false,"metadata":{},"default":"single","options":["single","multi"]},{"name":"language","label":"Language","type":"string","description":"BCP-47 language tag (en-US, es-ES, etc.) for pronunciation cues.","required":false,"metadata":{},"default":"en-US"},{"name":"voice","label":"Voice","type":"enum","description":"Primary voice name (e.g. Kore, Puck, Aoede). Leave blank for the default.","required":false,"metadata":{"option_labels":{"Kore":"Kore (Firm)","Leda":"Leda (Youthful)","Orus":"Orus (Firm)","Puck":"Puck (Upbeat)","Aoede":"Aoede (Breezy)","Achird":"Achird (Friendly)","Charon":"Charon (Informative)","Fenrir":"Fenrir (Excitable)","Gacrux":"Gacrux (Mature)","Zephyr":"Zephyr (Bright)","Algenib":"Algenib (Gravelly)","Algieba":"Algieba (Smooth)","Alnilam":"Alnilam (Firm)","Autonoe":"Autonoe (Bright)","Despina":"Despina (Smooth)","Erinome":"Erinome (Clear)","Iapetus":"Iapetus (Clear)","Schedar":"Schedar (Even)","Sulafat":"Sulafat (Warm)","Umbriel":"Umbriel (Easy-going)","Achernar":"Achernar (Soft)","Enceladus":"Enceladus (Breathy)","Laomedeia":"Laomedeia (Upbeat)","Sadachbia":"Sadachbia (Lively)","Callirrhoe":"Callirrhoe (Easy-going)","Rasalgethi":"Rasalgethi (Informative)","Sadaltager":"Sadaltager (Knowledgeable)","Pulcherrima":"Pulcherrima (Forward)","Vindemiatrix":"Vindemiatrix (Gentle)","Zubenelgenubi":"Zubenelgenubi (Casual)"}},"default":"Charon","options":["Zephyr","Puck","Charon","Kore","Fenrir","Leda","Orus","Aoede","Callirrhoe","Autonoe","Enceladus","Iapetus","Umbriel","Algieba","Despina","Erinome","Algenib","Rasalgethi","Laomedeia","Achernar","Alnilam","Schedar","Gacrux","Pulcherrima","Achird","Zubenelgenubi","Vindemiatrix","Sadachbia","Sadaltager","Sulafat"]},{"name":"voice2","label":"Voice2","type":"enum","description":"Second voice name for multi-speaker mode.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"multi"},"option_labels":{"Kore":"Kore (Firm)","Leda":"Leda (Youthful)","Orus":"Orus (Firm)","Puck":"Puck (Upbeat)","Aoede":"Aoede (Breezy)","Achird":"Achird (Friendly)","Charon":"Charon (Informative)","Fenrir":"Fenrir (Excitable)","Gacrux":"Gacrux (Mature)","Zephyr":"Zephyr (Bright)","Algenib":"Algenib (Gravelly)","Algieba":"Algieba (Smooth)","Alnilam":"Alnilam (Firm)","Autonoe":"Autonoe (Bright)","Despina":"Despina (Smooth)","Erinome":"Erinome (Clear)","Iapetus":"Iapetus (Clear)","Schedar":"Schedar (Even)","Sulafat":"Sulafat (Warm)","Umbriel":"Umbriel (Easy-going)","Achernar":"Achernar (Soft)","Enceladus":"Enceladus (Breathy)","Laomedeia":"Laomedeia (Upbeat)","Sadachbia":"Sadachbia (Lively)","Callirrhoe":"Callirrhoe (Easy-going)","Rasalgethi":"Rasalgethi (Informative)","Sadaltager":"Sadaltager (Knowledgeable)","Pulcherrima":"Pulcherrima (Forward)","Vindemiatrix":"Vindemiatrix (Gentle)","Zubenelgenubi":"Zubenelgenubi (Casual)"},"clear_when_hidden":true},"default":"Kore","options":["Zephyr","Puck","Charon","Kore","Fenrir","Leda","Orus","Aoede","Callirrhoe","Autonoe","Enceladus","Iapetus","Umbriel","Algieba","Despina","Erinome","Algenib","Rasalgethi","Laomedeia","Achernar","Alnilam","Schedar","Gacrux","Pulcherrima","Achird","Zubenelgenubi","Vindemiatrix","Sadachbia","Sadaltager","Sulafat"]},{"name":"speaker1_name","label":"Speaker1 Name","type":"string","description":"Display name used in the input prefix for speaker 1 (default: Speaker1).","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"multi"},"clear_when_hidden":true},"default":"Speaker1"},{"name":"speaker2_name","label":"Speaker2 Name","type":"string","description":"Display name used in the input prefix for speaker 2 (default: Speaker2).","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"multi"},"clear_when_hidden":true},"default":"Speaker2"},{"name":"output_format","label":"Output Format","type":"enum","description":"Audio file format: WAV, MP3, OGG (Opus), or ALAW / MULAW for telephony.","required":false,"metadata":{},"default":"WAV","options":["WAV","MP3","OGG","ALAW","MULAW"]},{"name":"speed","label":"Speed","type":"number","description":"Playback rate. 1.0 = natural; <1 slower, >1 faster.","required":false,"metadata":{},"default":1,"min":0.25,"max":2},{"name":"volume_gain","label":"Volume Gain","type":"number","description":"Output gain in dB. 0 = unchanged.","required":false,"metadata":{},"default":0,"min":-96,"max":16},{"name":"sample_rate","label":"Sample Rate","type":"enum","description":"Output sample rate in Hz (8000, 16000, 22050, 24000, 44100, or 48000).","required":false,"metadata":{},"default":"24000","options":["8000","16000","22050","24000","44100","48000"]},{"name":"style_prompt","label":"Style Prompt","type":"string","description":"Natural-language style direction (e.g. \"warm, conversational\" or \"newscaster, serious\").","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/audio/speech"],"pricing":{"prompt":"0.0000015","completion":"0.00003","image":"0","request":"0","input_cache_read":"0.0000015"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.50"},{"spec":"per 1M generated tokens","label":"Output","value":"$30.00"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.5","label":"Input"},{"unit":"1m_tokens","usd":"30","label":"Output"}],"limits":{"note":"**Modes**\n\n- Single speaker\n- Multi-speaker (max 2 voices): text must be in `SpeakerName: text` format\n\n**Limits**\n\n- Text + style prompt: 4,000 bytes each\n- Audio billing: ~32 tokens per second of generated audio (~10-15 chars/s)\n\n**Voices and languages**\n\n- 30+ voice options across emotional/tonal characters\n- 24+ language locales supported\n\n**Output formats**\n\n- MP3, WAV, OGG"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=gemini-2-5-flash-tts","api_url":"https://docs.empiriolabs.ai/models/gemini-2-5-flash-tts","logo":"https://media.empiriolabs.ai/model-logos/gemini-2-5-flash-tts.png","status":"available"},{"id":"gemini-2-5-pro-tts","object":"model","created":1747699200,"owned_by":"google","display_name":"Gemini 2.5 Pro TTS","author":"google","provider":"google","description":"High-quality TTS preview for podcasts, audiobooks, and customer support, with expressive multi-speaker voices across 23+ languages.","modality":"audio","type":"tts","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["text_to_speech","multi_speaker","multilingual"],"aliases":["gemini-2.5-pro-tts","google/gemini-2.5-pro-tts"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":19661,"model_released_at":"2025-05-20","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Text to convert to speech. For multi-speaker mode, prefix lines with Speaker1: / Speaker2:.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"single = one voice, multi = two-voice dialogue (uses voice + voice2 + speaker names).","required":false,"metadata":{},"default":"single","options":["single","multi"]},{"name":"language","label":"Language","type":"string","description":"BCP-47 language tag (en-US, es-ES, etc.) for pronunciation cues.","required":false,"metadata":{},"default":"en-US"},{"name":"voice","label":"Voice","type":"enum","description":"Primary voice name (e.g. Kore, Puck, Aoede). Leave blank for the default.","required":false,"metadata":{"option_labels":{"Kore":"Kore (Firm)","Leda":"Leda (Youthful)","Orus":"Orus (Firm)","Puck":"Puck (Upbeat)","Aoede":"Aoede (Breezy)","Achird":"Achird (Friendly)","Charon":"Charon (Informative)","Fenrir":"Fenrir (Excitable)","Gacrux":"Gacrux (Mature)","Zephyr":"Zephyr (Bright)","Algenib":"Algenib (Gravelly)","Algieba":"Algieba (Smooth)","Alnilam":"Alnilam (Firm)","Autonoe":"Autonoe (Bright)","Despina":"Despina (Smooth)","Erinome":"Erinome (Clear)","Iapetus":"Iapetus (Clear)","Schedar":"Schedar (Even)","Sulafat":"Sulafat (Warm)","Umbriel":"Umbriel (Easy-going)","Achernar":"Achernar (Soft)","Enceladus":"Enceladus (Breathy)","Laomedeia":"Laomedeia (Upbeat)","Sadachbia":"Sadachbia (Lively)","Callirrhoe":"Callirrhoe (Easy-going)","Rasalgethi":"Rasalgethi (Informative)","Sadaltager":"Sadaltager (Knowledgeable)","Pulcherrima":"Pulcherrima (Forward)","Vindemiatrix":"Vindemiatrix (Gentle)","Zubenelgenubi":"Zubenelgenubi (Casual)"}},"default":"Charon","options":["Zephyr","Puck","Charon","Kore","Fenrir","Leda","Orus","Aoede","Callirrhoe","Autonoe","Enceladus","Iapetus","Umbriel","Algieba","Despina","Erinome","Algenib","Rasalgethi","Laomedeia","Achernar","Alnilam","Schedar","Gacrux","Pulcherrima","Achird","Zubenelgenubi","Vindemiatrix","Sadachbia","Sadaltager","Sulafat"]},{"name":"voice2","label":"Voice2","type":"enum","description":"Second voice name for multi-speaker mode.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"multi"},"option_labels":{"Kore":"Kore (Firm)","Leda":"Leda (Youthful)","Orus":"Orus (Firm)","Puck":"Puck (Upbeat)","Aoede":"Aoede (Breezy)","Achird":"Achird (Friendly)","Charon":"Charon (Informative)","Fenrir":"Fenrir (Excitable)","Gacrux":"Gacrux (Mature)","Zephyr":"Zephyr (Bright)","Algenib":"Algenib (Gravelly)","Algieba":"Algieba (Smooth)","Alnilam":"Alnilam (Firm)","Autonoe":"Autonoe (Bright)","Despina":"Despina (Smooth)","Erinome":"Erinome (Clear)","Iapetus":"Iapetus (Clear)","Schedar":"Schedar (Even)","Sulafat":"Sulafat (Warm)","Umbriel":"Umbriel (Easy-going)","Achernar":"Achernar (Soft)","Enceladus":"Enceladus (Breathy)","Laomedeia":"Laomedeia (Upbeat)","Sadachbia":"Sadachbia (Lively)","Callirrhoe":"Callirrhoe (Easy-going)","Rasalgethi":"Rasalgethi (Informative)","Sadaltager":"Sadaltager (Knowledgeable)","Pulcherrima":"Pulcherrima (Forward)","Vindemiatrix":"Vindemiatrix (Gentle)","Zubenelgenubi":"Zubenelgenubi (Casual)"},"clear_when_hidden":true},"default":"Kore","options":["Zephyr","Puck","Charon","Kore","Fenrir","Leda","Orus","Aoede","Callirrhoe","Autonoe","Enceladus","Iapetus","Umbriel","Algieba","Despina","Erinome","Algenib","Rasalgethi","Laomedeia","Achernar","Alnilam","Schedar","Gacrux","Pulcherrima","Achird","Zubenelgenubi","Vindemiatrix","Sadachbia","Sadaltager","Sulafat"]},{"name":"speaker1_name","label":"Speaker1 Name","type":"string","description":"Display name used in the input prefix for speaker 1 (default: Speaker1).","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"multi"},"clear_when_hidden":true},"default":"Speaker1"},{"name":"speaker2_name","label":"Speaker2 Name","type":"string","description":"Display name used in the input prefix for speaker 2 (default: Speaker2).","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"multi"},"clear_when_hidden":true},"default":"Speaker2"},{"name":"output_format","label":"Output Format","type":"enum","description":"Audio file format: WAV, MP3, OGG (Opus), or ALAW / MULAW for telephony.","required":false,"metadata":{},"default":"WAV","options":["WAV","MP3","OGG","ALAW","MULAW"]},{"name":"speed","label":"Speed","type":"number","description":"Playback rate. 1.0 = natural; <1 slower, >1 faster.","required":false,"metadata":{},"default":1,"min":0.25,"max":2},{"name":"volume_gain","label":"Volume Gain","type":"number","description":"Output gain in dB. 0 = unchanged.","required":false,"metadata":{},"default":0,"min":-96,"max":16},{"name":"sample_rate","label":"Sample Rate","type":"enum","description":"Output sample rate in Hz (8000, 16000, 22050, 24000, 44100, or 48000).","required":false,"metadata":{},"default":"24000","options":["8000","16000","22050","24000","44100","48000"]},{"name":"style_prompt","label":"Style Prompt","type":"string","description":"Natural-language style direction (e.g. \"warm, conversational\" or \"newscaster, serious\").","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/audio/speech"],"pricing":{"prompt":"0.000003","completion":"0.00006","image":"0","request":"0","input_cache_read":"0.000003"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$3.00"},{"spec":"per 1M generated tokens","label":"Output","value":"$60.00"}],"unit_pricing":[{"unit":"1m_tokens","usd":"3","label":"Input"},{"unit":"1m_tokens","usd":"60","label":"Output"}],"limits":{"note":"**Modes**\n\n- Single speaker\n- Multi-speaker (max 2 voices): text must be in `SpeakerName: text` format\n\n**Limits**\n\n- Text + style prompt: 4,000 bytes each\n- Audio billing: ~32 tokens per second of generated audio (~10-15 chars/s)\n\n**Voices and languages**\n\n- 30+ voice options across emotional/tonal characters\n- 24+ language locales supported\n\n**Output formats**\n\n- MP3, WAV, OGG"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=gemini-2-5-pro-tts","api_url":"https://docs.empiriolabs.ai/models/gemini-2-5-pro-tts","logo":"https://media.empiriolabs.ai/model-logos/gemini-2-5-pro-tts.png","status":"available"},{"id":"gemini-3-1-flash-tts","object":"model","created":1776038400,"owned_by":"google","display_name":"Gemini 3.1 Flash TTS","author":"google","provider":"google","description":"Highly controllable TTS with new Audio Tags for precise style, tone, pace, and delivery across narration, assistants, and voice apps.","modality":"audio","type":"tts","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["text_to_speech","multi_speaker","multilingual"],"aliases":["gemini-3.1-flash-tts","google/gemini-3.1-flash-tts"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":19661,"model_released_at":"2026-04-13","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Text to convert to speech. For multi-speaker mode, prefix lines with Speaker1: / Speaker2:.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"single = one voice, multi = two-voice dialogue (uses voice + voice2 + speaker names).","required":false,"metadata":{},"default":"single","options":["single","multi"]},{"name":"language","label":"Language","type":"string","description":"BCP-47 language tag (en-US, es-ES, etc.) for pronunciation cues.","required":false,"metadata":{},"default":"en-US"},{"name":"voice","label":"Voice","type":"enum","description":"Primary voice name (e.g. Kore, Puck, Aoede). Leave blank for the default.","required":false,"metadata":{"option_labels":{"Kore":"Kore (Firm)","Leda":"Leda (Youthful)","Orus":"Orus (Firm)","Puck":"Puck (Upbeat)","Aoede":"Aoede (Breezy)","Achird":"Achird (Friendly)","Charon":"Charon (Informative)","Fenrir":"Fenrir (Excitable)","Gacrux":"Gacrux (Mature)","Zephyr":"Zephyr (Bright)","Algenib":"Algenib (Gravelly)","Algieba":"Algieba (Smooth)","Alnilam":"Alnilam (Firm)","Autonoe":"Autonoe (Bright)","Despina":"Despina (Smooth)","Erinome":"Erinome (Clear)","Iapetus":"Iapetus (Clear)","Schedar":"Schedar (Even)","Sulafat":"Sulafat (Warm)","Umbriel":"Umbriel (Easy-going)","Achernar":"Achernar (Soft)","Enceladus":"Enceladus (Breathy)","Laomedeia":"Laomedeia (Upbeat)","Sadachbia":"Sadachbia (Lively)","Callirrhoe":"Callirrhoe (Easy-going)","Rasalgethi":"Rasalgethi (Informative)","Sadaltager":"Sadaltager (Knowledgeable)","Pulcherrima":"Pulcherrima (Forward)","Vindemiatrix":"Vindemiatrix (Gentle)","Zubenelgenubi":"Zubenelgenubi (Casual)"}},"default":"Charon","options":["Zephyr","Puck","Charon","Kore","Fenrir","Leda","Orus","Aoede","Callirrhoe","Autonoe","Enceladus","Iapetus","Umbriel","Algieba","Despina","Erinome","Algenib","Rasalgethi","Laomedeia","Achernar","Alnilam","Schedar","Gacrux","Pulcherrima","Achird","Zubenelgenubi","Vindemiatrix","Sadachbia","Sadaltager","Sulafat"]},{"name":"voice2","label":"Voice2","type":"enum","description":"Second voice name for multi-speaker mode.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"multi"},"option_labels":{"Kore":"Kore (Firm)","Leda":"Leda (Youthful)","Orus":"Orus (Firm)","Puck":"Puck (Upbeat)","Aoede":"Aoede (Breezy)","Achird":"Achird (Friendly)","Charon":"Charon (Informative)","Fenrir":"Fenrir (Excitable)","Gacrux":"Gacrux (Mature)","Zephyr":"Zephyr (Bright)","Algenib":"Algenib (Gravelly)","Algieba":"Algieba (Smooth)","Alnilam":"Alnilam (Firm)","Autonoe":"Autonoe (Bright)","Despina":"Despina (Smooth)","Erinome":"Erinome (Clear)","Iapetus":"Iapetus (Clear)","Schedar":"Schedar (Even)","Sulafat":"Sulafat (Warm)","Umbriel":"Umbriel (Easy-going)","Achernar":"Achernar (Soft)","Enceladus":"Enceladus (Breathy)","Laomedeia":"Laomedeia (Upbeat)","Sadachbia":"Sadachbia (Lively)","Callirrhoe":"Callirrhoe (Easy-going)","Rasalgethi":"Rasalgethi (Informative)","Sadaltager":"Sadaltager (Knowledgeable)","Pulcherrima":"Pulcherrima (Forward)","Vindemiatrix":"Vindemiatrix (Gentle)","Zubenelgenubi":"Zubenelgenubi (Casual)"},"clear_when_hidden":true},"default":"Kore","options":["Zephyr","Puck","Charon","Kore","Fenrir","Leda","Orus","Aoede","Callirrhoe","Autonoe","Enceladus","Iapetus","Umbriel","Algieba","Despina","Erinome","Algenib","Rasalgethi","Laomedeia","Achernar","Alnilam","Schedar","Gacrux","Pulcherrima","Achird","Zubenelgenubi","Vindemiatrix","Sadachbia","Sadaltager","Sulafat"]},{"name":"speaker1_name","label":"Speaker1 Name","type":"string","description":"Display name used in the input prefix for speaker 1 (default: Speaker1).","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"multi"},"clear_when_hidden":true},"default":"Speaker1"},{"name":"speaker2_name","label":"Speaker2 Name","type":"string","description":"Display name used in the input prefix for speaker 2 (default: Speaker2).","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"multi"},"clear_when_hidden":true},"default":"Speaker2"},{"name":"output_format","label":"Output Format","type":"enum","description":"Audio file format: WAV, MP3, OGG (Opus), or ALAW / MULAW for telephony.","required":false,"metadata":{},"default":"WAV","options":["WAV","MP3","OGG","ALAW","MULAW"]},{"name":"speed","label":"Speed","type":"number","description":"Playback rate. 1.0 = natural; <1 slower, >1 faster.","required":false,"metadata":{},"default":1,"min":0.25,"max":2},{"name":"volume_gain","label":"Volume Gain","type":"number","description":"Output gain in dB. 0 = unchanged.","required":false,"metadata":{},"default":0,"min":-96,"max":16},{"name":"sample_rate","label":"Sample Rate","type":"enum","description":"Output sample rate in Hz (8000, 16000, 22050, 24000, 44100, or 48000).","required":false,"metadata":{},"default":"24000","options":["8000","16000","22050","24000","44100","48000"]},{"name":"style_prompt","label":"Style Prompt","type":"string","description":"Natural-language style direction (e.g. \"warm, conversational\" or \"newscaster, serious\").","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/audio/speech"],"pricing":{"prompt":"0.0000026","completion":"0.000052","image":"0","request":"0","input_cache_read":"0.0000026"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$2.60"},{"spec":"per 1M generated tokens","label":"Output","value":"$52.00"}],"unit_pricing":[{"unit":"1m_tokens","usd":"2.6","label":"Input"},{"unit":"1m_tokens","usd":"52","label":"Output"}],"limits":{"note":"Most controllable Gemini TTS to date.\n\n**Limits**\n\n- Text + style prompt: 4,000 bytes each (8,000 combined)\n- Max output: ~10 minutes\n- Audio billing: ~25 tokens per second (~15 chars/s)\n- Language is auto-detected; the language setting is a hint, not a constraint\n\n**Inline audio tags** (control delivery)\n\n- Emotion: `[whispers]`, `[shouts]`, `[laughs]`, `[sighs]`, `[cheerful]`, `[sad]`, `[angry]`, etc.\n- Pace: `[slow]`, `[fast]`, `[extremely fast]`, `[normal pace]`\n- Pauses: `[short pause]`, `[long pause]`, `[breath]`\n- Emphasis: `[softly]`, `[loudly]`, `[high pitch]`, `[low pitch]`, `[rising tone]`, `[falling tone]`"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=gemini-3-1-flash-tts","api_url":"https://docs.empiriolabs.ai/models/gemini-3-1-flash-tts","logo":"https://media.empiriolabs.ai/model-logos/gemini-3-1-flash-tts.png","status":"available"},{"id":"gemma-3-27b","object":"model","created":1741564800,"owned_by":"google","display_name":"Gemma 3 27B","author":"google","provider":"google","description":"Open-source vision-language model with 128K context, 140+ languages, improved math/reasoning, structured outputs, and function calling.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image"],"input_modalities":["text","image"],"output_modalities":["text"],"features":["vision"],"aliases":["gemma-3-27b-it","google/gemma-3-27b"],"structured_output":"none","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":131072,"context_length":131072,"max_output_tokens":16384,"model_released_at":"2025-03-10","deprecation_date":"2026-11-25","deprecated":true,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"temperature","label":"temperature","type":"number","description":"Sampling temperature","required":false,"metadata":{},"default":1,"min":0,"max":2},{"name":"top_p","label":"top_p","type":"number","description":"Nucleus sampling","required":false,"metadata":{},"default":1,"min":0.01,"max":1},{"name":"max_tokens","label":"max_tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":16384},{"name":"stop","label":"stop","type":"string","description":"Stop sequences: the model stops before generating any of them.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/gemma-3-27b:generateContent"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0.004","input_cache_read":"0"},"pricing_rows":[{"spec":"fixed","label":"Per Message","value":"$0.0040"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"request","usd":"0.004","label":"Per Message"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":null,"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=gemma-3-27b","api_url":"https://docs.empiriolabs.ai/models/gemma-3-27b","logo":"https://media.empiriolabs.ai/model-logos/gemma.png","status":"available"},{"id":"glm-tts","object":"model","created":1765411200,"owned_by":"zhipu","display_name":"GLM TTS","author":"zhipu","provider":"zhipu","description":"LLM-based text-to-speech with zero-shot voice cloning and emotion-expressive, controllable output via multi-reward RL.","modality":"audio","type":"tts","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text","audio"],"output_modalities":["audio"],"features":["voice_cloning","emotion_control"],"aliases":["zhipu/glm-tts"],"structured_output":null,"native_inference":true,"weight_precision":"INT8 / FP16","hugging_face_id":"zai-org/GLM-TTS","batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-12-11","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Text to synthesize. For multi-speaker use [S1] / [S2] tags or 'Speaker N:' lines.","required":true,"metadata":{}},{"name":"voice","label":"Voice","type":"enum","description":"emma=English Female, james=US Male, arthur=US Male alt, xiaomei=Chinese Female, zhigang=Chinese Male, custom=upload reference via voice_audio_url.","required":false,"metadata":{},"default":"emma","options":["emma","james","arthur","xiaomei","zhigang","custom"]},{"name":"voice_audio_url","label":"Reference audio URL","type":"string","description":"Reference audio URL for custom voice cloning: a recording of up to 30 seconds in which the speaker reads this consent statement aloud in English, in their own voice: \"I consent to Empirio Labs cloning my voice for the purpose of generating synthetic speech. I understand that my voice sample will be used to create personalized audio content.\" A recording without the statement is refused. Clone only the voice of a speaker who has given this consent.","required":false,"metadata":{"control":"audio-clip","max_seconds":30}},{"name":"output_format","label":"Output Format","type":"enum","description":"Audio file format.","required":false,"metadata":{},"default":"mp3","options":["mp3","wav"]},{"name":"speed","label":"Speed","type":"number","description":"Speaking rate multiplier.","required":false,"metadata":{},"default":1,"min":0.5,"max":2},{"name":"model_quality","label":"Model Quality","type":"enum","description":"quality=FP16 (better), fast=INT8 (quicker)","required":false,"metadata":{},"default":"quality","options":["quality","fast"]},{"name":"sample_rate","label":"Sample Rate","type":"enum","description":"Output sample rate in Hz.","required":false,"metadata":{},"default":"24000","options":["16000","24000","44100","48000"]},{"name":"volume","label":"Volume","type":"number","description":"Output gain multiplier.","required":false,"metadata":{},"default":1,"min":0.1,"max":3},{"name":"use_cache","label":"Use Cache","type":"boolean","description":"Keep the voice consistent across a long text by carrying its earlier parts into the later ones. No effect on short text.","required":false,"metadata":{},"default":true},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/audio/speech"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per 1k characters, minimum 50 characters per request","label":"Fast (INT8)","value":"$0.20"},{"spec":"per 1k characters, minimum 50 characters per request","label":"Quality (FP16)","value":"$0.21"}],"unit_pricing":[{"unit":"1k_characters","usd":"0.2","label":"Fast (INT8)","minimum_usd":"0.01"},{"unit":"1k_characters","usd":"0.21","label":"Quality (FP16)","minimum_usd":"0.0105"}],"limits":{"note":"**Limits**\n\n- Max input: 5,000 characters\n- Billed per character, with a minimum of 50 characters per request\n\n**Voice cloning**\n\n- Reference audio: up to 30 seconds of the speaker reading the consent statement aloud in English (see `voice_audio_url`); a recording without it is refused\n- Accepted formats: WAV, MP3, OGG, FLAC, AAC, M4A, WebM\n\n**Preset voices**\n\n- emma (English F)\n- james (US M)\n- arthur (UK M)\n- xiaomei (Chinese F)\n- zhigang (Chinese M)"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=glm-tts","api_url":"https://docs.empiriolabs.ai/models/glm-tts","logo":"https://media.empiriolabs.ai/model-logos/glm.png","status":"available"},{"id":"gptzero","object":"model","created":1735689600,"owned_by":"gptzero","display_name":"GPTZero","author":"gptzero","provider":"gptzero","description":"Deep-learning detector that flags portions of text likely generated by AI versus human, classifying content as entirely human, AI, or mixed.","modality":"text","type":"tool","category":"tools","category_label":null,"modality_label":null,"modalities":["text","document"],"input_modalities":["text","document"],"output_modalities":["text"],"features":["ai_detection","classification"],"aliases":["gptzero/detect"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Text to analyze","required":false,"metadata":{}},{"name":"scan_type","label":"Scan Type","type":"enum","description":"AI Detection: detect AI-generated text.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":"ai_detection","options":["ai_detection"]},{"name":"file_url","label":"Document URL","type":"string","description":"URL of a document to scan instead of pasting text. Supported: PDF, DOC, DOCX, RTF, ODT, TXT, MD (max 25 MB). Provide either `input` (text) or `file_url`, not both.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"model_version","label":"Model Version","type":"string","description":"The GPTZero model version to scan with. Leave as __latest__ to use the newest version. A version that is unknown or no longer available returns a 400 error that lists the versions you can use. Same as version.","required":false,"metadata":{"visible_when":{"op":"eq","field":"scan_type","value":"ai_detection"},"clear_when_hidden":true},"default":"__latest__"},{"name":"version","label":"Version","type":"string","description":"The GPTZero model version to scan with. Leave as __latest__ to use the newest version. A version that is unknown or no longer available returns a 400 error that lists the versions you can use. Same as model_version.","required":false,"metadata":{"examples":["__latest__","2026-10-07-base","2026-06-10-multilingual"]},"default":"__latest__"},{"name":"ai_threshold","label":"Ai Threshold","type":"number","description":"Formatted reports only: the probability at which a sentence is labeled AI-generated. Lower = more sensitive. Range 0.10 to 0.99. It does not change the detection scores.","required":false,"metadata":{"visible_when":{"op":"eq","field":"scan_type","value":"ai_detection"},"clear_when_hidden":true},"default":0.7,"min":0.1,"max":0.99},{"name":"max_sentences","label":"Max Sentences","type":"number","description":"Formatted reports only: the maximum number of sentences shown in the per-sentence breakdown.","required":false,"metadata":{"visible_when":{"op":"eq","field":"scan_type","value":"ai_detection"},"clear_when_hidden":true},"default":15,"min":1,"max":50},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the detection result as JSON instead of the formatted Markdown report.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/detect","POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/gptzero:generateContent"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per 1,000 words","label":"Text Scan","value":"$0.39"}],"unit_pricing":[{"unit":"1k_words","usd":"0.39","label":"Text Scan"}],"limits":{"note":"**File limits**\n\n- One document per request, sent as file_url\n- Max 25 MB\n- Each document truncated to 50,000 characters\n\n**Supported formats**\n\n- PDF, DOC, DOCX, RTF, ODT, TXT, MD"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=gptzero","api_url":"https://docs.empiriolabs.ai/models/gptzero","logo":"https://media.empiriolabs.ai/model-logos/gptzero.png","status":"available"},{"id":"happyhorse-1-0","object":"model","created":1778025600,"owned_by":"alibaba","display_name":"HappyHorse 1.0","author":"alibaba","provider":"alibaba","description":"Video model offering Text-to-Video, Image-to-Video, Reference-to-Video, and Video Edit modes with high-fidelity, motion-smooth output.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image","video"],"output_modalities":["video"],"features":["audio_sync","editing"],"aliases":["alibaba/happyhorse-1.0","happyhorse-1.0"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-05-06","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"t2v: text-to-video. i2v: animate the attached image. videoedit: edit the attached video. r2v: reference-to-video.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v","videoedit","r2v"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution. Larger = higher fidelity but slower / more expensive.","required":false,"metadata":{},"default":"1080p","options":["720p","1080p"]},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds. Not used by video edit, which follows the input clip (up to 15 seconds).","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"hidden_when":{"op":"eq","field":"mode","value":"videoedit"},"clear_when_hidden":true},"default":5,"min":3,"max":15},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio for text-to-video and reference-to-video. Image-to-video and video edit follow the input.","required":false,"metadata":{"ui":{"control":"segmented"},"hidden_when":{"op":"in","field":"mode","values":["i2v","videoedit"]},"clear_when_hidden":true},"default":"16:9","options":["16:9","9:16","1:1","4:3","3:4"]},{"name":"image","label":"Image","type":"string","description":"Image URL. One for i2v, up to 9 for r2v, and up to 5 optional references for videoedit.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"video","label":"Video","type":"string","description":"Source video URL. Required for videoedit.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed.","required":false,"metadata":{}},{"name":"audio_setting","label":"Audio Setting","type":"enum","description":"auto: generate native audio. origin: keep the audio of the source video (video edit only).","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"videoedit"},"clear_when_hidden":true},"default":"auto","options":["auto","origin"]},{"name":"watermark","label":"Watermark","type":"boolean","description":"Add a 'HappyHorse' watermark to the output.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"All Modes 720P","value":"$0.14"},{"spec":"per second","label":"All Modes 1080P","value":"$0.24"}],"unit_pricing":[{"unit":"second","usd":"0.14","label":"All Modes 720P"},{"unit":"second","usd":"0.24","label":"All Modes 1080P"}],"limits":{"note":"**Modes** (in one model)\n\n- Text-to-video\n- Image-to-video\n- Reference-to-video\n- Video-to-video Edit (MP4/MOV/WEBM input)\n\n**Constraints**\n\n- 720p / 1080p, 3-15s per generation\n- Edit duration matches the input video length\n\n**Aspect ratios**\n\n- Text modes: 16:9, 9:16, 1:1\n- Reference mode adds: 4:3, 3:4\n\n**Billing**\n\n- Video-to-video Edit is billed for input + output duration combined (a 10s input bills 20s).\n\n**Uploaded media preprocessing**\n\n- Video inputs are capped to 15 seconds."},"notes":"**Modes** (in one bot)\n\n- Text-to-video\n- Image-to-video\n- Reference-to-video\n- Video-to-video Edit (MP4/MOV/WEBM input)\n\n**Constraints**\n\n- 720p / 1080p, 3-15s per generation\n- Edit duration matches the input video length\n\n**Aspect ratios**\n\n- Text modes: 16:9, 9:16, 1:1\n- Reference mode adds: 4:3, 3:4\n\n**Billing**\n\n- Video-to-video Edit is billed for input + output duration combined (a 10s input bills 20s).\n\n**Uploaded media preprocessing**\n\n- Video inputs are capped to 15 seconds.\n- Uploaded video inputs are normalized to provider-compatible MP4 when needed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=happyhorse-1-0","api_url":"https://docs.empiriolabs.ai/models/happyhorse-1-0","logo":"https://media.empiriolabs.ai/model-logos/happyhorse-1-0.png","status":"available"},{"id":"hunyuan-image-3","object":"model","created":1759017600,"owned_by":"tencent","display_name":"Hunyuan Image 3","author":"tencent","provider":"tencent","description":"Open-source text-to-image model on a multimodal Mixture-of-Experts architecture with photorealistic detail and strong multilingual text rendering.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text"],"output_modalities":["image"],"features":["photorealistic","multilingual"],"aliases":["tencent/hunyuan-image-3"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-09-28","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Text prompt. Longer, specific prompts with layout and text details work well.","required":true,"metadata":{}},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio. The model renders about one megapixel at the chosen ratio.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"1:1","options":["1:1","16:9","9:16","4:3","3:4","3:2","2:3","5:4","4:5","21:9","9:21"]},{"name":"num_images","label":"Num Images","type":"number","description":"Number of images to generate. Each is billed separately.","required":false,"metadata":{},"default":1,"min":1,"max":4},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed. Leave empty for random.","required":false,"metadata":{}},{"name":"response_format","label":"Response Format","type":"enum","description":"Return signed URLs or base64 image data.","required":false,"metadata":{},"default":"url","options":["url","b64_json"]}],"supported_endpoints":["POST /v1/images/generations"],"pricing":{"prompt":"0","completion":"0","image":"0.13","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Standard","value":"$0.13"}],"unit_pricing":[{"unit":"image","usd":"0.13","label":"Standard"}],"limits":{"note":"Text-to-image at about one megapixel with a selectable aspect ratio.\n\n**Content safety**\n\n- Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=hunyuan-image-3","api_url":"https://docs.empiriolabs.ai/models/hunyuan-image-3","logo":"https://media.empiriolabs.ai/model-logos/hunyuan-image-3.png","status":"available"},{"id":"hunyuan-video-1-5","object":"model","created":1763596800,"owned_by":"tencent","display_name":"Hunyuan Video 1.5","author":"tencent","provider":"tencent","description":"8.3B-parameter video model with native 720p output (upscalable to 1080p), strong motion coherence, and bilingual prompt understanding up to 10s.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image"],"output_modalities":["video"],"features":["1080p_upscale","bilingual"],"aliases":["hunyuan-video-1.5","tencent/hunyuan-video-1.5"],"structured_output":null,"native_inference":true,"weight_precision":"Mixed FP16/FP8","hugging_face_id":"tencent/HunyuanVideo-1.5","batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-11-20","is_new":false,"is_featured":true,"discount":{"label":"Save up to 19%","percent":19},"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"Auto detects image-to-video when an image is attached; otherwise text-to-video.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v"]},{"name":"resolution","label":"Resolution","type":"enum","description":"480p is the fastest native tier. 1080p is upscaled and capped at 5 seconds.","required":false,"metadata":{},"default":"480p","options":["480p","720p","1080p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"16:9","options":["16:9","9:16","1:1","4:3","3:4"]},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds. 1080p is capped at 5 seconds.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"step":1,"variants":[{"max":5,"when":{"op":"eq","field":"resolution","value":"1080p"},"description":"Clip length in seconds. 1080p is capped at 5 seconds."}]},"default":5,"min":1,"max":10},{"name":"cfg_scale","label":"Cfg Scale","type":"number","description":"Classifier-free guidance. Higher = follows prompt more strictly.","required":false,"metadata":{},"default":6,"min":1,"max":20},{"name":"steps","label":"Steps","type":"number","description":"Diffusion steps. More = higher fidelity, slower.","required":false,"metadata":{"step":1},"default":25,"min":10,"max":50},{"name":"image","label":"Image","type":"string","description":"Reference image URL for i2v mode.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid.","required":false,"metadata":{},"default":""},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed.","required":false,"metadata":{},"min":0}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"480p","value":"$0.061 (was $0.075)"},{"spec":"per second","label":"720p","value":"$0.29"},{"spec":"per second","label":"1080p (upscaled)","value":"$0.67"}],"unit_pricing":[{"unit":"second","usd":"0.061","label":"480p"},{"unit":"second","usd":"0.29","label":"720p"},{"unit":"second","usd":"0.67","label":"1080p (upscaled)"}],"limits":{"note":"8.3B-parameter Mixture-of-Experts model with strong motion coherence and bilingual prompt understanding.\n\n**Constraints**\n\n- 1080p is upscaled from native 720p and limited to 5s duration\n\n**Image-to-Video formats**\n\n- jpg, jpeg, png, webp, heic, heif, bmp, tiff, tif\n\n**Estimated generation time**\n\n- 480p: ~2 min\n- 720p: ~8 min\n- 1080p: ~20 min"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=hunyuan-video-1-5","api_url":"https://docs.empiriolabs.ai/models/hunyuan-video-1-5","logo":"https://media.empiriolabs.ai/model-logos/hunyuan-video-1-5.png","status":"available"},{"id":"kling-o3","object":"model","created":1770249600,"owned_by":"kling","display_name":"Kling O3","author":"kling","provider":"kling","description":"Video model in Standard or Pro modes with Text-to-Video, Image-to-Video, Reference-to-Video, editing, native sound, and multi-scene transitions.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image","audio"],"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"features":["audio","editing"],"aliases":["kling/o3"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-02-05","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Multi-scene: pipe (|) or newline-separated prompts, optionally prefixed with duration like '5s: scene text'. Up to 6 scenes.","required":true,"metadata":{}},{"name":"model_tier","label":"Model Tier","type":"enum","description":"standard: cheapest. pro: balanced quality. 4k: highest fidelity, longest render.","required":false,"metadata":{},"default":"pro","options":["standard","pro","4k"]},{"name":"workflow","label":"Workflow","type":"enum","description":"auto: detect from inputs. t2v: text-to-video. i2v: image-to-video. video_edit: edit attached video. reference: use reference_images or reference_videos.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v","video_edit","reference"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Text-to-video and reference only: landscape, square, or portrait. Image-to-video follows the shape of the first frame.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"16:9","options":["16:9","1:1","9:16"]},{"name":"duration","label":"Duration","type":"number","description":"Total clip length in seconds. A multi-scene prompt splits it across the scenes unless each scene sets its own length. With a video attached the limit is 10 seconds, and video edit follows the length of the source video.","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":5,"min":3,"max":15},{"name":"sound","label":"Sound","type":"boolean","description":"Generate native audio with the video. Not used with a video input; keep_original_sound applies there.","required":false,"metadata":{},"default":true},{"name":"keep_original_sound","label":"Keep Original Sound","type":"boolean","description":"Video edit, and reference with a video, only. Keep audio from the source video.","required":false,"metadata":{},"default":true},{"name":"image","label":"Image","type":"string","description":"First frame for image-to-video, as an image URL or data URI.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"image_end","label":"Image End","type":"string","description":"Optional last frame for image-to-video, as an image URL or data URI.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"video","label":"Video","type":"string","description":"Source video URL for video_edit.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"reference_images","label":"Reference Images","type":"string","description":"Comma-separated image URLs for reference workflow.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"reference_videos","label":"Reference Videos","type":"string","description":"Comma-separated video URLs for reference workflow.","required":false,"metadata":{"ui":{"hide_in_playground":true}}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"Standard T2V/I2V","value":"$0.168"},{"spec":"per second","label":"Standard T2V/I2V Sound","value":"$0.224"},{"spec":"per second","label":"Standard Video Input","value":"$0.252"},{"spec":"per second","label":"Pro T2V/I2V","value":"$0.224"},{"spec":"per second","label":"Pro T2V/I2V Sound","value":"$0.280"},{"spec":"per second","label":"Pro Video Input","value":"$0.336"},{"spec":"per second","label":"4K T2V/I2V/Ref","value":"$0.525"}],"unit_pricing":[{"unit":"second","usd":"0.168","label":"Standard T2V/I2V"},{"unit":"second","usd":"0.224","label":"Standard T2V/I2V Sound"},{"unit":"second","usd":"0.252","label":"Standard Video Input"},{"unit":"second","usd":"0.224","label":"Pro T2V/I2V"},{"unit":"second","usd":"0.28","label":"Pro T2V/I2V Sound"},{"unit":"second","usd":"0.336","label":"Pro Video Input"},{"unit":"second","usd":"0.525","label":"4K T2V/I2V/Ref"}],"limits":{"note":"Video model in Standard or Pro modes with text-to-video, image-to-video, reference-to-video, editing, native sound, and multi-scene transitions.\n\n**Uploaded media preprocessing**\n\n- Video inputs are capped to 10 seconds for video-edit and video-reference workflows.\n- Uploaded video inputs are normalized to provider-compatible MP4 when needed.\n- Kling O3 4K supports text, image, and image-only reference workflows. Use Standard or Pro for video inputs."},"notes":"Video model in Standard or Pro modes with text-to-video, image-to-video, reference-to-video, editing, native sound, and multi-scene transitions.\n\n**Uploaded media preprocessing**\n\n- Video inputs are capped to 10 seconds for video-edit and video-reference workflows.\n- Uploaded video inputs are normalized to provider-compatible MP4 when needed.\n- Kling O3 4K supports text, image, and image-only reference workflows. Use Standard or Pro for video inputs.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=kling-o3","api_url":"https://docs.empiriolabs.ai/models/kling-o3","logo":"https://media.empiriolabs.ai/model-logos/kling-o3.png","status":"available"},{"id":"kling-v3-motion-control","object":"model","created":1735689600,"owned_by":"kling","display_name":"Kling v3 Motion Control","author":"kling","provider":"kling","description":"Kling 3.0 model that transfers motion from a reference video onto a character from a reference image, with Standard 720p and Pro 1080p tiers.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image","video"],"output_modalities":["video"],"features":["motion_control"],"aliases":["kling-v3-motion","kling-v3-motion-ctrl","kling/v3-motion"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Motion / scene description.","required":true,"metadata":{}},{"name":"reference_image","label":"Reference Image","type":"string","description":"URL of the reference image that provides the character or subject.","required":true,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"reference_video","label":"Reference Video","type":"string","description":"URL of the reference video that provides the motion to copy.","required":true,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"character_orientation","label":"Character Orientation","type":"enum","description":"image: character starts in the pose from the reference image (max 10s). video: character matches pose in the reference video (max 30s).","required":false,"metadata":{},"default":"image","options":["image","video"]},{"name":"mode","label":"Mode","type":"enum","description":"std: standard quality. pro: higher quality, slower.","required":false,"metadata":{},"default":"std","options":["std","pro"]},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds. The reference video is trimmed to this length, so a shorter reference gives a shorter clip, and the bill follows the clip returned. Capped at 10 when character_orientation=image, 30 when character_orientation=video.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"variants":[{"max":10,"when":{"op":"eq","field":"character_orientation","value":"image"}}]},"default":4,"min":1,"max":30},{"name":"keep_original_sound","label":"Keep Original Sound","type":"boolean","description":"Keep the audio track from the reference video.","required":false,"metadata":{},"default":true}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"Standard (720p)","value":"$0.14"},{"spec":"per second","label":"Pro (1080p)","value":"$0.18"}],"unit_pricing":[{"unit":"second","usd":"0.14","label":"Standard (720p)"},{"unit":"second","usd":"0.18","label":"Pro (1080p)"}],"limits":{"note":"Motion-control video: a reference IMAGE (the character/subject) and a reference VIDEO (the motion source) are BOTH required. The character from the image performs the movements from the video.\n\n**Reference image**\n\n- JPEG, PNG, or WEBP\n- Max 10 MB\n- Min 340px on the short edge\n- Aspect ratio 0.4 to 2.5\n\n**Reference video**\n\n- MP4, MOV, or WEBM\n- Max 100 MB\n- 340-3850px\n- 24-60 FPS\n- 3-10s (image orientation: max 10s; video orientation: max 30s)\n\n**Uploaded media preprocessing**\n\n- Reference videos are normalized to provider-compatible MP4 when needed.\n- Reference-video duration follows the selected character orientation limit."},"notes":"Motion-control video: a reference IMAGE (the character/subject) and a reference VIDEO (the motion source) are BOTH required. The character from the image performs the movements from the video.\n\n**Reference image**\n\n- JPEG, PNG, or WEBP\n- Max 10 MB\n- Min 340px on the short edge\n- Aspect ratio 0.4 to 2.5\n\n**Reference video**\n\n- MP4, MOV, or WEBM\n- Max 100 MB\n- 340-3850px\n- 24-60 FPS\n- 3-10s (image orientation: max 10s; video orientation: max 30s)\n\n**Uploaded media preprocessing**\n\n- Reference videos are normalized to provider-compatible MP4 when needed.\n- Reference-video duration follows the selected character orientation limit.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=kling-v3-motion-control","api_url":"https://docs.empiriolabs.ai/models/kling-v3-motion-control","logo":"https://media.empiriolabs.ai/model-logos/kling-v3-motion-ctrl.png","status":"available"},{"id":"linkup-deep-search","object":"model","created":1735689600,"owned_by":"linkup","display_name":"Linkup Deep Search","author":"linkup","provider":"linkup","description":"Iterative AI search that keeps querying when initial results are insufficient, returning more comprehensive answers than Standard mode.","modality":"text","type":"research","category":"research","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["web_search","deep_research"],"aliases":[],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"query","label":"Query","type":"string","description":"The natural-language query to search/research/answer.","required":true,"metadata":{}},{"name":"output_type","label":"Output Type","type":"enum","description":"sourcedAnswer returns a synthesized answer with citations; searchResults returns raw hits and is returned by POST /v1/search only.","required":false,"metadata":{},"default":"sourcedAnswer","options":["sourcedAnswer","searchResults"]},{"name":"domain_filter_mode","label":"Domain Filter Mode","type":"enum","description":"None applies whichever domain lists you send. Include returns results only from include_domains. Exclude drops results from exclude_domains.","required":false,"metadata":{},"default":"None","options":["None","Include","Exclude"]},{"name":"include_domains","label":"Include Domains","type":"string","description":"Comma-separated domains or URLs to include","required":false,"metadata":{"visible_when":{"op":"eq","field":"domain_filter_mode","value":"Include"},"clear_when_hidden":true}},{"name":"exclude_domains","label":"Exclude Domains","type":"string","description":"Comma-separated domains or URLs to exclude","required":false,"metadata":{"visible_when":{"op":"eq","field":"domain_filter_mode","value":"Exclude"},"clear_when_hidden":true}},{"name":"prioritize_domains","label":"Prioritize Domains","type":"string","description":"Comma-separated domains to prefer via query guidance","required":false,"metadata":{}},{"name":"from_date","label":"From Date","type":"string","description":"Only include sources published on or after this date. Format: YYYY-MM-DD.","required":false,"metadata":{}},{"name":"to_date","label":"To Date","type":"string","description":"Only include sources published on or before this date. Format: YYYY-MM-DD.","required":false,"metadata":{}},{"name":"include_images","label":"Include Images","type":"boolean","description":"Include relevant image URLs in the results.","required":false,"metadata":{},"default":false},{"name":"image_count","label":"Image Count","type":"number","description":"Maximum number of images returned.","required":false,"metadata":{"visible_when":{"op":"eq","field":"include_images","value":true},"clear_when_hidden":true},"default":6,"min":1,"max":45},{"name":"enable_inline_citations","label":"Enable Inline Citations","type":"boolean","description":"Embed [N] citations inline in the synthesized answer.","required":false,"metadata":{},"default":true},{"name":"include_sources","label":"Include Sources","type":"boolean","description":"Return the list of source URLs alongside the answer.","required":false,"metadata":{},"default":true},{"name":"max_results","label":"Max Results","type":"number","description":"Maximum number of results returned.","required":false,"metadata":{},"min":1,"max":100}],"supported_endpoints":["POST /v1/search","POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/linkup-deep-search:generateContent"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0.13","input_cache_read":"0"},"pricing_rows":[{"spec":"fixed","label":"Per Message","value":"$0.13"}],"unit_pricing":[{"unit":"request","usd":"0.13","label":"Per Message"}],"limits":{"note":"Iterative search, retries when initial results are insufficient."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=linkup-deep-search","api_url":"https://docs.empiriolabs.ai/models/linkup-deep-search","logo":"https://media.empiriolabs.ai/model-logos/linkup-deep-search.png","status":"available"},{"id":"linkup-standard","object":"model","created":1735689600,"owned_by":"linkup","display_name":"Linkup Standard","author":"linkup","provider":"linkup","description":"AI-powered web search with detailed overviews and answers, faster than Deep Search.","modality":"text","type":"search","category":"research","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["web_search"],"aliases":[],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"query","label":"Query","type":"string","description":"The natural-language query to search/research/answer.","required":true,"metadata":{}},{"name":"output_type","label":"Output Type","type":"enum","description":"sourcedAnswer returns a synthesized answer with citations; searchResults returns raw hits and is returned by POST /v1/search only.","required":false,"metadata":{},"default":"sourcedAnswer","options":["sourcedAnswer","searchResults"]},{"name":"domain_filter_mode","label":"Domain Filter Mode","type":"enum","description":"None applies whichever domain lists you send. Include returns results only from include_domains. Exclude drops results from exclude_domains.","required":false,"metadata":{},"default":"None","options":["None","Include","Exclude"]},{"name":"include_domains","label":"Include Domains","type":"string","description":"Comma-separated domains or URLs to include","required":false,"metadata":{"visible_when":{"op":"eq","field":"domain_filter_mode","value":"Include"},"clear_when_hidden":true}},{"name":"exclude_domains","label":"Exclude Domains","type":"string","description":"Comma-separated domains or URLs to exclude","required":false,"metadata":{"visible_when":{"op":"eq","field":"domain_filter_mode","value":"Exclude"},"clear_when_hidden":true}},{"name":"prioritize_domains","label":"Prioritize Domains","type":"string","description":"Comma-separated domains to prefer via query guidance","required":false,"metadata":{}},{"name":"from_date","label":"From Date","type":"string","description":"Only include sources published on or after this date. Format: YYYY-MM-DD.","required":false,"metadata":{}},{"name":"to_date","label":"To Date","type":"string","description":"Only include sources published on or before this date. Format: YYYY-MM-DD.","required":false,"metadata":{}},{"name":"include_images","label":"Include Images","type":"boolean","description":"Include relevant image URLs in the results.","required":false,"metadata":{},"default":false},{"name":"image_count","label":"Image Count","type":"number","description":"Maximum number of images returned.","required":false,"metadata":{"visible_when":{"op":"eq","field":"include_images","value":true},"clear_when_hidden":true},"default":6,"min":1,"max":45},{"name":"enable_inline_citations","label":"Enable Inline Citations","type":"boolean","description":"Embed [N] citations inline in the synthesized answer.","required":false,"metadata":{},"default":true},{"name":"include_sources","label":"Include Sources","type":"boolean","description":"Return the list of source URLs alongside the answer.","required":false,"metadata":{},"default":true},{"name":"max_results","label":"Max Results","type":"number","description":"Maximum number of results returned.","required":false,"metadata":{},"min":1,"max":100}],"supported_endpoints":["POST /v1/search","POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/linkup-standard:generateContent"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0.013","input_cache_read":"0"},"pricing_rows":[{"spec":"fixed","label":"Per Message","value":"$0.013"}],"unit_pricing":[{"unit":"request","usd":"0.013","label":"Per Message"}],"limits":null,"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=linkup-standard","api_url":"https://docs.empiriolabs.ai/models/linkup-standard","logo":"https://media.empiriolabs.ai/model-logos/linkup-standard.png","status":"available"},{"id":"mistral-small-3-1","object":"model","created":1742169600,"owned_by":"mistral","display_name":"Mistral Small 3.1","author":"mistral","provider":"mistral","description":"24B-parameter multimodal model for image analysis, programming, math, and multilingual tasks, tuned for efficient local inference.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image"],"input_modalities":["text","image"],"output_modalities":["text"],"features":["vision","function_calling"],"aliases":["mistral-small-3.1","mistralai/mistral-small-3.1"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":89587,"context_length":89587,"max_output_tokens":32768,"model_released_at":"2025-03-17","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 5 = maximum randomness.","required":false,"metadata":{},"default":0.15,"min":0,"max":5},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":1,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum tokens in the response.","required":false,"metadata":{},"default":4096,"min":1,"max":32768},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-format tool definitions","required":false,"metadata":{}},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"auto, none, required, or {type, function}","required":false,"metadata":{}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/mistral-small-3-1:generateContent"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0.0019","input_cache_read":"0"},"pricing_rows":[{"spec":"fixed","label":"Per Message","value":"$0.0019"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"request","usd":"0.0019","label":"Per Message"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Input is limited to about 500,000 characters per request."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=mistral-small-3-1","api_url":"https://docs.empiriolabs.ai/models/mistral-small-3-1","logo":"https://media.empiriolabs.ai/model-logos/mistral-small-3-1.png","status":"available"},{"id":"mistral-small-4","object":"model","created":1773619200,"owned_by":"mistral","display_name":"Mistral Small 4","author":"mistral","provider":"mistral","description":"Hybrid model unifying Instruct, Reasoning (Magistral), and Devstral families: 40% lower completion time and 3x throughput vs Small 3.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image"],"input_modalities":["text","image"],"output_modalities":["text"],"features":["vision","web_search","function_calling"],"aliases":["mistralai/mistral-small-4"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":"batch","batch_discount_pct":35,"context_window":262144,"context_length":262144,"max_output_tokens":65536,"model_released_at":"2026-03-16","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"reasoning_enabled","label":"Reasoning Enabled","type":"boolean","description":"Enable extended reasoning. Not applied when the request includes function tools.","required":false,"metadata":{},"default":true},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable web_search tool","required":false,"metadata":{},"default":false},{"name":"web_search_tier","label":"Web Search Tier","type":"enum","description":"Standard or Premium web-search tier. Premium uses higher-quality sources.","required":false,"metadata":{"visible_when":{"op":"eq","field":"tool_web_search","value":true},"clear_when_hidden":true},"default":"standard","options":["standard","premium"]},{"name":"tool_code_interpreter","label":"Tool Code Interpreter","type":"boolean","description":"Allow the model to execute Python code in a sandbox to compute / analyze data.","required":false,"metadata":{},"default":false},{"name":"tool_image_generation","label":"Tool Image Generation","type":"boolean","description":"Allow the model to generate images inline via the platform image-gen tool.","required":false,"metadata":{},"default":false},{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 1 = maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum tokens in the response.","required":false,"metadata":{},"default":4096,"min":1,"max":65536},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added.","required":false,"metadata":{},"default":false},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"control":"structured-output","so_tier":"json_object"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/mistral-small-4:generateContent"],"pricing":{"prompt":"0.00000015","completion":"0.0000006","image":"0","request":"0","input_cache_read":"0.00000015"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.15"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.60"},{"spec":"per call","label":"Standard Web Search","value":"$0.084"},{"spec":"per call","label":"Premium Web Search","value":"$0.140"},{"spec":"per call","label":"Code Interpreter","value":"$0.084"},{"spec":"per image","label":"Image Generation","value":"$0.280"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.15","label":"Input"},{"unit":"1m_tokens","usd":"0.6","label":"Output"},{"unit":"call","usd":"0.084","label":"Standard Web Search"},{"unit":"call","usd":"0.14","label":"Premium Web Search"},{"unit":"call","usd":"0.084","label":"Code Interpreter"},{"unit":"image","usd":"0.28","label":"Image Generation"}],"limits":{"note":"Tools (web search, code interpreter, image generation) are billed only when actually invoked. Requests that include your own function tools use standard function calling, and the built-in tools are unavailable on those requests: a request cannot combine both at once. With a built-in tool turned on, input is limited to about 235,000 tokens per request.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools (web search, code interpreter, etc.) inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape, exact field names, units, and which tools appear can vary slightly per provider:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nThe tool counts are already factored into `cost_usd`, they are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=mistral-small-4","api_url":"https://docs.empiriolabs.ai/models/mistral-small-4","logo":"https://media.empiriolabs.ai/model-logos/mistral-small-4.png","status":"available"},{"id":"moss-video-and-audio","object":"model","created":1769644800,"owned_by":"openmoss","display_name":"MOSS Video and Audio","author":"openmoss","provider":"openmoss","description":"Open-source 32B MoE foundation model that generates synchronized video and audio in one inference step with precise dual-tower lip-sync.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image","audio"],"input_modalities":["text","image"],"output_modalities":["video","audio"],"features":["audio_sync","lipsync"],"aliases":["moss-video-audio","openmoss/video-audio"],"structured_output":null,"native_inference":true,"weight_precision":"BF16","hugging_face_id":"OpenMOSS-Team/MOVA-360p","batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-01-29","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description. With image attached, becomes an image-to-video prompt.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"auto runs i2v when an image is attached, otherwise t2v. t2v: text-to-video. i2v: animate the attached image.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution.","required":false,"metadata":{},"default":"360p","options":["360p","720p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Text-to-video only: landscape (16:9) or portrait (9:16). Image-to-video follows the image.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"landscape","options":["landscape","portrait"]},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds, from 2 to 8.","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":4,"min":2,"max":8},{"name":"t2v_quality","label":"T2V Quality","type":"enum","description":"Text-to-video only. fast trades fidelity for ~2× speed.","required":false,"metadata":{},"default":"quality","options":["fast","quality"]},{"name":"num_inference_steps","label":"Num Inference Steps","type":"number","description":"Diffusion steps. More = higher fidelity, slower.","required":false,"metadata":{},"default":25,"min":10,"max":50},{"name":"cfg_scale","label":"Cfg Scale","type":"number","description":"Classifier-free guidance. Higher = follows prompt more strictly.","required":false,"metadata":{},"default":5,"min":1,"max":10},{"name":"sigma_shift","label":"Sigma Shift","type":"number","description":"Schedule shift. Only valid when resolution=360p.","required":false,"metadata":{"visible_when":{"op":"eq","field":"resolution","value":"360p"},"clear_when_hidden":true},"default":5,"min":1,"max":10},{"name":"image","label":"Image","type":"string","description":"Reference image URL for i2v mode.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid.","required":false,"metadata":{},"default":""},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed.","required":false,"metadata":{},"min":0,"max":4294967295}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"360p Video","value":"$0.12"},{"spec":"per second","label":"720p Video","value":"$2.50"},{"spec":"additional fee","label":"T2V Fast","value":"$0.065"},{"spec":"additional fee","label":"T2V Quality","value":"$0.13"}],"unit_pricing":[{"unit":"second","usd":"0.12","label":"360p Video"},{"unit":"second","usd":"2.5","label":"720p Video"}],"limits":{"note":"32B-parameter MoE with synchronized lip-sync video + audio in a single inference.\n\n**Constraints**\n\n- Generation can take 20+ minutes\n- Image-to-Video typically yields superior results to text-to-video\n- Only 1 image supported (used as the first frame)\n- Video inputs NOT supported\n\n**Image formats**\n\n- jpg, jpeg, png, webp, heic, heif, bmp, tiff, tif, gif"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=moss-video-and-audio","api_url":"https://docs.empiriolabs.ai/models/moss-video-and-audio","logo":"https://media.empiriolabs.ai/model-logos/moss-video-and-audio.png","status":"available"},{"id":"nova-lite-1-0","object":"model","created":1733184000,"owned_by":"amazon","display_name":"Nova Lite 1.0","author":"amazon","provider":"amazon","description":"Low-cost multimodal foundation model for text, images, and video on a 300K context (up to ~30 min video), tuned for speed and affordability.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["vision","function_calling"],"aliases":["amazon-nova-lite","amazon/nova-lite","nova-lite","us.amazon.nova-lite-v1:0"],"structured_output":"none","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":"batch","batch_discount_pct":35,"context_window":317379,"context_length":317379,"max_output_tokens":10000,"model_released_at":"2024-12-03","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature, from 0 (deterministic) to 1.","required":false,"metadata":{},"default":0.7,"min":0,"max":1},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum tokens in the response.","required":false,"metadata":{},"default":10000,"min":1,"max":10000},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/nova-lite-1-0:generateContent"],"pricing":{"prompt":"0.000000069","completion":"0.00000028","image":"0","request":"0","input_cache_read":"0.0000000386"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.069"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.28"},{"spec":"per 1M tokens","label":"Cached input","value":"$0.0386"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.069","label":"Input"},{"unit":"1m_tokens","usd":"0.28","label":"Output"},{"unit":"1m_tokens","usd":"0.0386","label":"Cached input"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":null,"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=nova-lite-1-0","api_url":"https://docs.empiriolabs.ai/models/nova-lite-1-0","logo":"https://media.empiriolabs.ai/model-logos/nova-lite-1-0.png","status":"available"},{"id":"nova-lite-2","object":"model","created":1764633600,"owned_by":"amazon","display_name":"Nova Lite 2","author":"amazon","provider":"amazon","description":"Fast, cost-effective multimodal reasoning model for text, images, documents, and video on a 1M context (long docs and ~90 min clips).","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video","document"],"input_modalities":["text","image","video","document"],"output_modalities":["text"],"features":["vision","function_calling","reasoning"],"aliases":["amazon-nova-lite-2","amazon/nova-lite-2","us.amazon.nova-2-lite-v1:0"],"structured_output":"none","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":"batch","batch_discount_pct":35,"context_window":1000000,"context_length":1000000,"max_output_tokens":131072,"model_released_at":"2025-12-02","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature, from 0 (deterministic) to 1. Not available with reasoning_effort high.","required":false,"metadata":{"hidden_when":{"op":"eq","field":"reasoning_effort","value":"high"},"clear_when_hidden":true},"default":0.7,"min":0,"max":1},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused. Not available with reasoning_effort high.","required":false,"metadata":{"hidden_when":{"op":"eq","field":"reasoning_effort","value":"high"},"clear_when_hidden":true},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum tokens in the response. Not available with reasoning_effort high.","required":false,"metadata":{"hidden_when":{"op":"eq","field":"reasoning_effort","value":"high"},"clear_when_hidden":true},"default":60000,"min":1,"max":65535},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable extended reasoning before the final answer. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning depth: low, medium or high. Higher takes longer and uses more output tokens. high takes no max_tokens, temperature or top_p, and its response can be longer than 65,535 tokens.","required":false,"metadata":{"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":"medium","options":["low","medium","high"]},{"name":"reasoning","label":"Reasoning","type":"string","description":"Responses API reasoning object: {\"effort\":\"low|medium|high\"}","required":false,"metadata":{}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/nova-lite-2:generateContent"],"pricing":{"prompt":"0.00000038","completion":"0.00000316","image":"0","request":"0","input_cache_read":"0.0000002128"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.38"},{"spec":"per 1M generated tokens","label":"Output","value":"$3.16"},{"spec":"per 1M tokens","label":"Cached input","value":"$0.2128"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.38","label":"Input"},{"unit":"1m_tokens","usd":"3.16","label":"Output"},{"unit":"1m_tokens","usd":"0.2128","label":"Cached input"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Reasoning traces are not returned. Video uploads up to ~1 GB."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=nova-lite-2","api_url":"https://docs.empiriolabs.ai/models/nova-lite-2","logo":"https://media.empiriolabs.ai/model-logos/nova-lite-2.png","status":"available"},{"id":"nova-micro-1-0","object":"model","created":1733184000,"owned_by":"amazon","display_name":"Nova Micro 1.0","author":"amazon","provider":"amazon","description":"Text-only foundation model tuned for ultra-low latency and cost on 128K context. Strong for summarization, translation, and chat with 44% cache discount.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["fast","function_calling"],"aliases":["amazon-nova-micro","amazon/nova-micro","nova-micro","us.amazon.nova-micro-v1:0"],"structured_output":"none","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":"batch","batch_discount_pct":35,"context_window":133003,"context_length":133003,"max_output_tokens":10000,"model_released_at":"2024-12-03","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature, from 0 (deterministic) to 1.","required":false,"metadata":{},"default":0.7,"min":0,"max":1},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum tokens in the response.","required":false,"metadata":{},"default":5000,"min":1,"max":10000},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/nova-micro-1-0:generateContent"],"pricing":{"prompt":"0.00000004","completion":"0.00000016","image":"0","request":"0","input_cache_read":"0.0000000224"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.040"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.16"},{"spec":"per 1M tokens","label":"Cached input","value":"$0.0224"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.04","label":"Input"},{"unit":"1m_tokens","usd":"0.16","label":"Output"},{"unit":"1m_tokens","usd":"0.0224","label":"Cached input"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"44% discount on cached chat."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=nova-micro-1-0","api_url":"https://docs.empiriolabs.ai/models/nova-micro-1-0","logo":"https://media.empiriolabs.ai/model-logos/nova-micro-1-0.png","status":"available"},{"id":"nova-pro-1-0","object":"model","created":1733184000,"owned_by":"amazon","display_name":"Nova Pro 1.0","author":"amazon","provider":"amazon","description":"Multimodal foundation model balancing accuracy, speed, and cost for text, images, and video on 300K context (up to ~30 min video).","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["vision","function_calling"],"aliases":["amazon-nova-pro","amazon.nova-pro-v1:0","amazon/nova-pro","nova-pro","us.amazon.nova-pro-v1:0"],"structured_output":"none","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":"batch","batch_discount_pct":35,"context_window":317319,"context_length":317319,"max_output_tokens":10000,"model_released_at":"2024-12-03","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature, from 0 (deterministic) to 1.","required":false,"metadata":{},"default":0.7,"min":0,"max":1},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum tokens in the response.","required":false,"metadata":{},"default":10000,"min":1,"max":10000},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_latency_optimized","label":"Latency Optimized","type":"boolean","description":"Faster responses, billed at the Latency Optimized rate ($3.00 input / $12.00 output per 1M tokens) instead of the Standard rate.","required":false,"metadata":{},"default":false},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/nova-pro-1-0:generateContent"],"pricing":{"prompt":"0.0000024","completion":"0.0000096","image":"0","request":"0","input_cache_read":"0.0000024"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$2.40"},{"spec":"per 1M generated tokens","label":"Output","value":"$9.60"},{"spec":"per 1M prompt tokens","label":"Latency Optimized Input","value":"$3.00"},{"spec":"per 1M generated tokens","label":"Latency Optimized Output","value":"$12.00"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"2.4","label":"Input"},{"unit":"1m_tokens","usd":"9.6","label":"Output"},{"unit":"1m_tokens","usd":"3","label":"Latency Optimized Input"},{"unit":"1m_tokens","usd":"12","label":"Latency Optimized Output"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Optional Latency-Optimized Inference for faster responses at higher cost."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=nova-pro-1-0","api_url":"https://docs.empiriolabs.ai/models/nova-pro-1-0","logo":"https://media.empiriolabs.ai/model-logos/nova-pro-1-0.png","status":"available"},{"id":"openai-whisper-1","object":"model","created":1663718400,"owned_by":"openai","display_name":"OpenAI Whisper 1","author":"openai","provider":"openai","description":"Whisper-1 speech-to-text transcription trained on multilingual supervised audio, with a 25 MB upload limit per file.","modality":"audio","type":"stt","category":"transcription","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio"],"output_modalities":["text"],"features":["transcription","speech_to_text","realtime","streaming_asr"],"aliases":["openai-whisper","whisper-1"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2022-09-21","deprecation_date":"2027-02-25","deprecated":true,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"file","label":"File","type":"string","description":"Audio file (multipart upload) OR use file_url for the JSON path.","required":true,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"file_url","label":"File Url","type":"string","description":"Public URL to fetch audio from (alternative to file upload).","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"translate","label":"Translate","type":"boolean","description":"If true, route to /audio/translations and translate to English instead of transcribing in source language.","required":false,"metadata":{},"default":false},{"name":"timestamps","label":"Timestamps","type":"boolean","description":"Convenience toggle. If true, sets response_format=verbose_json and includes word-level timestamp_granularities.","required":false,"metadata":{},"default":false},{"name":"language","label":"Language","type":"string","description":"Optional ISO-639-1 language code. Auto-detected if omitted. Ignored when translate=true.","required":false,"metadata":{}},{"name":"prompt","label":"Prompt","type":"string","description":"Glossary or prior context to bias the model.","required":false,"metadata":{}},{"name":"response_format","label":"Response Format","type":"enum","description":"Defaults to verbose_json, which timestamps=true always uses.","required":false,"metadata":{},"default":"verbose_json","options":["json","text","srt","verbose_json","vtt"]},{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature.","required":false,"metadata":{},"default":0,"min":0,"max":1},{"name":"timestamp_granularities","label":"Timestamp Granularities","type":"string","description":"Comma-separated list: word, segment. Used when response_format=verbose_json.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/audio/transcriptions","WEBSOCKET /v1/realtime"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per minute","label":"Per Minute of Audio","value":"$0.030"}],"unit_pricing":[{"unit":"minute","usd":"0.03","label":"Per Minute of Audio"}],"limits":{"note":"Upload a file to POST /v1/audio/transcriptions, or transcribe live over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=openai-whisper-1. The socket takes 24 kHz mono 16-bit PCM as base64 in input_audio_buffer.append and returns transcript events; voice activity detection decides when each phrase ends, so you do not send a commit. Both surfaces bill per minute of audio at the same rate."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=openai-whisper-1","api_url":"https://docs.empiriolabs.ai/models/openai-whisper-1","logo":"https://media.empiriolabs.ai/model-logos/openai-whisper-1.png","status":"available"},{"id":"perplexity-advanced-deep-research","object":"model","created":1735689600,"owned_by":"perplexity","display_name":"Perplexity Advanced Deep Research","author":"perplexity","provider":"perplexity","description":"Institutional-grade research agent that runs many rounds of web search and page reading, with maximum depth and extensive source coverage.","modality":"text","type":"research","category":"research","category_label":null,"modality_label":null,"modalities":["text","image","document"],"input_modalities":["text","image","document"],"output_modalities":["text"],"features":["web_search","reasoning","deep_research"],"aliases":[],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":16000,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"How much the model reasons while it researches. high is the most thorough, takes the longest and uses the most tokens.","required":false,"metadata":{},"default":"medium","options":["low","medium","high"]},{"name":"max_output_tokens","label":"Max Output Tokens","type":"number","description":"Maximum tokens in the final answer (does not count research steps). Range 10000-16000.","required":false,"metadata":{},"default":10000,"min":10000,"max":16000},{"name":"max_tokens_per_page","label":"Max Tokens Per Page","type":"number","description":"Max tokens extracted per search result page, from 1 to 16384. Higher = more content per source but slower.","required":false,"metadata":{},"default":4096,"min":1,"max":16384},{"name":"max_results","label":"Max Search Results","type":"number","description":"Most results each web search returns. More results give more sources to draw on.","required":false,"metadata":{},"default":15,"min":1,"max":50},{"name":"search_domain_filter","label":"Search Domain Filter","type":"string","description":"Comma-separated domains. Prefix with '-' to exclude. Max 200.","required":false,"metadata":{}},{"name":"search_recency_filter","label":"Search Recency Filter","type":"enum","description":"Relative time filter. Cannot be combined with specific dates.","required":false,"metadata":{},"default":"none","options":["none","hour","day","week","month","year"]},{"name":"search_after_date","label":"Search After Date","type":"string","description":"Only include sources published after this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"search_before_date","label":"Search Before Date","type":"string","description":"Only include sources published before this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"country","label":"Country","type":"string","description":"Two-letter ISO 3166-1 code (e.g. US, GB) for biasing results to a country.","required":false,"metadata":{}},{"name":"region","label":"Region","type":"string","description":"State or province name for location bias.","required":false,"metadata":{}},{"name":"city","label":"City","type":"string","description":"City name for location bias.","required":false,"metadata":{}},{"name":"latitude","label":"Latitude","type":"number","description":"Latitude for location bias, in decimal degrees.","required":false,"metadata":{}},{"name":"longitude","label":"Longitude","type":"number","description":"Longitude for location bias, in decimal degrees.","required":false,"metadata":{}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Skip the EmpirioLabs Markdown formatting (citation hyperlinks + References block + reasoning_content render). The plain answer text and the structured reasoning_steps array (with search queries, results, and fetched URLs) are still returned. Applies to /v1/chat/completions and /v1/messages.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1/search","POST /v1beta/models/perplexity-advanced-deep-research:generateContent"],"pricing":{"prompt":"0.000012","completion":"0.00006","image":"0","request":"0","input_cache_read":"0.000012"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$12.00"},{"spec":"per 1M generated tokens","label":"Output","value":"$60.00"},{"spec":"per call","label":"Web Search Call","value":"$0.012"},{"spec":"per call","label":"URL Fetch Call","value":"$0.0012"}],"unit_pricing":[{"unit":"1m_tokens","usd":"12","label":"Input"},{"unit":"1m_tokens","usd":"60","label":"Output"},{"unit":"call","usd":"0.012","label":"Web Search Call"},{"unit":"call","usd":"0.0012","label":"URL Fetch Call"}],"limits":{},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=perplexity-advanced-deep-research","api_url":"https://docs.empiriolabs.ai/models/perplexity-advanced-deep-research","logo":"https://media.empiriolabs.ai/model-logos/perplexity-adv-deep-research.png","status":"available"},{"id":"perplexity-deep-research","object":"model","created":1735689600,"owned_by":"perplexity","display_name":"Perplexity Deep Research","author":"perplexity","provider":"perplexity","description":"Research model for multi-step retrieval, synthesis, and reasoning, autonomously searching, reading, and evaluating sources across complex topics.","modality":"text","type":"research","category":"research","category_label":null,"modality_label":null,"modalities":["text","image","document"],"input_modalities":["text","image","document"],"output_modalities":["text"],"features":["web_search","reasoning","deep_research"],"aliases":[],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":919327,"context_length":919327,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum tokens in the response, at least 16. When omitted, the model's own default applies.","required":false,"metadata":{},"min":16,"max":65536},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"How much the model reasons while it researches. high is the most thorough, takes the longest and uses the most tokens.","required":false,"metadata":{},"default":"medium","options":["low","medium","high"]},{"name":"search_domain_filter","label":"Search Domain Filter","type":"string","description":"Comma-separated domains. Prefix with '-' to exclude. Max 200.","required":false,"metadata":{}},{"name":"max_results","label":"Max Search Results","type":"number","description":"Most results each web search returns. More results give more sources to draw on.","required":false,"metadata":{},"default":15,"min":1,"max":50},{"name":"search_after_date_filter","label":"Search After Date Filter","type":"string","description":"Only include sources published after this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"search_before_date_filter","label":"Search Before Date Filter","type":"string","description":"Only include sources published before this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"search_recency_filter","label":"Search Recency Filter","type":"enum","description":"Relative time filter. Cannot be combined with specific dates.","required":false,"metadata":{},"default":"none","options":["none","hour","day","week","month","year"]},{"name":"last_updated_after_filter","label":"Last Updated After Filter","type":"string","description":"Only include sources last updated after this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"last_updated_before_filter","label":"Last Updated Before Filter","type":"string","description":"Only include sources last updated before this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"country","label":"Country","type":"string","description":"Two-letter ISO 3166-1 code (e.g. US, GB) for biasing results to a country.","required":false,"metadata":{}},{"name":"region","label":"Region","type":"string","description":"State or province name for location bias.","required":false,"metadata":{}},{"name":"city","label":"City","type":"string","description":"City name for location bias.","required":false,"metadata":{}},{"name":"latitude","label":"Latitude","type":"number","description":"Latitude for location bias, in decimal degrees.","required":false,"metadata":{}},{"name":"longitude","label":"Longitude","type":"number","description":"Longitude for location bias, in decimal degrees.","required":false,"metadata":{}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Skip the EmpirioLabs Markdown formatting (citation [[N]](url) rewriting + References block + <think> extraction to reasoning_content). Raw mode keeps the <think>...</think> tags inside content so callers can parse reasoning themselves.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1/search","POST /v1beta/models/perplexity-deep-research:generateContent"],"pricing":{"prompt":"0.0000048","completion":"0.000019","image":"0","request":"0","input_cache_read":"0.0000048"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$4.80"},{"spec":"per 1M generated tokens","label":"Output","value":"$19.00"},{"spec":"per 1M tokens","label":"Citation Tokens","value":"$4.80"},{"spec":"per 1M tokens","label":"Reasoning Tokens","value":"$7.20"},{"spec":"per query","label":"Search Queries","value":"$0.012"}],"unit_pricing":[{"unit":"1m_tokens","usd":"4.8","label":"Input"},{"unit":"1m_tokens","usd":"19","label":"Output"},{"unit":"1m_tokens","usd":"4.8","label":"Citation Tokens"},{"unit":"1m_tokens","usd":"7.2","label":"Reasoning Tokens"},{"unit":"search","usd":"0.012","label":"Search Queries"}],"limits":{"note":"Long-running multi-step retrieval and reasoning. Pricing splits Input / Output / Citation / Reasoning tokens plus per-query search charge."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=perplexity-deep-research","api_url":"https://docs.empiriolabs.ai/models/perplexity-deep-research","logo":"https://media.empiriolabs.ai/model-logos/perplexity-deep-research.png","status":"available"},{"id":"perplexity-pro-search","object":"model","created":1735689600,"owned_by":"perplexity","display_name":"Perplexity Pro Search","author":"perplexity","provider":"perplexity","description":"Sonar Pro as an agentic researcher: chains web searches, fetches full pages, and streams live reasoning, adapting strategy for complex queries.","modality":"text","type":"search","category":"research","category_label":null,"modality_label":null,"modalities":["text","image"],"input_modalities":["text","image"],"output_modalities":["text"],"features":["web_search"],"aliases":[],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":32768,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum tokens in the response, at least 16. When omitted, the model's own default applies.","required":false,"metadata":{},"min":16,"max":32768},{"name":"search_context_size","label":"Search Context Size","type":"enum","description":"Higher context gives better answers but increases the base fee per request.","required":false,"metadata":{},"default":"medium","options":["low","medium","high"]},{"name":"search_mode","label":"Search Mode","type":"enum","description":"Filter search results by source type. Academic limits search to scholarly publishers. SEC adds financial filings and company data.","required":false,"metadata":{},"default":"default","options":["default","academic","sec"]},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"How much the model reasons before it answers. Higher is more thorough and slower.","required":false,"metadata":{},"default":"minimal","options":["minimal","low","medium","high"]},{"name":"search_domain_filter","label":"Search Domain Filter","type":"string","description":"Comma-separated domains. Prefix with '-' to exclude. Max 200.","required":false,"metadata":{}},{"name":"max_results","label":"Max Search Results","type":"number","description":"Most results each web search returns. More results give more sources to draw on.","required":false,"metadata":{},"default":15,"min":1,"max":50},{"name":"search_after_date","label":"Search After Date","type":"string","description":"Only include sources published after this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"search_before_date","label":"Search Before Date","type":"string","description":"Only include sources published before this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"search_recency_filter","label":"Search Recency Filter","type":"enum","description":"Relative time filter. Cannot be combined with specific dates.","required":false,"metadata":{},"default":"none","options":["none","hour","day","week","month","year"]},{"name":"last_updated_after_filter","label":"Last Updated After Filter","type":"string","description":"Only include sources last updated after this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"last_updated_before_filter","label":"Last Updated Before Filter","type":"string","description":"Only include sources last updated before this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"country","label":"Country","type":"string","description":"Two-letter ISO 3166-1 code (e.g. US, GB) for biasing results to a country.","required":false,"metadata":{}},{"name":"region","label":"Region","type":"string","description":"State or province name for location bias.","required":false,"metadata":{}},{"name":"city","label":"City","type":"string","description":"City name for location bias.","required":false,"metadata":{}},{"name":"latitude","label":"Latitude","type":"number","description":"Latitude for location bias, in decimal degrees.","required":false,"metadata":{}},{"name":"longitude","label":"Longitude","type":"number","description":"Longitude for location bias, in decimal degrees.","required":false,"metadata":{}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Skip the EmpirioLabs Markdown formatting (citation [[N]](url) rewriting + References block + Images / Videos blocks + reasoning_content render). The plain answer text and the structured reasoning_steps array from Perplexity are still returned.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1/search","POST /v1beta/models/perplexity-pro-search:generateContent"],"pricing":{"prompt":"0.0000078","completion":"0.000039","image":"0","request":"0.036","input_cache_read":"0.0000078"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$7.80"},{"spec":"per 1M generated tokens","label":"Output","value":"$39.00"},{"spec":"per request","label":"Base Fee (Low Context)","value":"$0.036"},{"spec":"per request","label":"Base Fee (Medium Context)","value":"$0.047"},{"spec":"per request","label":"Base Fee (High Context)","value":"$0.057"}],"unit_pricing":[{"unit":"1m_tokens","usd":"7.8","label":"Input"},{"unit":"1m_tokens","usd":"39","label":"Output"},{"unit":"request","usd":"0.036","label":"Base Fee (Low Context)"},{"unit":"request","usd":"0.047","label":"Base Fee (Medium Context)"},{"unit":"request","usd":"0.057","label":"Base Fee (High Context)"}],"limits":{"note":"**Search context size**\n\n- Low / Medium / High: controls depth and cost\n\n**Search modes**\n\n- `academic`: scholarly publishers only\n- `sec`: adds financial filings and company data\n\n**Date filters**\n\n- Specific date filters and recency filters are mutually exclusive\n- Explicit dates take priority\n\n**Optional location filters**\n\n- country, region, city, latitude/longitude\n- Coordinates need a country"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=perplexity-pro-search","api_url":"https://docs.empiriolabs.ai/models/perplexity-pro-search","logo":"https://media.empiriolabs.ai/model-logos/perplexity-pro-search.png","status":"available"},{"id":"perplexity-search","object":"model","created":1735689600,"owned_by":"perplexity","display_name":"Perplexity Search","author":"perplexity","provider":"perplexity","description":"Real-time web search with filtering by domain, language, date, and more. Returns search results, not LLM responses; no file uploads.","modality":"text","type":"search","category":"research","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["web_search","no_llm"],"aliases":[],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"query","label":"Query","type":"string","description":"The natural-language search query.","required":true,"metadata":{}},{"name":"max_results","label":"Max Results","type":"number","description":"Maximum number of results to return.","required":false,"metadata":{},"default":10,"min":1,"max":20},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum tokens extracted across all results.","required":false,"metadata":{},"default":1000000,"min":1,"max":1000000},{"name":"max_tokens_per_page","label":"Max Tokens Per Page","type":"number","description":"Max tokens extracted per individual result page.","required":false,"metadata":{},"default":4096,"min":1,"max":16384},{"name":"multi_query_mode","label":"Multi Query Mode","type":"boolean","description":"Let Perplexity expand the query into multiple parallel searches for broader coverage.","required":false,"metadata":{},"default":false},{"name":"search_domain_filter","label":"Search Domain Filter","type":"string","description":"Comma-separated domains. Prefix with '-' to exclude. Max 200.","required":false,"metadata":{}},{"name":"search_language_filter","label":"Search Language Filter","type":"string","description":"Comma-separated ISO 639-1 codes (2 letters). Max 10.","required":false,"metadata":{}},{"name":"search_recency_filter","label":"Search Recency Filter","type":"enum","description":"Relative time filter (hour | day | week | month | year).","required":false,"metadata":{},"default":"none","options":["none","hour","day","week","month","year"]},{"name":"search_after_date_filter","label":"Search After Date Filter","type":"string","description":"Use MM/DD/YYYY or YYYY-MM-DD. Only include sources after this date.","required":false,"metadata":{}},{"name":"search_before_date_filter","label":"Search Before Date Filter","type":"string","description":"Use MM/DD/YYYY or YYYY-MM-DD. Only include sources before this date.","required":false,"metadata":{}},{"name":"last_updated_after_filter","label":"Last Updated After Filter","type":"string","description":"Use MM/DD/YYYY or YYYY-MM-DD. Only include sources after this date.","required":false,"metadata":{}},{"name":"last_updated_before_filter","label":"Last Updated Before Filter","type":"string","description":"Use MM/DD/YYYY or YYYY-MM-DD. Only include sources before this date.","required":false,"metadata":{}},{"name":"country","label":"Country","type":"string","description":"Two-letter ISO 3166-1 code (US, GB, etc.) for biasing results to a country.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/search"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0.006","input_cache_read":"0"},"pricing_rows":[{"spec":"per request","label":"Search Request","value":"$0.0060"}],"unit_pricing":[{"unit":"request","usd":"0.006","label":"Search Request"}],"limits":{"note":"Returns title/url/snippet only, no LLM-style answer. Up to 5 queries via newline-separated `multi_query`."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=perplexity-search","api_url":"https://docs.empiriolabs.ai/models/perplexity-search","logo":"https://media.empiriolabs.ai/model-logos/perplexity-search.png","status":"available"},{"id":"perplexity-sonar","object":"model","created":1735689600,"owned_by":"perplexity","display_name":"Perplexity Sonar","author":"perplexity","provider":"perplexity","description":"Real-time web-connected search with accurate citations and customizable sources for up-to-date AI search integration in production apps.","modality":"text","type":"search","category":"research","category_label":null,"modality_label":null,"modalities":["text","image","document"],"input_modalities":["text","image","document"],"output_modalities":["text"],"features":["web_search"],"aliases":["perplexity/sonar"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":919327,"context_length":919327,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum tokens in the response, at least 16. When omitted, the model's own default applies.","required":false,"metadata":{},"min":16,"max":32768},{"name":"search_context_size","label":"Search Context Size","type":"enum","description":"Higher context gives better answers but increases the base fee per request.","required":false,"metadata":{},"default":"medium","options":["low","medium","high"]},{"name":"search_mode","label":"Search Mode","type":"enum","description":"Filter search results by source type. Academic limits search to scholarly publishers. SEC adds financial filings and company data.","required":false,"metadata":{},"default":"default","options":["default","academic","sec"]},{"name":"search_domain_filter","label":"Search Domain Filter","type":"string","description":"Comma-separated domains. Prefix with '-' to exclude. Max 200.","required":false,"metadata":{}},{"name":"max_results","label":"Max Search Results","type":"number","description":"Most results each web search returns. More results give more sources to draw on.","required":false,"metadata":{},"default":10,"min":1,"max":50},{"name":"search_after_date","label":"Search After Date","type":"string","description":"Only include sources published after this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"search_before_date","label":"Search Before Date","type":"string","description":"Only include sources published before this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"search_recency_filter","label":"Search Recency Filter","type":"enum","description":"Relative time filter. Cannot be combined with specific dates.","required":false,"metadata":{},"default":"none","options":["none","hour","day","week","month","year"]},{"name":"last_updated_after_filter","label":"Last Updated After Filter","type":"string","description":"Only include sources last updated after this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"last_updated_before_filter","label":"Last Updated Before Filter","type":"string","description":"Only include sources last updated before this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"country","label":"Country","type":"string","description":"Two-letter ISO 3166-1 code (e.g. US, GB) for biasing results to a country.","required":false,"metadata":{}},{"name":"region","label":"Region","type":"string","description":"State or province name for location bias.","required":false,"metadata":{}},{"name":"city","label":"City","type":"string","description":"City name for location bias.","required":false,"metadata":{}},{"name":"latitude","label":"Latitude","type":"number","description":"Latitude for location bias, in decimal degrees.","required":false,"metadata":{}},{"name":"longitude","label":"Longitude","type":"number","description":"Longitude for location bias, in decimal degrees.","required":false,"metadata":{}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers, and no References, Images or Videos block is added. search_results and citations are still returned.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1/search","POST /v1beta/models/perplexity-sonar:generateContent"],"pricing":{"prompt":"0.0000024","completion":"0.0000024","image":"0","request":"0.012","input_cache_read":"0.0000024"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$2.40"},{"spec":"per 1M generated tokens","label":"Output","value":"$2.40"},{"spec":"per request","label":"Base Fee (Low Context)","value":"$0.012"},{"spec":"per request","label":"Base Fee (Medium Context)","value":"$0.019"},{"spec":"per request","label":"Base Fee (High Context)","value":"$0.029"}],"unit_pricing":[{"unit":"1m_tokens","usd":"2.4","label":"Input"},{"unit":"1m_tokens","usd":"2.4","label":"Output"},{"unit":"request","usd":"0.012","label":"Base Fee (Low Context)"},{"unit":"request","usd":"0.019","label":"Base Fee (Medium Context)"},{"unit":"request","usd":"0.029","label":"Base Fee (High Context)"}],"limits":{},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=perplexity-sonar","api_url":"https://docs.empiriolabs.ai/models/perplexity-sonar","logo":"https://media.empiriolabs.ai/model-logos/perplexity-sonar.png","status":"available"},{"id":"perplexity-sonar-pro","object":"model","created":1735689600,"owned_by":"perplexity","display_name":"Perplexity Sonar Pro","author":"perplexity","provider":"perplexity","description":"Search-grounded model with double the citations and a larger context window, tuned for complex queries needing in-depth, nuanced answers.","modality":"text","type":"search","category":"research","category_label":null,"modality_label":null,"modalities":["text","image","document"],"input_modalities":["text","image","document"],"output_modalities":["text"],"features":["web_search"],"aliases":["perplexity/sonar-pro"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":919328,"context_length":919328,"max_output_tokens":32768,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum tokens in the response, at least 16. When omitted, the model's own default applies.","required":false,"metadata":{},"min":16,"max":32768},{"name":"search_context_size","label":"Search Context Size","type":"enum","description":"Higher context gives better answers but increases the base fee per request.","required":false,"metadata":{},"default":"medium","options":["low","medium","high"]},{"name":"search_mode","label":"Search Mode","type":"enum","description":"Filter search results by source type. Academic limits search to scholarly publishers. SEC adds financial filings and company data.","required":false,"metadata":{},"default":"default","options":["default","academic","sec"]},{"name":"search_domain_filter","label":"Search Domain Filter","type":"string","description":"Comma-separated domains. Prefix with '-' to exclude. Max 200.","required":false,"metadata":{}},{"name":"max_results","label":"Max Search Results","type":"number","description":"Most results each web search returns. More results give more sources to draw on.","required":false,"metadata":{},"default":15,"min":1,"max":50},{"name":"search_after_date","label":"Search After Date","type":"string","description":"Only include sources published after this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"search_before_date","label":"Search Before Date","type":"string","description":"Only include sources published before this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"search_recency_filter","label":"Search Recency Filter","type":"enum","description":"Relative time filter. Cannot be combined with specific dates.","required":false,"metadata":{},"default":"none","options":["none","hour","day","week","month","year"]},{"name":"last_updated_after_filter","label":"Last Updated After Filter","type":"string","description":"Only include sources last updated after this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"last_updated_before_filter","label":"Last Updated Before Filter","type":"string","description":"Only include sources last updated before this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"country","label":"Country","type":"string","description":"Two-letter ISO 3166-1 code (e.g. US, GB) for biasing results to a country.","required":false,"metadata":{}},{"name":"region","label":"Region","type":"string","description":"State or province name for location bias.","required":false,"metadata":{}},{"name":"city","label":"City","type":"string","description":"City name for location bias.","required":false,"metadata":{}},{"name":"latitude","label":"Latitude","type":"number","description":"Latitude for location bias, in decimal degrees.","required":false,"metadata":{}},{"name":"longitude","label":"Longitude","type":"number","description":"Longitude for location bias, in decimal degrees.","required":false,"metadata":{}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers, and no References, Images or Videos block is added. search_results and citations are still returned.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1/search","POST /v1beta/models/perplexity-sonar-pro:generateContent"],"pricing":{"prompt":"0.0000072","completion":"0.000036","image":"0","request":"0.014","input_cache_read":"0.0000072"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$7.20"},{"spec":"per 1M generated tokens","label":"Output","value":"$36.00"},{"spec":"per request","label":"Base Fee (Low Context)","value":"$0.014"},{"spec":"per request","label":"Base Fee (Medium Context)","value":"$0.024"},{"spec":"per request","label":"Base Fee (High Context)","value":"$0.034"}],"unit_pricing":[{"unit":"1m_tokens","usd":"7.2","label":"Input"},{"unit":"1m_tokens","usd":"36","label":"Output"},{"unit":"request","usd":"0.014","label":"Base Fee (Low Context)"},{"unit":"request","usd":"0.024","label":"Base Fee (Medium Context)"},{"unit":"request","usd":"0.034","label":"Base Fee (High Context)"}],"limits":{"note":"Double the citations and larger context window vs Sonar. Max output 32K tokens."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=perplexity-sonar-pro","api_url":"https://docs.empiriolabs.ai/models/perplexity-sonar-pro","logo":"https://media.empiriolabs.ai/model-logos/perplexity-sonar-pro.png","status":"available"},{"id":"perplexity-sonar-reasoning-pro","object":"model","created":1735689600,"owned_by":"perplexity","display_name":"Perplexity Sonar Reasoning Pro","author":"perplexity","provider":"perplexity","description":"Reasoning model that researches over several rounds of web search, chaining evidence across many sources before it answers, with inline citations.","modality":"text","type":"search","category":"research","category_label":null,"modality_label":null,"modalities":["text","image","document"],"input_modalities":["text","image","document"],"output_modalities":["text"],"features":["web_search","reasoning"],"aliases":["perplexity/sonar-reasoning-pro"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":919330,"context_length":919330,"max_output_tokens":131072,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum tokens in the response, at least 16. When omitted, the model's own default applies.","required":false,"metadata":{},"min":16,"max":131072},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"How much the model reasons before it answers. Higher is more thorough and slower.","required":false,"metadata":{},"default":"medium","options":["low","medium","high"]},{"name":"search_context_size","label":"Search Context Size","type":"enum","description":"Higher context gives better answers but increases the base fee per request.","required":false,"metadata":{},"default":"medium","options":["low","medium","high"]},{"name":"search_mode","label":"Search Mode","type":"enum","description":"Filter search results by source type. Academic limits search to scholarly publishers. SEC adds financial filings and company data.","required":false,"metadata":{},"default":"default","options":["default","academic","sec"]},{"name":"search_domain_filter","label":"Search Domain Filter","type":"string","description":"Comma-separated domains. Prefix with '-' to exclude. Max 200.","required":false,"metadata":{}},{"name":"max_results","label":"Max Search Results","type":"number","description":"Most results each web search returns. More results give more sources to draw on.","required":false,"metadata":{},"default":15,"min":1,"max":50},{"name":"search_after_date","label":"Search After Date","type":"string","description":"Only include sources published after this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"search_before_date","label":"Search Before Date","type":"string","description":"Only include sources published before this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"search_recency_filter","label":"Search Recency Filter","type":"enum","description":"Relative time filter. Cannot be combined with specific dates.","required":false,"metadata":{},"default":"none","options":["none","hour","day","week","month","year"]},{"name":"last_updated_after_filter","label":"Last Updated After Filter","type":"string","description":"Only include sources last updated after this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"last_updated_before_filter","label":"Last Updated Before Filter","type":"string","description":"Only include sources last updated before this date. Use MM/DD/YYYY or YYYY-MM-DD.","required":false,"metadata":{}},{"name":"country","label":"Country","type":"string","description":"Two-letter ISO 3166-1 code (e.g. US, GB) for biasing results to a country.","required":false,"metadata":{}},{"name":"region","label":"Region","type":"string","description":"State or province name for location bias.","required":false,"metadata":{}},{"name":"city","label":"City","type":"string","description":"City name for location bias.","required":false,"metadata":{}},{"name":"latitude","label":"Latitude","type":"number","description":"Latitude for location bias, in decimal degrees.","required":false,"metadata":{}},{"name":"longitude","label":"Longitude","type":"number","description":"Longitude for location bias, in decimal degrees.","required":false,"metadata":{}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Skip the EmpirioLabs Markdown formatting (citation [[N]](url) rewriting + References block + Images / Videos blocks + <think> extraction to reasoning_content). Raw mode keeps the <think>...</think> tags inside content; structured search_results / citations still pass through.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1/search","POST /v1beta/models/perplexity-sonar-reasoning-pro:generateContent"],"pricing":{"prompt":"0.0000048","completion":"0.000019","image":"0","request":"0.014","input_cache_read":"0.0000048"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$4.80"},{"spec":"per 1M generated tokens","label":"Output","value":"$19.00"},{"spec":"per request","label":"Base Fee (Low Context)","value":"$0.014"},{"spec":"per request","label":"Base Fee (Medium Context)","value":"$0.024"},{"spec":"per request","label":"Base Fee (High Context)","value":"$0.034"}],"unit_pricing":[{"unit":"1m_tokens","usd":"4.8","label":"Input"},{"unit":"1m_tokens","usd":"19","label":"Output"},{"unit":"request","usd":"0.014","label":"Base Fee (Low Context)"},{"unit":"request","usd":"0.024","label":"Base Fee (Medium Context)"},{"unit":"request","usd":"0.034","label":"Base Fee (High Context)"}],"limits":{},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=perplexity-sonar-reasoning-pro","api_url":"https://docs.empiriolabs.ai/models/perplexity-sonar-reasoning-pro","logo":"https://media.empiriolabs.ai/model-logos/perplexity-sonar-rsn-pro.png","status":"available"},{"id":"pixverse-v5","object":"model","created":1756425600,"owned_by":"pixverse","display_name":"Pixverse v5","author":"pixverse","provider":"pixverse","description":"Cinematic video generation in Text-to-Video, Image-to-Video, and Transition modes with high detail, fluid motion, and lifelike animations.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image"],"output_modalities":["video"],"features":["audio","styles"],"aliases":["pixverse/v5"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-08-29","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"auto picks the mode from your attachments: transition with an end frame, i2v with an image, otherwise t2v. t2v: text to video. i2v: animate one image. transition: interpolate between a first and last frame.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v","transition"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution. Larger = higher fidelity but slower / more expensive.","required":false,"metadata":{},"default":"720p","options":["360p","540p","720p","1080p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio for text-to-video. Image modes follow the source image.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"16:9","options":["16:9","4:3","1:1","3:4","9:16"]},{"name":"duration","label":"Duration","type":"enum","description":"1080p only supports 5s.","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":"5s","options":["5s","8s"]},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"Text description of what to avoid in the output.","required":false,"metadata":{},"default":""},{"name":"image","label":"Image","type":"string","description":"Reference image URL. Required for i2v / transition.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"image_end","label":"Image End","type":"string","description":"End-frame image URL for transition mode.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0.23","input_cache_read":"0"},"pricing_rows":[{"spec":"per video","label":"360p/540p 5s","value":"$0.23"},{"spec":"per video","label":"360p/540p 8s","value":"$0.46"},{"spec":"per video","label":"720p 5s","value":"$0.306667"},{"spec":"per video","label":"720p 8s","value":"$0.613333"},{"spec":"per video","label":"1080p 5s","value":"$0.613333"}],"unit_pricing":[{"unit":"video","usd":"0.23","label":"360p/540p 5s"},{"unit":"video","usd":"0.46","label":"360p/540p 8s"},{"unit":"video","usd":"0.306667","label":"720p 5s"},{"unit":"video","usd":"0.613333","label":"720p 8s"},{"unit":"video","usd":"0.613333","label":"1080p 5s"}],"limits":{"note":"Cinematic video generation in Text-to-Video, Image-to-Video, and Transition modes."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=pixverse-v5","api_url":"https://docs.empiriolabs.ai/models/pixverse-v5","logo":"https://media.empiriolabs.ai/model-logos/pixverse-v5.png","status":"available"},{"id":"pixverse-v5-6","object":"model","created":1769385600,"owned_by":"pixverse","display_name":"Pixverse v5.6","author":"pixverse","provider":"pixverse","description":"Generates videos from text or 1-2 frame image prompts up to 1080p, multiple aspect ratios, 5-10s durations, with optional synchronized audio.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image"],"output_modalities":["video"],"features":["audio","styles","reference_to_video"],"aliases":["pixverse-v5.6","pixverse/v5.6"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-01-26","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"auto picks the mode from your attachments: reference with two or more images, i2v with one image, otherwise t2v. t2v: text to video. i2v: animate one image. reference: combine up to 7 reference images in a new scene.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v","reference"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution. Larger = higher fidelity but slower / more expensive.","required":false,"metadata":{},"default":"1080p","options":["360p","540p","720p","1080p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio for text-to-video and reference mode. Image-to-video follows the source image.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"16:9","options":["16:9","4:3","1:1","3:4","9:16"]},{"name":"duration","label":"Duration","type":"enum","description":"1080p only supports 5s and 8s.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"variants":[{"when":{"op":"eq","field":"resolution","value":"1080p"},"options":["5","8"],"allowed_values":["5","8"]}]},"default":"5s","options":["5s","8s","10s"]},{"name":"audio","label":"Audio","type":"boolean","description":"Generate native audio with the video.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":true},{"name":"image","label":"Image","type":"string","description":"Reference image URL. Required for i2v.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"image_end","label":"Image End","type":"string","description":"Optional last-frame image URL for image-to-video.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"style","label":"Style","type":"enum","description":"Stylization preset. Applies to text-to-video and image-to-video.","required":false,"metadata":{"hidden_when":{"op":"eq","field":"mode","value":"reference"},"clear_when_hidden":true},"default":"none","options":["none","anime","3d_animation","clay","comic","cyberpunk"]},{"name":"thinking","label":"Thinking","type":"enum","description":"Whether the model uses chain-of-thought before generating. auto lets PixVerse decide. Applies to text-to-video and image-to-video.","required":false,"metadata":{"hidden_when":{"op":"eq","field":"mode","value":"reference"},"clear_when_hidden":true},"default":"auto","options":["auto","enabled","disabled"]},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid (≤2048 chars). Applies to text-to-video and image-to-video.","required":false,"metadata":{"hidden_when":{"op":"eq","field":"mode","value":"reference"},"clear_when_hidden":true},"default":""},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed.","required":false,"metadata":{}},{"name":"reference_images","label":"Reference Images","type":"string","description":"Reference image URLs for reference mode, as a list. Up to 7 images.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"reference_names","label":"Reference Names","type":"string","description":"Comma-separated names for the attached reference images, in order, so the prompt can address them as @name.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0.35","input_cache_read":"0"},"pricing_rows":[{"spec":"per video","label":"360p/540p 5s no audio","value":"$0.35"},{"spec":"per video","label":"360p/540p 5s audio","value":"$0.80"},{"spec":"per video","label":"360p/540p 8s no audio","value":"$0.70"},{"spec":"per video","label":"360p/540p 8s audio","value":"$1.15"},{"spec":"per video","label":"360p/540p 10s no audio","value":"$0.77"},{"spec":"per video","label":"360p/540p 10s audio","value":"$1.22"},{"spec":"per video","label":"720p 5s no audio","value":"$0.45"},{"spec":"per video","label":"720p 5s audio","value":"$0.90"},{"spec":"per video","label":"720p 8s no audio","value":"$0.90"},{"spec":"per video","label":"720p 8s audio","value":"$1.35"},{"spec":"per video","label":"720p 10s no audio","value":"$0.99"},{"spec":"per video","label":"720p 10s audio","value":"$1.44"},{"spec":"per video","label":"1080p 5s no audio","value":"$0.75"},{"spec":"per video","label":"1080p 5s audio","value":"$1.50"},{"spec":"per video","label":"1080p 8s no audio","value":"$1.50"},{"spec":"per video","label":"1080p 8s audio","value":"$1.95"}],"unit_pricing":[{"unit":"video","usd":"0.35","label":"360p/540p 5s no audio"},{"unit":"video","usd":"0.8","label":"360p/540p 5s audio"},{"unit":"video","usd":"0.7","label":"360p/540p 8s no audio"},{"unit":"video","usd":"1.15","label":"360p/540p 8s audio"},{"unit":"video","usd":"0.77","label":"360p/540p 10s no audio"},{"unit":"video","usd":"1.22","label":"360p/540p 10s audio"},{"unit":"video","usd":"0.45","label":"720p 5s no audio"},{"unit":"video","usd":"0.9","label":"720p 5s audio"},{"unit":"video","usd":"0.9","label":"720p 8s no audio"},{"unit":"video","usd":"1.35","label":"720p 8s audio"},{"unit":"video","usd":"0.99","label":"720p 10s no audio"},{"unit":"video","usd":"1.44","label":"720p 10s audio"},{"unit":"video","usd":"0.75","label":"1080p 5s no audio"},{"unit":"video","usd":"1.5","label":"1080p 5s audio"},{"unit":"video","usd":"1.5","label":"1080p 8s no audio"},{"unit":"video","usd":"1.95","label":"1080p 8s audio"}],"limits":{"note":"Generates videos from text, 1-2 frame image prompts, or up to seven reference images, up to 1080p with optional audio.\n\n**Reference images**\n\n- `reference`: combine up to 7 reference images in a new scene. Send them as `reference_images`, or attach two or more images.\n- Name a reference with `reference_names` and address it in the prompt as `@name` followed by a space.\n- `style`, `thinking` and `negative_prompt` apply to text-to-video and image-to-video.\n\n**Uploaded media preprocessing**\n\n- Image inputs smaller than 300px are upscaled, images larger than 4000px are downscaled, and oversized image uploads are recompressed before generation."},"notes":"Generates videos from text, 1-2 frame image prompts, or up to seven reference images, up to 1080p with optional audio.\n\n**Reference images**\n\n- `reference`: combine up to 7 reference images in a new scene. Send them as `reference_images`, or attach two or more images.\n- Name a reference with `reference_names` and address it in the prompt as `@name` followed by a space.\n- `style`, `thinking` and `negative_prompt` apply to text-to-video and image-to-video.\n\n**Uploaded media preprocessing**\n\n- Image inputs smaller than 300px are upscaled, images larger than 4000px are downscaled, and oversized image uploads are recompressed before generation.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=pixverse-v5-6","api_url":"https://docs.empiriolabs.ai/models/pixverse-v5-6","logo":"https://media.empiriolabs.ai/model-logos/pixverse-v5-6.png","status":"available"},{"id":"qwen-image-2-0","object":"model","created":1772496000,"owned_by":"alibaba","display_name":"Qwen Image 2.0","author":"alibaba","provider":"alibaba","description":"Unified image generation and editing model with class-leading complex Chinese/English text rendering, realistic textures, and multi-image fusion.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text","image"],"output_modalities":["image"],"features":["text_rendering","image_editing","multi_image"],"aliases":[],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-03-03","is_new":false,"is_featured":false,"discount":{"label":"Save up to 8%","percent":8},"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Text prompt. With input images attached, becomes an editing instruction.","required":true,"metadata":{}},{"name":"model_variant","label":"Variant","type":"enum","description":"Pro variants offer higher quality. Dated snapshots pin a specific weights revision for reproducibility; the undated \"qwen-image-2.0-pro\" tracks the latest pro release.","required":false,"metadata":{},"default":"qwen-image-2.0-pro-2026-04-22","options":["qwen-image-2.0-pro-2026-04-22","qwen-image-2.0-pro-2026-03-03","qwen-image-2.0-pro","qwen-image-2.0"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Optional. If omitted, text-to-image defaults to 16:9; image-edit matches the last input image's native ratio.","required":false,"metadata":{"ui":{"control":"segmented"}},"options":["16:9","9:16","1:1","3:2","2:3","4:3","3:4","5:4","4:5"]},{"name":"use_custom_size","label":"Use Custom Size","type":"boolean","description":"Override aspect_ratio with explicit pixel dimensions.","required":false,"metadata":{},"default":false},{"name":"custom_width","label":"Custom Width","type":"number","description":"Pixels (512–2048). Total pixel area must be in [512×512, 2048×2048]. Only when use_custom_size=true.","required":false,"metadata":{"ui":{"step":1,"control":"text_field"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":512,"max":2048},{"name":"custom_height","label":"Custom Height","type":"number","description":"Pixels (512–2048). Total pixel area must be in [512×512, 2048×2048]. Only when use_custom_size=true.","required":false,"metadata":{"ui":{"step":1,"control":"text_field"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":512,"max":2048},{"name":"image","label":"Image","type":"string","description":"Up to 3 input image URLs. Triggers image-edit mode.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"num_images","label":"Num Images","type":"number","description":"Number of images to generate. Each is billed separately.","required":false,"metadata":{},"default":1,"min":1,"max":6},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid in the output.","required":false,"metadata":{},"default":""},{"name":"prompt_extend","label":"Prompt Extend","type":"boolean","description":"Automatically expand and refine the prompt for better results.","required":false,"metadata":{},"default":true},{"name":"watermark","label":"Watermark","type":"boolean","description":"When true, a small Qwen provenance watermark is stamped on each generated image. EmpirioLabs does not add any watermark of its own.","required":false,"metadata":{},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed. Leave empty for random.","required":false,"metadata":{},"min":0,"max":2147483647},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return signed image URLs by default, or include base64 image data when b64_json is requested.","required":false,"metadata":{},"default":"url","options":["url","b64_json"]}],"supported_endpoints":["POST /v1/images/generations"],"pricing":{"prompt":"0","completion":"0","image":"0.0322","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Standard","value":"$0.0322 (was $0.035)"},{"spec":"per image","label":"Pro","value":"$0.069 (was $0.075)"}],"unit_pricing":[{"unit":"image","usd":"0.0322","label":"Standard"},{"unit":"image","usd":"0.069","label":"Pro"}],"limits":{"note":"**Modes**\n\n- Text-to-image: no images attached\n- Image-editing: upload 1-3 images\n\n**Constraints**\n\n- Positive prompt: max 800 characters\n- Negative prompt: max 500 characters\n- Custom width/height: 512-2048 px (total area between 512x512 and 2048x2048)\n- Per image is billed\n\n**Performance**\n\n- Responses take 10-30 seconds depending on resolution, image count, and prompt complexity\n\n**Content safety**\n\n- Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen-image-2-0","api_url":"https://docs.empiriolabs.ai/models/qwen-image-2-0","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen-image-3-0","object":"model","created":1784592000,"owned_by":"alibaba","display_name":"Qwen Image 3.0","author":"alibaba","provider":"alibaba","description":"Qwen image generation and editing with Base and Pro variants, multilingual typography, multi-image references, and controllable 1K or 2K output.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text","image"],"output_modalities":["image"],"features":["image_generation","image_editing","multi_image","text_rendering","multilingual_text","dense_layouts","photorealism"],"aliases":["qwen-image-3.0","qwen-image-3-0-pro","qwen-image-3.0-pro","alibaba/qwen-image-3-0","alibaba/qwen-image-3.0","alibaba/qwen-image-3-0-pro","alibaba/qwen-image-3.0-pro"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-07-21","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Describe the image to create. With input images attached, this becomes the editing instruction. An image-only edit uses a neutral preservation prompt.","required":false,"metadata":{"ui":{"control":"text_area","section":"Input"}}},{"name":"model_variant","label":"Variant","type":"enum","description":"Choose Pro for stronger photorealism, dense layouts, fine multilingual typography, and complex edits, or Base for lower-cost generation. When this is not set, the model ids \"qwen-image-3.0\", \"alibaba/qwen-image-3.0\" and \"alibaba/qwen-image-3-0\" select Base and every other id of this model selects Pro.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Settings"}},"default":"qwen-image-3.0-pro","options":["qwen-image-3.0-pro","qwen-image-3.0"]},{"name":"image","label":"Images","type":"string","description":"One to three reference images as URLs, data URIs, or uploaded image objects.","required":false,"metadata":{"ui":{"accept":"image/*","control":"file","section":"Input","multiple":true,"max_files":3}}},{"name":"images","label":"Images","type":"string","description":"Plural alias for multiple uploaded image references.","required":false,"metadata":{"ui":{"hidden":true}}},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Optional output aspect ratio. Auto is the default. With a fixed 1K or 2K resolution, Auto uses that tier's square size. With Resolution set to Auto, the model chooses the complete output size.","required":false,"metadata":{"ui":{"control":"segmented","section":"Settings"}},"default":"auto","options":["auto","1:1","16:9","9:16","3:2","2:3","4:3","3:4","5:4","4:5"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output pixel tier. Defaults to 2K, the maximum supported tier. The 1K tier stays at or below 2.25 megapixels, while 2K is above 2.25 megapixels. Auto lets the model choose when Aspect Ratio is Auto; with a selected aspect ratio, Auto uses the 1K preset.","required":false,"metadata":{"ui":{"control":"segmented","section":"Settings"}},"default":"2K","options":["auto","1K","2K"]},{"name":"size","label":"Size","type":"string","description":"Exact output size as WIDTH*HEIGHT, for example 2048*1536. This overrides aspect_ratio and resolution.","required":false,"metadata":{"ui":{"section":"Advanced","hide_in_playground":true}}},{"name":"use_custom_size","label":"Use Custom Size","type":"boolean","description":"Use custom_width and custom_height instead of the aspect-ratio and resolution presets.","required":false,"metadata":{"ui":{"control":"toggle","section":"Settings"}},"default":false},{"name":"custom_width","label":"Custom Width","type":"number","description":"Custom output width in pixels. Total area must be between 512x512 and 2048x2048, with an aspect ratio from 1:8 to 8:1.","required":false,"metadata":{"ui":{"step":1,"control":"text_field","section":"Settings"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":256,"max":2048},{"name":"custom_height","label":"Custom Height","type":"number","description":"Custom output height in pixels. Total area must be between 512x512 and 2048x2048, with an aspect ratio from 1:8 to 8:1.","required":false,"metadata":{"ui":{"step":1,"control":"text_field","section":"Settings"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":256,"max":2048},{"name":"num_images","label":"Number of Images","type":"number","description":"Number of output images. Each output is billed separately.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Output"}},"default":1,"min":1,"max":6},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"Describe visual elements or qualities to avoid in the output.","required":false,"metadata":{"ui":{"control":"text_area","section":"Advanced"}},"default":""},{"name":"prompt_extend","label":"Prompt Extension","type":"boolean","description":"Expand the prompt automatically for stronger composition and detail.","required":false,"metadata":{"ui":{"control":"toggle","section":"Advanced"}},"default":true},{"name":"prompt_extend_mode","label":"Prompt Extension Mode","type":"enum","description":"Direct works for generation and editing. Agent performs deeper prompt refinement and is available for text-to-image requests only.","required":false,"metadata":{"ui":{"control":"segmented","section":"Advanced"},"visible_when":{"op":"eq","field":"prompt_extend","value":true}},"default":"direct","options":["direct","agent"]},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed. Leave empty for a random result.","required":false,"metadata":{"ui":{"step":1,"control":"text_field","section":"Advanced"}},"min":0,"max":2147483647},{"name":"watermark","label":"Watermark","type":"boolean","description":"Add the Qwen provenance watermark to the generated image. EmpirioLabs does not add a watermark of its own.","required":false,"metadata":{"ui":{"control":"toggle","section":"Advanced"}},"default":false},{"name":"response_format","label":"Response Format","type":"enum","description":"Return signed image URLs by default, or include base64 image data when b64_json is requested.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Output"}},"default":"url","options":["url","b64_json"]}],"supported_endpoints":["POST /v1/images/generations"],"pricing":{"prompt":"0","completion":"0","image":"0.03","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Base Output (1K or 2K)","value":"$0.030"},{"spec":"per image","label":"Pro Output up to 2.25MP (1K)","value":"$0.040"},{"spec":"per image","label":"Pro Output above 2.25MP (2K)","value":"$0.075"},{"spec":"per input image","label":"Input Image (1K or 2K)","value":"$0.003"}],"unit_pricing":[{"unit":"image","usd":"0.03","label":"Base Output (1K or 2K)"},{"unit":"image","usd":"0.04","label":"Pro Output up to 2.25MP (1K)"},{"unit":"image","usd":"0.075","label":"Pro Output above 2.25MP (2K)"},{"unit":"image","usd":"0.003","label":"Input Image (1K or 2K)"}],"limits":{"note":"Qwen Image 3.0 combines Base and Pro image generation and editing in one model. Pro is selected by default, output starts at 2K, and aspect ratio starts in Auto. Base provides a lower-cost option for fast iteration.\n\n**Variants**\n\n- Choose qwen-image-3.0-pro for photorealism, dense layouts, fine multilingual typography, and complex multi-image edits.\n- Choose qwen-image-3.0 for lower-cost generation and routine edits.\n- Choose with model_variant. Without it, the model ids qwen-image-3.0, alibaba/qwen-image-3.0 and alibaba/qwen-image-3-0 run Base and every other id of this model runs Pro.\n\n**Modes**\n\n- Text to image from a prompt.\n- Image editing and reference-guided generation from one to three images.\n- Direct prompt extension works for generation and editing. Agent prompt extension provides deeper refinement for text-to-image requests only.\n\n**Output and input limits**\n\n- One to six output images per request.\n- 1K, 2K, automatic, aspect-ratio presets, or an exact custom size.\n- Preset and custom sizes stay between 512x512 and 2048x2048 pixels, with each selected side up to 2048 pixels and aspect ratio from 1:8 to 8:1. Automatic sizing can choose its own dimensions within the 1K or 2K output tiers.\n- Input images can be JPG, JPEG, PNG, BMP, TIFF, WEBP, or GIF, up to 10 MB each.\n- Prompts support up to 4,500 tokens.\n\n**Billing**\n\n- Base uses one output rate across 1K and 2K.\n- Pro outputs up to 2.25 megapixels use the 1K rate. Larger Pro outputs use the 2K rate.\n- Every reference image adds the input-image rate shown above.\n\n**Performance**\n\n- 1K generations are optimized for interactive iteration. Complex 2K edits can take several minutes.\n\n**Content safety**\n\nGenerated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed."},"notes":"Qwen Image 3.0 combines Base and Pro image generation and editing in one model. Pro is selected by default, output starts at 2K, and aspect ratio starts in Auto. Base provides a lower-cost option for fast iteration.\n\n**Variants**\n\n- Choose qwen-image-3.0-pro for photorealism, dense layouts, fine multilingual typography, and complex multi-image edits.\n- Choose qwen-image-3.0 for lower-cost generation and routine edits.\n\n**Modes**\n\n- Text to image from a prompt.\n- Image editing and reference-guided generation from one to three images.\n- Direct prompt extension works for generation and editing. Agent prompt extension provides deeper refinement for text-to-image requests only.\n\n**Output and input limits**\n\n- One to six output images per request.\n- 1K, 2K, automatic, aspect-ratio presets, or an exact custom size.\n- Preset and custom sizes stay between 512x512 and 2048x2048 pixels, with each selected side up to 2048 pixels and aspect ratio from 1:8 to 8:1. Automatic sizing can choose its own dimensions within the 1K or 2K output tiers.\n- Input images can be JPG, JPEG, PNG, BMP, TIFF, WEBP, or GIF, up to 10 MB each.\n- Prompts support up to 4,500 tokens.\n\n**Billing**\n\n- Base uses one output rate across 1K and 2K.\n- Pro outputs up to 2.25 megapixels use the 1K rate. Larger Pro outputs use the 2K rate.\n- Every reference image adds the input-image rate shown above.\n\n**Performance**\n\n- 1K generations are optimized for interactive iteration. Complex 2K edits can take several minutes.\n\n**Content safety**\n\nGenerated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen-image-3-0","api_url":"https://docs.empiriolabs.ai/models/qwen-image-3-0","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-5-flash","object":"model","created":1771891200,"owned_by":"alibaba","display_name":"Qwen3.5 Flash","author":"alibaba","provider":"alibaba","description":"Vision-language model with hybrid linear-attention plus sparse MoE, 1M context, and fast multimodal text/image/video inference.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["vision","web_search","code_interpreter","function_calling","reasoning"],"aliases":["qwen3.5-flash"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":995904,"context_length":995904,"max_output_tokens":32768,"model_released_at":"2026-02-24","is_new":false,"is_featured":false,"discount":{"label":"Save up to 10%","percent":10},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":65536},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":81920},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies. Not available when a built-in tool is on, or on /v1/responses.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. Applies when no built-in tool is enabled, and not on /v1/responses.","required":false,"metadata":{},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{},"default":2,"min":0.1,"max":10},{"name":"treat_images_as_video","label":"Treat Images as Video","type":"boolean","description":"Treat a sequence of images as video frames.","required":false,"metadata":{},"default":false},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.015 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_search_image","label":"Text-to-Image Search","type":"boolean","description":"Search the web for images from text descriptions. Adds $0.012 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_image_search","label":"Image-to-Image Search","type":"boolean","description":"Find similar images from an uploaded image. Adds $0.012 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"control":"structured-output","so_tier":"json_object"}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added. Applies to streamed responses that use a built-in tool.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-5-flash:generateContent"],"pricing":{"prompt":"0.00000009","completion":"0.000000368","image":"0","request":"0","input_cache_read":"0.00000009"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.090 (was $0.10)"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.368 (was $0.40)"},{"spec":"per call when invoked","label":"Web search","value":"$0.015"},{"spec":"per call when invoked","label":"Text-to-image search","value":"$0.012"},{"spec":"per call when invoked","label":"Image-to-image search","value":"$0.012"},{"spec":"per call when invoked","label":"Web extractor","value":"$0.00"},{"spec":"per call when invoked","label":"Code interpreter","value":"$0.00"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.09","label":"Input"},{"unit":"1m_tokens","usd":"0.368","label":"Output"},{"unit":"call","usd":"0.015","label":"Web search"},{"unit":"call","usd":"0.012","label":"Text-to-image search"},{"unit":"call","usd":"0.012","label":"Image-to-image search"},{"unit":"call","usd":"0","label":"Web extractor"},{"unit":"call","usd":"0","label":"Code interpreter"}],"limits":{"note":"**Built-in tools** (billed only when invoked)\n\n- Web search: $0.015/call\n- Web extractor: free\n- Code interpreter: free\n- Text-to-image search: $0.012/call\n- Image-to-image search: $0.012/call\n\n**Other**\n\n- Thinking tokens are billed as output tokens\n\nText-to-Image Search and Image-to-Image Search use the Image Search pricing row. Each invoked image search is billed at that listed per-call rate.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes tools (web search, code interpreter, etc.) inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape, exact field names, units, and which tools appear can vary slightly per provider:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nThe tool counts are already factored into `cost_usd`, they are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-5-flash","api_url":"https://docs.empiriolabs.ai/models/qwen3-5-flash","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-5-omni-flash","object":"model","created":1774828800,"owned_by":"alibaba","display_name":"Qwen3.5 Omni Flash","author":"alibaba","provider":"alibaba","description":"Cost-efficient omni-modal model handling text, image, audio, and video, with up to 3 hours of audio and 1 hour of video across 90+ languages.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video","audio"],"input_modalities":["text","image","video","audio"],"output_modalities":["text","audio"],"features":["vision","audio_in","audio_out","multilingual","function_calling","web_search"],"aliases":["qwen3.5-omni-flash"],"structured_output":"none","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":196608,"context_length":196608,"max_output_tokens":32768,"model_released_at":"2026-03-30","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":32768},{"name":"output_mode","label":"Output Mode","type":"enum","description":"Output format mode. text = text only, text_audio = text plus synthesized speech.","required":false,"metadata":{},"default":"text","options":["text","text_audio"]},{"name":"voice","label":"Voice","type":"string","description":"Voice for audio output, used when output_mode is text_audio.","required":false,"metadata":{"visible_when":{"op":"eq","field":"output_mode","value":"text_audio"},"clear_when_hidden":true},"default":"Tina"},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. When omitted, the model's own default applies.","required":false,"metadata":{}},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{},"default":2,"min":0.1,"max":10},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.015 to the request cost when enabled.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1/audio/speech","POST /v1beta/models/qwen3-5-omni-flash:generateContent","POST /v1/audio/speech:stream"],"pricing":{"prompt":"0.0000008","completion":"0.0000044","image":"0","request":"0","input_cache_read":"0.0000008"},"pricing_rows":[{"spec":"per 1M audio input tokens","label":"Input: audio","value":"$6.00"},{"spec":"per 1M prompt tokens","label":"Input","value":"$0.80"},{"spec":"per 1M generated tokens, text-only replies","label":"Output","value":"$4.40"},{"spec":"per 1M generated audio tokens","label":"Output: audio","value":"$23.80"},{"spec":"per request when enabled","label":"Web search","value":"$0.015"}],"unit_pricing":[{"unit":"1m_tokens","usd":"6","label":"Input: audio"},{"unit":"1m_tokens","usd":"0.8","label":"Input"},{"unit":"1m_tokens","usd":"23.8","label":"Output: audio"},{"unit":"request","usd":"0.015","label":"Web search"}],"limits":{"note":"**Audio billing**\n\n- Audio is billed at a higher token rate than text/image/video\n- When audio output is enabled, output text is NOT charged, only audio tokens\n\n**Voice and language**\n\n- 55 voice timbres available\n- Audio output supports 29 languages, 7 dialects","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes tools (web search, code interpreter, etc.) inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape, exact field names, units, and which tools appear can vary slightly per provider:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nThe tool counts are already factored into `cost_usd`, they are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-5-omni-flash","api_url":"https://docs.empiriolabs.ai/models/qwen3-5-omni-flash","logo":"https://media.empiriolabs.ai/model-logos/qwen3-5-omni-flash.png","status":"available"},{"id":"qwen3-5-omni-plus","object":"model","created":1774828800,"owned_by":"alibaba","display_name":"Qwen3.5 Omni Plus","author":"alibaba","provider":"alibaba","description":"Flagship omni-modal model for text, image, audio, and video. 3h audio, 1h video, 90+ input and 30+ output languages, 55 voice timbres.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video","audio"],"input_modalities":["text","image","video","audio"],"output_modalities":["text","audio"],"features":["vision","audio_in","audio_out","multilingual","function_calling","web_search"],"aliases":["qwen3.5-omni-plus"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":196608,"context_length":196608,"max_output_tokens":32768,"model_released_at":"2026-03-30","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":32768},{"name":"output_mode","label":"Output Mode","type":"enum","description":"Output format mode. text = text only, text_audio = text plus synthesized speech.","required":false,"metadata":{},"default":"text","options":["text","text_audio"]},{"name":"voice","label":"Voice","type":"string","description":"Voice for audio output, used when output_mode is text_audio.","required":false,"metadata":{"visible_when":{"op":"eq","field":"output_mode","value":"text_audio"},"clear_when_hidden":true},"default":"Tina"},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. When omitted, the model's own default applies.","required":false,"metadata":{}},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{},"default":2,"min":0.1,"max":10},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.015 to the request cost when enabled.","required":false,"metadata":{},"default":false},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1/audio/speech","POST /v1beta/models/qwen3-5-omni-plus:generateContent","POST /v1/audio/speech:stream"],"pricing":{"prompt":"0.0000028","completion":"0.0000166","image":"0","request":"0","input_cache_read":"0.0000028"},"pricing_rows":[{"spec":"per 1M audio input tokens","label":"Input: audio","value":"$22.00"},{"spec":"per 1M prompt tokens","label":"Input","value":"$2.80"},{"spec":"per 1M generated tokens, text-only replies","label":"Output","value":"$16.60"},{"spec":"per 1M generated audio tokens","label":"Output: audio","value":"$88.00"},{"spec":"per request when enabled","label":"Web search","value":"$0.015"}],"unit_pricing":[{"unit":"1m_tokens","usd":"22","label":"Input: audio"},{"unit":"1m_tokens","usd":"2.8","label":"Input"},{"unit":"1m_tokens","usd":"88","label":"Output: audio"},{"unit":"request","usd":"0.015","label":"Web search"}],"limits":{"note":"**Audio billing**\n\n- Audio is billed at a higher token rate than text/image/video\n- When audio output is enabled, output text is NOT charged, only audio tokens\n\n**Voice and language**\n\n- 55 voice timbres available\n- Audio output supports 29 languages, 7 dialects","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes tools (web search, code interpreter, etc.) inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape, exact field names, units, and which tools appear can vary slightly per provider:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nThe tool counts are already factored into `cost_usd`, they are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-5-omni-plus","api_url":"https://docs.empiriolabs.ai/models/qwen3-5-omni-plus","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-5-plus","object":"model","created":1771200000,"owned_by":"alibaba","display_name":"Qwen3.5 Plus","author":"alibaba","provider":"alibaba","description":"Multimodal model with hybrid architecture for efficient deep thinking and visual understanding across text, image, and video on a 1M context.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["vision","web_search","code_interpreter","function_calling","reasoning"],"aliases":["qwen3.5-plus"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":983616,"context_length":983616,"max_output_tokens":65536,"model_released_at":"2026-02-16","deprecation_date":"2027-01-18","deprecated":true,"is_new":false,"is_featured":true,"discount":{"label":"Save up to 10%","percent":10},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":65536},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":81920},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies. Not available when a built-in tool is on, or on /v1/responses.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. Applies when no built-in tool is enabled, and not on /v1/responses.","required":false,"metadata":{},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{},"default":2,"min":0.1,"max":10},{"name":"treat_images_as_video","label":"Treat Images as Video","type":"boolean","description":"Treat a sequence of images as video frames.","required":false,"metadata":{},"default":false},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.015 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_search_image","label":"Text-to-Image Search","type":"boolean","description":"Search the web for images from text descriptions. Adds $0.012 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_image_search","label":"Image-to-Image Search","type":"boolean","description":"Find similar images from an uploaded image. Adds $0.012 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"control":"structured-output","so_tier":"json_object"}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added. Applies to streamed responses that use a built-in tool.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-5-plus:generateContent"],"pricing":[{"prompt":"0.00000036","completion":"0.00000221","image":"0","request":"0","input_cache_read":"0.00000036"},{"prompt":"0.00000045","completion":"0.00000276","image":"0","request":"0","input_cache_read":"0.00000045","min_context":256000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=256K $0.36 (was $0.40); 256K-1M $0.45 (was $0.50)"},{"spec":"per 1M generated tokens","label":"Output","value":"<=256K $2.21 (was $2.40); 256K-1M $2.76 (was $3.00)"},{"spec":"per call when invoked","label":"Web search","value":"$0.015"},{"spec":"per call when invoked","label":"Text-to-image search","value":"$0.012"},{"spec":"per call when invoked","label":"Image-to-image search","value":"$0.012"},{"spec":"per call when invoked","label":"Web extractor","value":"$0.00"},{"spec":"per call when invoked","label":"Code interpreter","value":"$0.00"}],"unit_pricing":[{"unit":"call","usd":"0.015","label":"Web search"},{"unit":"call","usd":"0.012","label":"Text-to-image search"},{"unit":"call","usd":"0.012","label":"Image-to-image search"},{"unit":"call","usd":"0","label":"Web extractor"},{"unit":"call","usd":"0","label":"Code interpreter"}],"limits":{"note":"Pricing is 1.25x for input/output above 256K tokens. Built-in tools (web search, web extractor, code interpreter, image search) billed only when invoked.\n\nText-to-Image Search and Image-to-Image Search use the Image Search pricing row. Each invoked image search is billed at that listed per-call rate.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes tools (web search, code interpreter, etc.) inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape, exact field names, units, and which tools appear can vary slightly per provider:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nThe tool counts are already factored into `cost_usd`, they are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-5-plus","api_url":"https://docs.empiriolabs.ai/models/qwen3-5-plus","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-6-plus","object":"model","created":1775088000,"owned_by":"alibaba","display_name":"Qwen3.6 Plus","author":"alibaba","provider":"alibaba","description":"Vision-language model with major upgrades over 3.5: agentic and front-end coding, multimodal recognition, OCR, and object localization.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["agentic_coding","function_calling","reasoning","video","vision","web_search"],"aliases":["qwen3.6-plus"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":983616,"context_length":983616,"max_output_tokens":65536,"model_released_at":"2026-04-02","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":65536},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable reasoning before answering. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled. When omitted, the model decides how long to reason.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"min":1,"max":131072},{"name":"preserve_thinking","label":"Preserve Thinking","type":"boolean","description":"Include the reasoning of earlier assistant turns in the model's input on /v1/chat/completions. Return each turn's reasoning unchanged in that assistant message's reasoning_content field. The earlier reasoning is billed as input tokens. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies. Not available when a built-in tool is on, or on /v1/responses.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"min":0.1,"max":2},{"name":"n","label":"Choices","type":"number","description":"Number of answers to return. Above 1 runs only on /v1/chat/completions, with enable_thinking false and without tools, web search or logprobs. The output tokens of every answer are billed.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling","hide_in_playground":true},"variants":[{"max":1,"when":{"op":"eq","field":"enable_thinking","value":true}}]},"default":1,"min":1,"max":4},{"name":"logprobs","label":"Logprobs","type":"boolean","description":"Return the log probabilities of the answer tokens, not the reasoning, on /v1/chat/completions. Not available when a built-in tool is on.","required":false,"metadata":{"ui":{"control":"toggle","section":"Debug"},"visible_when":[{"op":"eq","field":"tool_code_interpreter","value":false},{"op":"eq","field":"tool_image_search","value":false},{"op":"eq","field":"tool_web_extractor","value":false},{"op":"eq","field":"tool_web_search","value":false},{"op":"eq","field":"tool_web_search_image","value":false}],"clear_when_hidden":true},"default":false},{"name":"top_logprobs","label":"Top Logprobs","type":"number","description":"Return up to this many most likely alternatives for each answer token. Needs logprobs set to true.","required":false,"metadata":{"ui":{"control":"number","section":"Debug"},"visible_when":{"op":"eq","field":"logprobs","value":true},"clear_when_hidden":true},"default":0,"min":0,"max":5},{"name":"vl_high_resolution_images","label":"High Resolution Images","type":"boolean","description":"Use higher resolution processing for image inputs. Applies when no built-in tool is enabled, and not on /v1/responses.","required":false,"metadata":{},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixel count per image when high resolution processing is disabled.","required":false,"metadata":{"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":4096,"max":16777216},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs.","required":false,"metadata":{},"default":2,"min":0.1,"max":10},{"name":"treat_images_as_video","label":"Treat Images as Video","type":"boolean","description":"Treat a sequence of images as video frames.","required":false,"metadata":{},"default":false},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.026 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_web_search_image","label":"Text-to-Image Search","type":"boolean","description":"Search the web for images from text descriptions. Adds $0.0208 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"tool_image_search","label":"Image-to-Image Search","type":"boolean","description":"Find similar images from an uploaded image. Adds $0.0208 to the request cost for each invoked call. Not used when the request also has function tools, response_format or video input.","required":false,"metadata":{"hidden_when":{"op":"exists","field":"response_format"},"clear_when_hidden":true},"default":false},{"name":"parallel_tool_calls","label":"Parallel Tool Calls","type":"boolean","description":"Allow multiple tool calls in a single assistant turn. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.","required":false,"metadata":{"control":"structured-output","so_tier":"json_object"}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added. Applies to streamed responses that use a built-in tool.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-6-plus:generateContent"],"pricing":[{"prompt":"0.0000005","completion":"0.000003","image":"0","request":"0","input_cache_read":"0.0000005"},{"prompt":"0.000002","completion":"0.000006","image":"0","request":"0","input_cache_read":"0.000002","min_context":256000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=256K $0.50; 256K-1M $2.00"},{"spec":"per 1M generated tokens","label":"Output","value":"<=256K $3.00; 256K-1M $6.00"},{"spec":"per call when invoked","label":"Web search","value":"$0.026"},{"spec":"per call when invoked","label":"Text-to-image search","value":"$0.0208"},{"spec":"per call when invoked","label":"Image-to-image search","value":"$0.0208"},{"spec":"per call when invoked","label":"Web extractor","value":"$0.00"},{"spec":"per call when invoked","label":"Code interpreter","value":"$0.00"}],"unit_pricing":[{"unit":"call","usd":"0.026","label":"Web search"},{"unit":"call","usd":"0.0208","label":"Text-to-image search"},{"unit":"call","usd":"0.0208","label":"Image-to-image search"},{"unit":"call","usd":"0","label":"Web extractor"},{"unit":"call","usd":"0","label":"Code interpreter"}],"limits":{"note":"Pricing is 4x for input and 2x for output above 256K tokens. Built-in tool calls are NOT supported when video is attached.\n\nText-to-Image Search and Image-to-Image Search use the Image Search pricing row. Each invoked image search is billed at that listed per-call rate.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes tools (web search, code interpreter, etc.) inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape, exact field names, units, and which tools appear can vary slightly per provider:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nThe tool counts are already factored into `cost_usd`, they are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-6-plus","api_url":"https://docs.empiriolabs.ai/models/qwen3-6-plus","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-rerank","object":"model","created":1749081600,"owned_by":"alibaba","display_name":"Qwen3 Rerank","author":"alibaba","provider":"alibaba","description":"Semantic document reranker. Sorts up to 500 candidates per query by relevance, supports 100+ languages, and accepts a custom sorting instruction.","modality":null,"type":null,"category":"reranker","category_label":null,"modality_label":null,"modalities":["text","ranking"],"input_modalities":["text"],"output_modalities":["ranking"],"features":["semantic ranking","multilingual","rag","custom instructions"],"aliases":[],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":4000,"context_length":4000,"max_output_tokens":null,"model_released_at":"2025-06-05","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"query","label":"Query","type":"string","description":"Query text to rank documents against. Max 4,000 tokens.","required":true,"metadata":{}},{"name":"documents","label":"Documents","type":"string","description":"Candidate documents to sort (strings). Max 500 items, each up to 4,000 tokens.","required":true,"metadata":{}},{"name":"top_n","label":"Top N","type":"number","description":"Number of top-ranked documents to return. Defaults to all.","required":false,"metadata":{},"min":1,"max":500},{"name":"instruct","label":"Sorting Instruction","type":"string","description":"Custom English instruction. Use \"Retrieve semantically similar text.\" for similarity sorting.","required":false,"metadata":{},"default":"Given a web search query, retrieve relevant passages that answer the query."},{"name":"return_documents","label":"Return Documents","type":"boolean","description":"When true, return the original document text alongside each result.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/reranks"],"pricing":{"prompt":"0.0000001","completion":"0","image":"0","request":"0","input_cache_read":"0.0000001"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.10"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.1","label":"Input"}],"limits":{"note":"**Per-request limits**\n\n- Up to 500 candidate documents per request\n- Max 4,000 tokens per query/document\n- Max 120,000 tokens per request (formula: query_tokens × n_docs + sum_of_doc_tokens)\n- Tokens billed are query+documents combined; only successful reranks are charged\n\n**Languages**\n\n- 100+ major languages including Chinese, English, Spanish, French, Portuguese, Indonesian, Japanese, Korean, German, Russian\n\n**Sorting modes (`instruct` parameter)**\n\n- *Default, Q&A retrieval*: ``Given a web search query, retrieve relevant passages that answer the query.``\n- *Semantic similarity*: ``Retrieve semantically similar text.``\n- Or any custom English instruction (see [model task prompts](https://github.com/QwenLM/Qwen3-Embedding/blob/main/evaluation/task_prompts.json))"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-rerank","api_url":"https://docs.empiriolabs.ai/models/qwen3-rerank","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"seed-2-0-code","object":"model","created":1771027200,"owned_by":"bytedance","display_name":"Seed 2.0 Code","author":"bytedance","provider":"bytedance","description":"Coding-tuned model with strong front-end results and multilingual programming support for AI coding tools and agents.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video","document"],"input_modalities":["text","image","video","document"],"output_modalities":["text"],"features":["code_interpreter","reasoning","agentic_coding","function_calling","vision"],"aliases":["bytedance/seed-2-code","dola-seed-2.0-code","doubao-seed-2-code","seed-2-0-code-preview-260328","seed-2-code"],"structured_output":"none","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":229096,"context_length":229096,"max_output_tokens":128000,"model_released_at":"2026-02-14","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"max_tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":128000},{"name":"frequency_penalty","label":"frequency_penalty","type":"number","description":"Penalty for repeated tokens. >0 reduces repetition, <0 encourages it. Not applied when web search is on or a document is attached.","required":false,"metadata":{},"default":0,"min":-2,"max":2},{"name":"presence_penalty","label":"presence_penalty","type":"number","description":"Penalty for new vs. seen tokens. >0 encourages new topics, <0 encourages staying on topic. Not applied when web search is on or a document is attached.","required":false,"metadata":{},"default":0,"min":-2,"max":2},{"name":"stop","label":"stop","type":"string","description":"Comma-separated stop sequences","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable deep thinking / reasoning mode.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"reasoning_effort","type":"enum","description":"Reasoning effort tier. Use enable_thinking=false to disable reasoning entirely.","required":false,"metadata":{"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":"medium","options":["low","medium","high"]},{"name":"enable_web_search","label":"Web Search","type":"boolean","description":"Enable web search: retrieves live web results and provides them to the model as additional context.","required":false,"metadata":{},"default":false},{"name":"max_tool_calls","label":"Max Web Searches","type":"number","description":"Max number of web search rounds the model can run in one request.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"visible_when":{"op":"eq","field":"enable_web_search","value":true},"clear_when_hidden":true},"default":3,"min":1,"max":10},{"name":"image_detail","label":"image_detail","type":"enum","description":"Image visual quality tier for vision input.","required":false,"metadata":{},"default":"high","options":["low","high","xhigh"]},{"name":"video_fps","label":"video_fps","type":"number","description":"Frames per second extracted from video input.","required":false,"metadata":{},"min":0.2,"max":5}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/seed-2-0-code:generateContent"],"pricing":[{"prompt":"0.0000004","completion":"0.0000024","image":"0","request":"0","input_cache_read":"0.0000004"},{"prompt":"0.0000008","completion":"0.0000048","image":"0","request":"0","input_cache_read":"0.0000008","min_context":128000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=128K $0.40; 128K-256K $0.80"},{"spec":"per 1M generated tokens","label":"Output","value":"<=128K $2.40; 128K-256K $4.80"}],"unit_pricing":[],"limits":{"note":"Pricing is 2x when input tokens >=128K. Temperature and top_p are server-fixed (temp=1, top_p=0.95) regardless of client value.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools (web search, code interpreter, etc.) inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape, exact field names, units, and which tools appear can vary slightly per provider:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nThe tool counts are already factored into `cost_usd`, they are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=seed-2-0-code","api_url":"https://docs.empiriolabs.ai/models/seed-2-0-code","logo":"https://media.empiriolabs.ai/model-logos/seed-2-0-code.png","status":"available"},{"id":"seed-2-0-lite","object":"model","created":1771027200,"owned_by":"bytedance","display_name":"Seed 2.0 Lite","author":"bytedance","provider":"bytedance","description":"Balanced general-purpose model for high-frequency enterprise workloads: information processing, content, search, and data analysis.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video","document"],"input_modalities":["text","image","video","document"],"output_modalities":["text"],"features":["vision","reasoning","function_calling"],"aliases":["bytedance/seed-2-lite","doubao-seed-2-lite","seed-2-0-lite-260215","seed-2-lite"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":"batch","batch_discount_pct":0,"context_window":229096,"context_length":229096,"max_output_tokens":128000,"model_released_at":"2026-02-14","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"max_tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":128000},{"name":"frequency_penalty","label":"frequency_penalty","type":"number","description":"Penalty for repeated tokens. >0 reduces repetition, <0 encourages it. Not applied when web search is on or a document is attached.","required":false,"metadata":{},"default":0,"min":-2,"max":2},{"name":"presence_penalty","label":"presence_penalty","type":"number","description":"Penalty for new vs. seen tokens. >0 encourages new topics, <0 encourages staying on topic. Not applied when web search is on or a document is attached.","required":false,"metadata":{},"default":0,"min":-2,"max":2},{"name":"stop","label":"stop","type":"string","description":"Comma-separated stop sequences","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable deep thinking / reasoning mode.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"reasoning_effort","type":"enum","description":"Reasoning effort tier. Use enable_thinking=false to disable reasoning entirely.","required":false,"metadata":{"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":"medium","options":["low","medium","high"]},{"name":"enable_web_search","label":"Web Search","type":"boolean","description":"Enable web search: retrieves live web results and provides them to the model as additional context.","required":false,"metadata":{},"default":false},{"name":"max_tool_calls","label":"Max Web Searches","type":"number","description":"Max number of web search rounds the model can run in one request.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"visible_when":{"op":"eq","field":"enable_web_search","value":true},"clear_when_hidden":true},"default":3,"min":1,"max":10},{"name":"image_detail","label":"image_detail","type":"enum","description":"Image visual quality tier for vision input.","required":false,"metadata":{},"default":"high","options":["low","high","xhigh"]},{"name":"video_fps","label":"video_fps","type":"number","description":"Frames per second extracted from video input.","required":false,"metadata":{},"min":0.2,"max":5},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/seed-2-0-lite:generateContent"],"pricing":[{"prompt":"0.00000031","completion":"0.0000025","image":"0","request":"0","input_cache_read":"0.00000031"},{"prompt":"0.00000062","completion":"0.000005","image":"0","request":"0","input_cache_read":"0.00000062","min_context":128000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=128K $0.31; 128K-256K $0.62"},{"spec":"per 1M generated tokens","label":"Output","value":"<=128K $2.50; 128K-256K $5.00"}],"unit_pricing":[],"limits":{"note":"Pricing is 2x when input tokens >=128K. Temperature and top_p are server-fixed (temp=1, top_p=0.95) regardless of client value.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools (web search, code interpreter, etc.) inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape, exact field names, units, and which tools appear can vary slightly per provider:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nThe tool counts are already factored into `cost_usd`, they are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=seed-2-0-lite","api_url":"https://docs.empiriolabs.ai/models/seed-2-0-lite","logo":"https://media.empiriolabs.ai/model-logos/seed-2-0-lite.png","status":"available"},{"id":"seed-2-0-mini","object":"model","created":1771027200,"owned_by":"bytedance","display_name":"Seed 2.0 Mini","author":"bytedance","provider":"bytedance","description":"Latency-focused multimodal model with four reasoning effort modes and image/video understanding for high-concurrency use.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video","document"],"input_modalities":["text","image","video","document"],"output_modalities":["text"],"features":["vision","reasoning","function_calling"],"aliases":["bytedance/seed-2-mini","doubao-seed-2-mini","seed-2-0-mini-260215","seed-2-mini"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":"batch","batch_discount_pct":0,"context_window":229156,"context_length":229156,"max_output_tokens":128000,"model_released_at":"2026-02-14","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"temperature","type":"number","description":"Sampling temperature","required":false,"metadata":{},"default":0.7,"min":0,"max":2},{"name":"top_p","label":"top_p","type":"number","description":"Nucleus sampling","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"max_tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":128000},{"name":"frequency_penalty","label":"frequency_penalty","type":"number","description":"Penalty for repeated tokens. >0 reduces repetition, <0 encourages it. Not applied when web search is on or a document is attached.","required":false,"metadata":{},"default":0,"min":-2,"max":2},{"name":"presence_penalty","label":"presence_penalty","type":"number","description":"Penalty for new vs. seen tokens. >0 encourages new topics, <0 encourages staying on topic. Not applied when web search is on or a document is attached.","required":false,"metadata":{},"default":0,"min":-2,"max":2},{"name":"stop","label":"stop","type":"string","description":"Comma-separated stop sequences","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable deep thinking / reasoning mode.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"reasoning_effort","type":"enum","description":"Reasoning effort tier. Use enable_thinking=false to disable reasoning entirely.","required":false,"metadata":{"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":"medium","options":["low","medium","high"]},{"name":"enable_web_search","label":"Web Search","type":"boolean","description":"Enable web search: retrieves live web results and provides them to the model as additional context.","required":false,"metadata":{},"default":false},{"name":"max_tool_calls","label":"Max Web Searches","type":"number","description":"Max number of web search rounds the model can run in one request.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"visible_when":{"op":"eq","field":"enable_web_search","value":true},"clear_when_hidden":true},"default":3,"min":1,"max":10},{"name":"image_detail","label":"image_detail","type":"enum","description":"Image visual quality tier for vision input.","required":false,"metadata":{},"default":"high","options":["low","high","xhigh"]},{"name":"video_fps","label":"video_fps","type":"number","description":"Frames per second extracted from video input.","required":false,"metadata":{},"min":0.2,"max":5},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/seed-2-0-mini:generateContent"],"pricing":[{"prompt":"0.00000012","completion":"0.0000005","image":"0","request":"0","input_cache_read":"0.00000012"},{"prompt":"0.00000024","completion":"0.000001","image":"0","request":"0","input_cache_read":"0.00000024","min_context":128000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=128K $0.12; 128K-256K $0.24"},{"spec":"per 1M generated tokens","label":"Output","value":"<=128K $0.50; 128K-256K $1.00"}],"unit_pricing":[],"limits":{"note":"Pricing is 2x when input tokens >=128K. Temperature and top_p are server-fixed (temp=1, top_p=0.95) regardless of client value.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools (web search, code interpreter, etc.) inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape, exact field names, units, and which tools appear can vary slightly per provider:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nThe tool counts are already factored into `cost_usd`, they are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=seed-2-0-mini","api_url":"https://docs.empiriolabs.ai/models/seed-2-0-mini","logo":"https://media.empiriolabs.ai/model-logos/seed-2-0-mini.png","status":"available"},{"id":"seed-2-0-pro","object":"model","created":1771027200,"owned_by":"bytedance","display_name":"Seed 2.0 Pro","author":"bytedance","provider":"bytedance","description":"Flagship general model for complex reasoning, multimodal understanding, structured generation, and tool-augmented execution.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video","document"],"input_modalities":["text","image","video","document"],"output_modalities":["text"],"features":["vision","reasoning","function_calling"],"aliases":["bytedance/seed-2-pro","doubao-seed-2-pro","seed-2-0-pro-260328","seed-2-pro"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":"batch","batch_discount_pct":0,"context_window":229096,"context_length":229096,"max_output_tokens":128000,"model_released_at":"2026-02-14","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"max_tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":128000},{"name":"frequency_penalty","label":"frequency_penalty","type":"number","description":"Penalty for repeated tokens. >0 reduces repetition, <0 encourages it. Not applied when web search is on or a document is attached.","required":false,"metadata":{},"default":0,"min":-2,"max":2},{"name":"presence_penalty","label":"presence_penalty","type":"number","description":"Penalty for new vs. seen tokens. >0 encourages new topics, <0 encourages staying on topic. Not applied when web search is on or a document is attached.","required":false,"metadata":{},"default":0,"min":-2,"max":2},{"name":"stop","label":"stop","type":"string","description":"Comma-separated stop sequences","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable deep thinking / reasoning mode.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"reasoning_effort","type":"enum","description":"Reasoning effort tier. Use enable_thinking=false to disable reasoning entirely.","required":false,"metadata":{"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":"medium","options":["low","medium","high"]},{"name":"enable_web_search","label":"Web Search","type":"boolean","description":"Enable web search: retrieves live web results and provides them to the model as additional context.","required":false,"metadata":{},"default":false},{"name":"max_tool_calls","label":"Max Web Searches","type":"number","description":"Max number of web search rounds the model can run in one request.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"visible_when":{"op":"eq","field":"enable_web_search","value":true},"clear_when_hidden":true},"default":3,"min":1,"max":10},{"name":"image_detail","label":"image_detail","type":"enum","description":"Image visual quality tier for vision input.","required":false,"metadata":{},"default":"high","options":["low","high","xhigh"]},{"name":"video_fps","label":"video_fps","type":"number","description":"Frames per second extracted from video input.","required":false,"metadata":{},"min":0.2,"max":5},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/seed-2-0-pro:generateContent"],"pricing":[{"prompt":"0.00000063","completion":"0.00000379","image":"0","request":"0","input_cache_read":"0.00000063"},{"prompt":"0.00000126","completion":"0.00000758","image":"0","request":"0","input_cache_read":"0.00000126","min_context":128000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=128K $0.63; 128K-256K $1.26"},{"spec":"per 1M generated tokens","label":"Output","value":"<=128K $3.79; 128K-256K $7.58"}],"unit_pricing":[],"limits":{"note":"Pricing is 2x when input tokens >=128K. Temperature and top_p are server-fixed (temp=1, top_p=0.95) regardless of client value.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes built-in tools (web search, code interpreter, etc.) inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape, exact field names, units, and which tools appear can vary slightly per provider:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nThe tool counts are already factored into `cost_usd`, they are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=seed-2-0-pro","api_url":"https://docs.empiriolabs.ai/models/seed-2-0-pro","logo":"https://media.empiriolabs.ai/model-logos/seed-2-0-pro.png","status":"available"},{"id":"seedance-2-0-fast","object":"model","created":1770854400,"owned_by":"bytedance","display_name":"Seedance 2.0 Fast","author":"bytedance","provider":"bytedance","description":"Speed-optimized 2.0 video variant for cinematic clips with native audio sync, camera control, and stable motion at lower cost per render.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image","audio"],"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"features":["audio_sync","camera_control"],"aliases":["bytedance/seedance-2.0-fast","seedance-2.0-fast"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-02-12","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"auto: detect from inputs. t2v: text-to-video. i2v_first: animate first frame. i2v_both: morph between start (image) and end (image_end). reference: use image as visual reference. edit: edit attached video. extend: extend attached video.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v_first","i2v_both","reference","edit","extend"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution.","required":false,"metadata":{},"default":"720p","options":["480p","720p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio. adaptive lets the model choose from your inputs.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"adaptive","options":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]},{"name":"custom_duration","label":"Custom Duration","type":"boolean","description":"If false, the model decides clip length. If true, use the duration field.","required":false,"metadata":{},"default":true},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds. Only used when custom_duration=true.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"visible_when":{"op":"eq","field":"custom_duration","value":true},"clear_when_hidden":true},"default":5,"min":4,"max":15},{"name":"generate_audio","label":"Generate Audio","type":"boolean","description":"Generate native audio with the video.","required":false,"metadata":{},"default":true},{"name":"image","label":"Image","type":"string","description":"Reference image URL.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"image_end","label":"Image End","type":"string","description":"End-frame image URL for i2v_both.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"video","label":"Video","type":"string","description":"Reference video URL for edit / extend.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid.","required":false,"metadata":{},"default":""}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"T2V/I2V 480P","value":"$0.122"},{"spec":"per second","label":"T2V/I2V 720P","value":"$0.260"},{"spec":"per second","label":"Video Input 480P","value":"$0.284"},{"spec":"per second","label":"Video Input 720P","value":"$0.610"}],"unit_pricing":[{"unit":"second","usd":"0.122","label":"T2V/I2V 480P"},{"unit":"second","usd":"0.26","label":"T2V/I2V 720P"},{"unit":"second","usd":"0.284","label":"Video Input 480P"},{"unit":"second","usd":"0.61","label":"Video Input 720P"}],"limits":{"note":"Speed-optimized variant of Seedance 2.0 Pro: faster, lower-cost, ideal for rapid iteration. 480p and 720p only (no 1080p).\n\n**Tip**\n\n- Uploaded images and videos that show a real person's face are blocked. To feature a person, start from an image made with Seedream 5.5. To use your own face, verify it in [My face](https://platform.empiriolabs.ai/dashboard/verified-portrait).\n\n**Uploaded media preprocessing**\n\n- Video inputs are capped to 15 seconds for reference, edit, and extend workflows.\n- Uploaded video inputs are normalized to provider-compatible MP4 when needed."},"notes":"Speed-optimized variant of Seedance 2.0 Pro: faster, lower-cost, ideal for rapid iteration. 480p and 720p only (no 1080p).\n\n**Tip**\n\n- Uploaded images and videos that show a real person's face are blocked. To feature a person, start from an image made with Seedream 5.5. To use your own face, verify it in [My face](https://platform.empiriolabs.ai/dashboard/verified-portrait).\n\n**Uploaded media preprocessing**\n\n- Video inputs are capped to 15 seconds for reference, edit, and extend workflows.\n- Uploaded video inputs are normalized to provider-compatible MP4 when needed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=seedance-2-0-fast","api_url":"https://docs.empiriolabs.ai/models/seedance-2-0-fast","logo":"https://media.empiriolabs.ai/model-logos/seedance-2-0-fast.png","status":"available"},{"id":"seedance-2-0-pro","object":"model","created":1770854400,"owned_by":"bytedance","display_name":"Seedance 2.0 Pro","author":"bytedance","provider":"bytedance","description":"Multimodal video model for cinematic output from text, image, audio, or video inputs, with stable motion and consistent characters.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image","audio"],"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"features":["audio_sync","camera_control","character_consistency"],"aliases":["bytedance/seedance-2.0-pro","seedance-2.0-pro"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-02-12","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"auto: detect from inputs. t2v: text-to-video. i2v_first: animate first frame. i2v_both: morph between start (image) and end (image_end). reference: use image as visual reference. edit: edit attached video. extend: extend attached video.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v_first","i2v_both","reference","edit","extend"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution.","required":false,"metadata":{},"default":"480p","options":["480p","720p","1080p","4k"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio. adaptive lets the model choose from your inputs.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"adaptive","options":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]},{"name":"custom_duration","label":"Custom Duration","type":"boolean","description":"If false, the model decides clip length. If true, use the duration field.","required":false,"metadata":{},"default":true},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds. Only used when custom_duration=true.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"visible_when":{"op":"eq","field":"custom_duration","value":true},"clear_when_hidden":true},"default":5,"min":4,"max":15},{"name":"generate_audio","label":"Generate Audio","type":"boolean","description":"Generate native audio with the video.","required":false,"metadata":{},"default":true},{"name":"image","label":"Image","type":"string","description":"Reference image URL.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"image_end","label":"Image End","type":"string","description":"End-frame image URL for i2v_both.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"video","label":"Video","type":"string","description":"Reference video URL for edit / extend.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid.","required":false,"metadata":{},"default":""}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"T2V/I2V 480P","value":"$0.139"},{"spec":"per second","label":"T2V/I2V 720P","value":"$0.300"},{"spec":"per second","label":"T2V/I2V 1080P","value":"$0.749"},{"spec":"per second","label":"T2V/I2V 4K","value":"$1.555"},{"spec":"per second","label":"Video Input 480P","value":"$0.342"},{"spec":"per second","label":"Video Input 720P","value":"$0.736"},{"spec":"per second","label":"Video Input 1080P","value":"$1.841"},{"spec":"per second","label":"Video Input 4K","value":"$3.732"}],"unit_pricing":[{"unit":"second","usd":"0.139","label":"T2V/I2V 480P"},{"unit":"second","usd":"0.3","label":"T2V/I2V 720P"},{"unit":"second","usd":"0.749","label":"T2V/I2V 1080P"},{"unit":"second","usd":"1.555","label":"T2V/I2V 4K"},{"unit":"second","usd":"0.342","label":"Video Input 480P"},{"unit":"second","usd":"0.736","label":"Video Input 720P"},{"unit":"second","usd":"1.841","label":"Video Input 1080P"},{"unit":"second","usd":"3.732","label":"Video Input 4K"}],"limits":{"note":"Multimodal video from text, images, audio, and video inputs. Native audio-video sync, strong motion stability, consistent character handling. Outputs up to 4K (3840x2160).\n\n**Tip**\n\n- Uploaded images and videos that show a real person's face are blocked. To feature a person, start from an image made with Seedream 5.5. To use your own face, verify it in [My face](https://platform.empiriolabs.ai/dashboard/verified-portrait).\n\n**4K output**\n\n- 4K outputs are native 10-bit H.265 (HEVC) for maximum quality, delivered in full on download and through the API. Browsers cannot decode 4K HEVC inline, so the playground plays a 1080p preview while Download gives the full 4K. Open 4K files in any HEVC-capable player or editor.\n\n**Uploaded media preprocessing**\n\n- Video inputs are capped to 15 seconds for reference, edit, and extend workflows.\n- Uploaded video inputs are normalized to provider-compatible MP4 when needed."},"notes":"Multimodal video from text, images, audio, and video inputs. Native audio-video sync, strong motion stability, consistent character handling.\n\n**Tip**\n\n- Uploaded images and videos that show a real person's face are blocked. To feature a person, start from an image made with Seedream 5.5. To use your own face, verify it in [My face](https://platform.empiriolabs.ai/dashboard/verified-portrait).\n\n**Uploaded media preprocessing**\n\n- Video inputs are capped to 15 seconds for reference, edit, and extend workflows.\n- Uploaded video inputs are normalized to provider-compatible MP4 when needed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=seedance-2-0-pro","api_url":"https://docs.empiriolabs.ai/models/seedance-2-0-pro","logo":"https://media.empiriolabs.ai/model-logos/seedance-2-0-pro.png","status":"available"},{"id":"seedream-5-0-lite","object":"model","created":1770940800,"owned_by":"bytedance","display_name":"Seedream 5.0 Lite","author":"bytedance","provider":"bytedance","description":"Unified multimodal image model that reasons through prompts before rendering, producing high-resolution and consistent edits and brand visuals.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text","image"],"output_modalities":["image"],"features":["reasoning","editing"],"aliases":["bytedance/seedream-5-lite","seedream-5-lite"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-02-13","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Text prompt. With image attached, becomes an editing instruction. For batch mode, describe each image sequentially.","required":true,"metadata":{}},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Auto lets the model choose dimensions within the selected resolution tier. Explicit ratios use the preset size for that tier.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"auto","options":["auto","1:1","16:9","9:16","4:3","3:4","3:2","2:3","21:9"]},{"name":"quality","label":"Quality","type":"enum","description":"2K is about 4MP. 3K is about 9MP.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Settings"}},"default":"2K","options":["2K","3K"]},{"name":"use_custom_size","label":"Use Custom Size","type":"boolean","description":"Use custom_width and custom_height instead of preset aspect_ratio and quality. Applies when aspect_ratio is auto.","required":false,"metadata":{"visible_when":{"op":"eq","field":"aspect_ratio","value":"auto"},"clear_when_hidden":true},"default":false},{"name":"custom_width","label":"Custom Width","type":"number","description":"Pixels. Total area must be in [3.69MP, 10.4MP]; aspect must be in [1:16, 16:1]. Only when use_custom_size=true.","required":false,"metadata":{"ui":{"step":1,"control":"text_field"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":1024,"max":4704},{"name":"custom_height","label":"Custom Height","type":"number","description":"Pixels. Total area must be in [3.69MP, 10.4MP]; aspect must be in [1:16, 16:1]. Only when use_custom_size=true.","required":false,"metadata":{"ui":{"step":1,"control":"text_field"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":1024,"max":4704},{"name":"image","label":"Image","type":"string","description":"Up to 14 reference image URLs for editing. Triggers image-edit mode.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"batch_enabled","label":"Batch Enabled","type":"boolean","description":"Generate a cohesive set of related images from a single prompt. A max_images above 1 also generates a set.","required":false,"metadata":{},"default":false},{"name":"images","label":"Images","type":"string","description":"Alias for image. Use this for multiple uploaded image references.","required":false,"metadata":{"ui":{"hidden":true}}},{"name":"max_images","label":"Max Images","type":"number","description":"Batch mode only. Maximum images in the set; the model decides actual count. You are billed only for images returned.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"visible_when":{"op":"eq","field":"batch_enabled","value":true},"clear_when_hidden":true},"default":4,"min":1,"max":15},{"name":"watermark","label":"Watermark","type":"boolean","description":"When enabled, the generated image includes an AI-generated provenance watermark. EmpirioLabs does not add a separate watermark.","required":false,"metadata":{},"default":false},{"name":"output_format","label":"Output Format","type":"enum","description":"Output image file format.","required":false,"metadata":{},"default":"png","options":["jpeg","png"]},{"name":"response_format","label":"Response Format","type":"enum","description":"Return signed image URLs by default, or include base64 image data when b64_json is requested.","required":false,"metadata":{},"default":"url","options":["url","b64_json"]}],"supported_endpoints":["POST /v1/images/generations"],"pricing":{"prompt":"0","completion":"0","image":"0.035","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Standard","value":"$0.0350"}],"unit_pricing":[{"unit":"image","usd":"0.035","label":"Standard"}],"limits":{"note":"Multi-image reference combine and edit. Stronger reasoning before rendering than 4.0. Per generated image is billed; batch mode bills per actual image returned.\n\n**Content safety**\n\n- Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed."},"notes":"Multi-image reference combine and edit. Stronger reasoning before rendering than 4.0. Per generated image is billed; batch mode bills per actual image returned.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=seedream-5-0-lite","api_url":"https://docs.empiriolabs.ai/models/seedream-5-0-lite","logo":"https://media.empiriolabs.ai/model-logos/seedream-5-0-lite.png","status":"available"},{"id":"seedream-5-5","object":"model","created":1794182400,"owned_by":"bytedance","display_name":"Seedream 5.5","author":"bytedance","provider":"bytedance","description":"Seedream image model with native transparent output, precise multi-round editing, and decomposition into up to 99 editable layers with text recognition.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text","image"],"output_modalities":["image"],"features":["image_generation","image_editing","layer_decomposition","interactive_editing","multi_reference","text_rendering","multilingual_text","transparent_background"],"aliases":["bytedance/dola-seedream-5-5-261028","bytedance/seedream-5-5","byteplus/dola-seedream-5-5-261028","byteplus/seedream-5-5","dola-seedream-5-5-261028","seedream-5-5-261028","seedream-5.5"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-11-09","is_new":true,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Text prompt. With image attached, becomes an editing or fusion instruction.","required":true,"metadata":{"ui":{"control":"prompt","section":"Input"}}},{"name":"image","label":"Image","type":"string","description":"Reference image URL, data URI, or uploaded image object. Seedream 5.5 supports up to 10 reference images, and exactly one for layer decomposition.","required":false,"metadata":{"ui":{"accept":"image/*","control":"file","section":"Input","multiple":true}}},{"name":"images","label":"Images","type":"string","description":"Alias for image. Use this for multiple uploaded image references.","required":false,"metadata":{"ui":{"hidden":true}}},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Auto lets the model choose dimensions within the selected resolution tier. Explicit ratios use the preset size for that tier.","required":false,"metadata":{"ui":{"control":"segmented","section":"Settings"}},"default":"auto","options":["auto","1:1","16:9","9:16","4:3","3:4","3:2","2:3","21:9"]},{"name":"layer_decomposition","label":"Layer Decomposition","type":"boolean","description":"Split one input image into a base image plus up to 99 transparent PNG layers, each returned with its stacking order, its position in the base image, a name, and a description. Requires exactly one input image. The prompt is optional and can name the elements or coordinate regions to separate.","required":false,"metadata":{"ui":{"control":"toggle","section":"Settings"}},"default":false},{"name":"max_images","label":"Max Images","type":"number","description":"Layer decomposition only. Maximum images returned, the base image included, from 2 to 100; the model decides the actual count. You are billed only for images returned.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Settings"},"visible_when":{"op":"eq","field":"layer_decomposition","value":true},"clear_when_hidden":true},"default":30,"min":2,"max":100},{"name":"text_recognition","label":"Text Recognition","type":"boolean","description":"Layer decomposition only. Also return the text, line positions, and styling (similar font, color, bold, italic, underline, strikethrough, shadow, and translucency) of each regular text layer as text_recognition. Artistic text and handwriting are not recognized.","required":false,"metadata":{"ui":{"control":"toggle","section":"Settings"},"visible_when":{"op":"eq","field":"layer_decomposition","value":true},"clear_when_hidden":true},"default":false},{"name":"quality","label":"Quality","type":"enum","description":"Output resolution tier. 1.5K has the same price as 1K and provides higher resolution. Defaults to 2K. In layer decomposition, leaving this unset matches the input image instead.","required":false,"metadata":{"ui":{"control":"segmented","section":"Settings"}},"default":"2K","options":["1K","1.5K","2K"]},{"name":"size","label":"Size","type":"string","description":"Resolution tier or explicit pixel size such as 1K, 1.5K, 2K, or 2048x1152. Explicit pixels override aspect_ratio and quality. Layer decomposition accepts tiers or auto only.","required":false,"metadata":{"ui":{"control":"text_field","section":"Settings","placeholder":"2048x2048"}}},{"name":"use_custom_size","label":"Use Custom Size","type":"boolean","description":"Use custom_width and custom_height instead of preset aspect_ratio and quality. Applies when aspect_ratio is auto.","required":false,"metadata":{"ui":{"control":"toggle","section":"Settings"},"visible_when":{"op":"eq","field":"aspect_ratio","value":"auto"}},"default":false},{"name":"custom_width","label":"Custom Width","type":"number","description":"Custom output width in pixels. Total area must be in [0.92MP, 4.62MP] and aspect must be in [1:16, 16:1].","required":false,"metadata":{"ui":{"step":16,"control":"text_field","section":"Settings"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":15,"max":8600},{"name":"custom_height","label":"Custom Height","type":"number","description":"Custom output height in pixels. Total area must be in [0.92MP, 4.62MP] and aspect must be in [1:16, 16:1].","required":false,"metadata":{"ui":{"step":16,"control":"text_field","section":"Settings"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":15,"max":8600},{"name":"watermark","label":"Watermark","type":"boolean","description":"When enabled, the generated image includes an AI-generated provenance watermark. EmpirioLabs does not add a separate watermark.","required":false,"metadata":{"ui":{"control":"toggle","section":"Settings"}},"default":false},{"name":"output_format","label":"Output Format","type":"enum","description":"Output image file format. In layer decomposition this sets the base image format, and layers are always returned as PNG.","required":false,"metadata":{"ui":{"control":"segmented","section":"Output"}},"default":"png","options":["jpeg","png"]},{"name":"background","label":"Background","type":"enum","description":"Auto lets the model decide from the prompt and output format whether the image has transparency. Transparent returns an image with an alpha channel, from text or from up to 10 reference images, and requires png output. Opaque returns an image without one. Not available with layer decomposition.","required":false,"metadata":{"ui":{"control":"segmented","section":"Output"},"hidden_when":{"op":"eq","field":"layer_decomposition","value":true},"option_labels":{"auto":"Auto","opaque":"Opaque","transparent":"Transparent"},"clear_when_hidden":true},"default":"auto","options":["auto","transparent","opaque"]},{"name":"response_format","label":"Response Format","type":"enum","description":"Return signed image URLs by default, or include base64 image data when b64_json is requested.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Output"}},"default":"url","options":["url","b64_json"]}],"supported_endpoints":["POST /v1/images/generations"],"pricing":{"prompt":"0","completion":"0","image":"0.0332","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Output up to 2.61MP","value":"$0.0332"},{"spec":"per image","label":"Output above 2.61MP","value":"$0.0581"},{"spec":"per input image","label":"Input image","value":"$0.0133"}],"unit_pricing":[{"unit":"image","usd":"0.0332","label":"Output up to 2.61MP"},{"unit":"image","usd":"0.0581","label":"Output above 2.61MP"},{"unit":"image","usd":"0.0133","label":"Input image"}],"limits":{"note":"**Modes**\n\n- Text to image\n- Single or multi-image to image\n- Interactive editing with coordinate or sketch markers\n- Layer decomposition into a base image plus up to 99 layers, with optional text recognition\n\n**Interactive editing**\n\nMark the region to change directly on the input image with a sketch, circle, or arrow, then describe it in the prompt. For exact placement, use coordinate tags on a 0 to 1000 normalized grid:\n\n```text\nPlace the subject from image 1 <bbox>179 283 796 986</bbox> at the position in image 2 <bbox>118 331 933 871</bbox>.\n```\n\n**Layer decomposition**\n\nSet layer_decomposition to true with exactly one input image to split it into a base image plus up to 99 transparent PNG layers. max_images sets the most images returned, the base image included, from 2 to 100, and defaults to 30; a higher value allows a finer decomposition. Every returned image carries its stacking order as z_index, and each layer also carries its position in the base image as bounding_box.absolute and bounding_box.normalized, plus a name and a description. Scale each layer to its box when you reassemble the image. Leave the prompt empty to let the model choose the elements, or name the elements or coordinate regions to separate. Resolution accepts 1K, 1.5K, or 2K, and matches the input image when unset.\n\n**Text recognition**\n\nWith text_recognition on, each regular text layer also returns text_recognition: its full text, the position of each line, and the styling of each run of text (a similar font, color, bold, italic, underline, strikethrough, shadow, and translucency). Artistic text and handwriting are not recognized.\n\n**Transparency**\n\nbackground defaults to auto, which lets the model decide from the prompt and output format. Transparent returns an image with an alpha channel, from text alone or from up to 10 reference images that need no alpha channel, and requires PNG output. Opaque returns an image without one. Each returned image reports its actual transparency as background. Layer decomposition does not take background, and its layers are always transparent PNG.\n\n**Limits**\n\n- One output image per request, except layer decomposition, which returns the base image plus its layers\n- Up to 10 reference images, and exactly one for layer decomposition\n- 1K, 1.5K, and 2K resolution tiers, or an exact size from 0.92MP to 4.62MP\n- PNG or JPEG output, and layers are always PNG\n- No grouped output, streaming, or web search\n\n**Billing**\n\nEach returned image bills at its own size: up to 2.61MP, which covers 1K and 1.5K, or above 2.61MP, which covers 2K. Every input image bills, the one for layer decomposition included. Layer decomposition bills every returned image, the base image and each layer, at its own size.\n\n**Content safety**\n\nGenerated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed."},"notes":"**Modes**\n\n- Text to image\n- Single or multi-image to image\n- Interactive editing with coordinate or sketch markers\n- Layer decomposition into a base image plus up to 99 layers, with optional text recognition\n\n**Interactive editing**\n\nMark the region to change directly on the input image with a sketch, circle, or arrow, then describe it in the prompt. For exact placement, use coordinate tags on a 0 to 1000 normalized grid:\n\n```text\nPlace the subject from image 1 <bbox>179 283 796 986</bbox> at the position in image 2 <bbox>118 331 933 871</bbox>.\n```\n\n**Layer decomposition**\n\nSet layer_decomposition to true with exactly one input image to split it into a base image plus up to 99 transparent PNG layers. max_images sets the most images returned, the base image included, from 2 to 100, and defaults to 30; a higher value allows a finer decomposition. Every returned image carries its stacking order as z_index, and each layer also carries its position in the base image as bounding_box.absolute and bounding_box.normalized, plus a name and a description. Scale each layer to its box when you reassemble the image. Leave the prompt empty to let the model choose the elements, or name the elements or coordinate regions to separate. Resolution accepts 1K, 1.5K, or 2K, and matches the input image when unset.\n\n**Text recognition**\n\nWith text_recognition on, each regular text layer also returns text_recognition: its full text, the position of each line, and the styling of each run of text (a similar font, color, bold, italic, underline, strikethrough, shadow, and translucency). Artistic text and handwriting are not recognized.\n\n**Transparency**\n\nbackground defaults to auto, which lets the model decide from the prompt and output format. Transparent returns an image with an alpha channel, from text alone or from up to 10 reference images that need no alpha channel, and requires PNG output. Opaque returns an image without one. Each returned image reports its actual transparency as background. Layer decomposition does not take background, and its layers are always transparent PNG.\n\n**Limits**\n\n- One output image per request, except layer decomposition, which returns the base image plus its layers\n- Up to 10 reference images, and exactly one for layer decomposition\n- 1K, 1.5K, and 2K resolution tiers, or an exact size from 0.92MP to 4.62MP\n- PNG or JPEG output, and layers are always PNG\n- No grouped output, streaming, or web search\n\n**Billing**\n\nEach returned image bills at its own size: up to 2.61MP, which covers 1K and 1.5K, or above 2.61MP, which covers 2K. Every input image bills, the one for layer decomposition included. Layer decomposition bills every returned image, the base image and each layer, at its own size.\n\n**Content safety**\n\nGenerated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=seedream-5-5","api_url":"https://docs.empiriolabs.ai/models/seedream-5-5","logo":"https://media.empiriolabs.ai/model-logos/seedream-5-0-lite.png","status":"available"},{"id":"seedream-5-0-pro","object":"model","created":1783468800,"owned_by":"bytedance","display_name":"Seedream 5.0 Pro","author":"bytedance","provider":"bytedance","description":"Premium Seedream image model that splits one image into editable layers, edits by coordinate or sketch marker, and fuses up to 10 references.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text","image"],"output_modalities":["image"],"features":["image_generation","image_editing","layer_decomposition","interactive_editing","multi_reference","text_rendering","multilingual_text","transparent_background"],"aliases":["bytedance/dola-seedream-5-0-pro-260628","bytedance/seedream-5-0-pro","byteplus/dola-seedream-5-0-pro-260628","byteplus/seedream-5-0-pro","dola-seedream-5-0-pro-260628","seedream-5-0-pro-260628","seedream-5-pro","seedream-5.0-pro"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-07-08","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Text prompt. With image attached, becomes an editing or fusion instruction.","required":true,"metadata":{"ui":{"control":"prompt","section":"Input"}}},{"name":"image","label":"Image","type":"string","description":"Reference image URL, data URI, or uploaded image object. Seedream 5.0 Pro supports up to 10 reference images, and exactly one for layer decomposition or a transparent background.","required":false,"metadata":{"ui":{"accept":"image/*","control":"file","section":"Input","multiple":true}}},{"name":"images","label":"Images","type":"string","description":"Alias for image. Use this for multiple uploaded image references.","required":false,"metadata":{"ui":{"hidden":true}}},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Auto lets the model choose dimensions within the selected resolution tier. Explicit ratios use the preset size for that tier.","required":false,"metadata":{"ui":{"control":"segmented","section":"Settings"}},"default":"auto","options":["auto","1:1","16:9","9:16","4:3","3:4","3:2","2:3","21:9"]},{"name":"layer_decomposition","label":"Layer Decomposition","type":"boolean","description":"Split one input image into a base image plus up to 16 transparent PNG layers, each returned with its stacking order, its position in the base image, a name, and a description. Requires exactly one input image. The prompt is optional and can name the elements or coordinate regions to separate.","required":false,"metadata":{"ui":{"control":"toggle","section":"Settings"}},"default":false},{"name":"prompt_optimization_mode","label":"Prompt Optimization","type":"enum","description":"Standard prioritizes prompt adherence and image quality. Fast reduces generation latency with slightly lower image quality.","required":false,"metadata":{"ui":{"control":"segmented","section":"Settings"},"option_labels":{"fast":"Fast","standard":"Standard"}},"default":"standard","options":["standard","fast"]},{"name":"quality","label":"Quality","type":"enum","description":"Seedream Pro resolution tier. 1.5K has the same price as 1K and provides higher resolution. Defaults to 2K. In layer decomposition, leaving this unset matches the input image instead.","required":false,"metadata":{"ui":{"control":"segmented","section":"Settings"}},"default":"2K","options":["1K","1.5K","2K"]},{"name":"size","label":"Size","type":"string","description":"Resolution tier or explicit pixel size such as 1K, 1.5K, 2K, or 2048x1152. Explicit pixels override aspect_ratio and quality. Layer decomposition accepts tiers or auto only.","required":false,"metadata":{"ui":{"control":"text_field","section":"Settings","placeholder":"2048x2048"}}},{"name":"use_custom_size","label":"Use Custom Size","type":"boolean","description":"Use custom_width and custom_height instead of preset aspect_ratio and quality. Applies when aspect_ratio is auto.","required":false,"metadata":{"ui":{"control":"toggle","section":"Settings"},"visible_when":{"op":"eq","field":"aspect_ratio","value":"auto"}},"default":false},{"name":"custom_width","label":"Custom Width","type":"number","description":"Custom output width in pixels. Total area must be in [0.92MP, 4.62MP] and aspect must be in [1:16, 16:1].","required":false,"metadata":{"ui":{"step":16,"control":"text_field","section":"Settings"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":15,"max":8600},{"name":"custom_height","label":"Custom Height","type":"number","description":"Custom output height in pixels. Total area must be in [0.92MP, 4.62MP] and aspect must be in [1:16, 16:1].","required":false,"metadata":{"ui":{"step":16,"control":"text_field","section":"Settings"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":15,"max":8600},{"name":"watermark","label":"Watermark","type":"boolean","description":"When enabled, the generated image includes an AI-generated provenance watermark. EmpirioLabs does not add a separate watermark.","required":false,"metadata":{"ui":{"control":"toggle","section":"Settings"}},"default":false},{"name":"output_format","label":"Output Format","type":"enum","description":"Output image file format. In layer decomposition this sets the base image format, and layers are always returned as PNG.","required":false,"metadata":{"ui":{"control":"segmented","section":"Output"}},"default":"png","options":["jpeg","png"]},{"name":"background","label":"Background","type":"enum","description":"Transparent keeps the alpha channel so the output has no background. Supported when editing exactly one input image that already has an alpha channel, and requires png output.","required":false,"metadata":{"ui":{"control":"segmented","section":"Output"},"option_labels":{"opaque":"Opaque","transparent":"Transparent"}},"default":"opaque","options":["opaque","transparent"]},{"name":"response_format","label":"Response Format","type":"enum","description":"Return signed image URLs by default, or include base64 image data when b64_json is requested.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Output"}},"default":"url","options":["url","b64_json"]}],"supported_endpoints":["POST /v1/images/generations"],"pricing":{"prompt":"0","completion":"0","image":"0.075","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Output up to 2.61MP","value":"$0.075"},{"spec":"per image","label":"Output above 2.61MP","value":"$0.150"},{"spec":"per image","label":"Layer decomposition up to 2.61MP","value":"$0.0375"},{"spec":"per image","label":"Layer decomposition above 2.61MP","value":"$0.075"},{"spec":"per input image after the first","label":"Extra input image","value":"$0.005"}],"unit_pricing":[{"unit":"image","usd":"0.075","label":"Output up to 2.61MP"},{"unit":"image","usd":"0.15","label":"Output above 2.61MP"},{"unit":"image","usd":"0.0375","label":"Layer decomposition up to 2.61MP"},{"unit":"image","usd":"0.075","label":"Layer decomposition above 2.61MP"}],"limits":{"note":"**Modes**\n\n- Text to image\n- Single or multi-image to image\n- Interactive editing with coordinate or sketch markers\n- Layer decomposition into a base image plus up to 16 layers\n\n**Interactive editing**\n\nMark the region to change directly on the input image with a sketch, circle, or arrow, then describe it in the prompt. For exact placement, use coordinate tags on a 0 to 1000 normalized grid:\n\n```text\nPlace the subject from image 1 <bbox>179 283 796 986</bbox> at the position in image 2 <bbox>118 331 933 871</bbox>.\n```\n\n**Layer decomposition**\n\nSet layer_decomposition to true with exactly one input image to split it into a base image plus up to 16 transparent PNG layers. Every returned image carries its stacking order as z_index, and each layer also carries its position in the base image as bounding_box.absolute and bounding_box.normalized, plus a name and a description. Leave the prompt empty to let the model choose the elements, or name the elements or coordinate regions to separate. Resolution accepts 1K, 1.5K, or 2K, and matches the input image when unset.\n\n**Prompt optimization**\n\n- Standard (default): prioritizes prompt adherence and image quality\n- Fast: reduces generation latency with slightly lower image quality\n\n**Limits**\n\n- One output image per request, except layer decomposition, which returns the base image plus its layers\n- Up to 10 reference images, and exactly one for layer decomposition or a transparent background\n- 1K, 1.5K, and 2K resolution tiers\n- PNG or JPEG output, and layers are always PNG\n- A transparent background needs one input image that already has an alpha channel, and PNG output\n- No grouped output, streaming, or web search\n\n**Billing**\n\nLayer decomposition bills every returned image, the base image and each layer, at half the standard per-image rate, tiered on the pixel count of that image.\n\n**Content safety**\n\nGenerated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed."},"notes":"**Modes**\n\n- Text to image\n- Single or multi-image to image\n- Interactive editing with coordinate or sketch markers\n- Layer decomposition into a base image plus up to 16 layers\n\n**Interactive editing**\n\nMark the region to change directly on the input image with a sketch, circle, or arrow, then describe it in the prompt. For exact placement, use coordinate tags on a 0 to 1000 normalized grid:\n\n```text\nPlace the subject from image 1 <bbox>179 283 796 986</bbox> at the position in image 2 <bbox>118 331 933 871</bbox>.\n```\n\n**Layer decomposition**\n\nSet layer_decomposition to true with exactly one input image to split it into a base image plus up to 16 transparent PNG layers. Every returned image carries its stacking order as z_index, and each layer also carries its position in the base image as bounding_box.absolute and bounding_box.normalized, plus a name and a description. Leave the prompt empty to let the model choose the elements, or name the elements or coordinate regions to separate. Resolution accepts 1K, 1.5K, or 2K, and matches the input image when unset.\n\n**Prompt optimization**\n\n- Standard (default): prioritizes prompt adherence and image quality\n- Fast: reduces generation latency with slightly lower image quality\n\n**Limits**\n\n- One output image per request, except layer decomposition, which returns the base image plus its layers\n- Up to 10 reference images, and exactly one for layer decomposition or a transparent background\n- 1K, 1.5K, and 2K resolution tiers\n- PNG or JPEG output, and layers are always PNG\n- A transparent background needs one input image that already has an alpha channel, and PNG output\n- No grouped output, streaming, or web search\n\n**Billing**\n\nLayer decomposition bills every returned image, the base image and each layer, at half the standard per-image rate, tiered on the pixel count of that image.\n\n**Content safety**\n\nGenerated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=seedream-5-0-pro","api_url":"https://docs.empiriolabs.ai/models/seedream-5-0-pro","logo":"https://media.empiriolabs.ai/model-logos/seedream-5-0-lite.png","status":"available"},{"id":"seedream-5-0-flash","object":"model","created":1790553600,"owned_by":"bytedance","display_name":"Seedream 5.0 Flash","author":"bytedance","provider":"bytedance","description":"Fast Seedream image model that splits one image into editable layers, edits by coordinate or sketch marker, and fuses up to 10 references.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text","image"],"output_modalities":["image"],"features":["image_generation","image_editing","layer_decomposition","interactive_editing","multi_reference","text_rendering","multilingual_text","transparent_background"],"aliases":["bytedance/dola-seedream-5-0-flash-260915","bytedance/seedream-5-0-flash","byteplus/dola-seedream-5-0-flash-260915","byteplus/seedream-5-0-flash","dola-seedream-5-0-flash-260915","seedream-5-0-flash-260915","seedream-5-flash","seedream-5.0-flash"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-09-28","is_new":true,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Text prompt. With image attached, becomes an editing or fusion instruction.","required":true,"metadata":{"ui":{"control":"prompt","section":"Input"}}},{"name":"image","label":"Image","type":"string","description":"Reference image URL, data URI, or uploaded image object. Seedream 5.0 Flash supports up to 10 reference images, and exactly one for layer decomposition or a transparent background.","required":false,"metadata":{"ui":{"accept":"image/*","control":"file","section":"Input","multiple":true}}},{"name":"images","label":"Images","type":"string","description":"Alias for image. Use this for multiple uploaded image references.","required":false,"metadata":{"ui":{"hidden":true}}},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Auto lets the model choose dimensions within the selected resolution tier. Explicit ratios use the preset size for that tier.","required":false,"metadata":{"ui":{"control":"segmented","section":"Settings"}},"default":"auto","options":["auto","1:1","16:9","9:16","4:3","3:4","3:2","2:3","21:9"]},{"name":"layer_decomposition","label":"Layer Decomposition","type":"boolean","description":"Split one input image into a base image plus up to 16 transparent PNG layers, each returned with its stacking order, its position in the base image, a name, and a description. Requires exactly one input image. The prompt is optional and can name the elements or coordinate regions to separate.","required":false,"metadata":{"ui":{"control":"toggle","section":"Settings"}},"default":false},{"name":"quality","label":"Quality","type":"enum","description":"Output resolution tier. All tiers are billed at the same flat per-image rate. Defaults to 2K. In layer decomposition, leaving this unset matches the input image instead.","required":false,"metadata":{"ui":{"control":"segmented","section":"Settings"}},"default":"2K","options":["1K","1.5K","2K"]},{"name":"size","label":"Size","type":"string","description":"Resolution tier or explicit pixel size such as 1K, 1.5K, 2K, or 2048x1152. Explicit pixels override aspect_ratio and quality. Layer decomposition accepts tiers or auto only.","required":false,"metadata":{"ui":{"control":"text_field","section":"Settings","placeholder":"2048x2048"}}},{"name":"use_custom_size","label":"Use Custom Size","type":"boolean","description":"Use custom_width and custom_height instead of preset aspect_ratio and quality. Applies when aspect_ratio is auto.","required":false,"metadata":{"ui":{"control":"toggle","section":"Settings"},"visible_when":{"op":"eq","field":"aspect_ratio","value":"auto"}},"default":false},{"name":"custom_width","label":"Custom Width","type":"number","description":"Custom output width in pixels. Total area must be in [0.92MP, 4.62MP] and aspect must be in [1:16, 16:1].","required":false,"metadata":{"ui":{"step":16,"control":"text_field","section":"Settings"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":15,"max":8600},{"name":"custom_height","label":"Custom Height","type":"number","description":"Custom output height in pixels. Total area must be in [0.92MP, 4.62MP] and aspect must be in [1:16, 16:1].","required":false,"metadata":{"ui":{"step":16,"control":"text_field","section":"Settings"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":15,"max":8600},{"name":"watermark","label":"Watermark","type":"boolean","description":"When enabled, the generated image includes an AI-generated provenance watermark. EmpirioLabs does not add a separate watermark.","required":false,"metadata":{"ui":{"control":"toggle","section":"Settings"}},"default":false},{"name":"output_format","label":"Output Format","type":"enum","description":"Output image file format. In layer decomposition this sets the base image format, and layers are always returned as PNG.","required":false,"metadata":{"ui":{"control":"segmented","section":"Output"}},"default":"png","options":["jpeg","png"]},{"name":"background","label":"Background","type":"enum","description":"Transparent keeps the alpha channel so the output has no background. Supported when editing exactly one input image that already has an alpha channel, and requires png output.","required":false,"metadata":{"ui":{"control":"segmented","section":"Output"},"option_labels":{"opaque":"Opaque","transparent":"Transparent"}},"default":"opaque","options":["opaque","transparent"]},{"name":"response_format","label":"Response Format","type":"enum","description":"Return signed image URLs by default, or include base64 image data when b64_json is requested.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Output"}},"default":"url","options":["url","b64_json"]}],"supported_endpoints":["POST /v1/images/generations"],"pricing":{"prompt":"0","completion":"0","image":"0.03","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Image generation","value":"$0.030"},{"spec":"per image","label":"Layer decomposition","value":"$0.030"}],"unit_pricing":[{"unit":"image","usd":"0.03","label":"Image generation"},{"unit":"image","usd":"0.03","label":"Layer decomposition"}],"limits":{"note":"**Modes**\n\n- Text to image\n- Single or multi-image to image\n- Interactive editing with coordinate or sketch markers\n- Layer decomposition into a base image plus up to 16 layers\n\n**Interactive editing**\n\nMark the region to change directly on the input image with a sketch, circle, or arrow, then describe it in the prompt. For exact placement, use coordinate tags on a 0 to 1000 normalized grid:\n\n```text\nPlace the subject from image 1 <bbox>179 283 796 986</bbox> at the position in image 2 <bbox>118 331 933 871</bbox>.\n```\n\n**Layer decomposition**\n\nSet layer_decomposition to true with exactly one input image to split it into a base image plus up to 16 transparent PNG layers. Every returned image carries its stacking order as z_index, and each layer also carries its position in the base image as bounding_box.absolute and bounding_box.normalized, plus a name and a description. Leave the prompt empty to let the model choose the elements, or name the elements or coordinate regions to separate. Resolution accepts 1K, 1.5K, or 2K, and matches the input image when unset.\n\n**Limits**\n\n- One output image per request, except layer decomposition, which returns the base image plus its layers\n- Up to 10 reference images, and exactly one for layer decomposition or a transparent background\n- 1K, 1.5K, and 2K resolution tiers\n- PNG or JPEG output, and layers are always PNG\n- A transparent background needs one input image that already has an alpha channel, and PNG output\n- No grouped output, streaming, or web search\n\n**Billing**\n\nEvery resolution tier bills at the same per-image rate, and reference images are free. Layer decomposition bills every returned image, the base image and each layer, at that same rate.\n\n**Content safety**\n\nGenerated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed."},"notes":"**Modes**\n\n- Text to image\n- Single or multi-image to image\n- Interactive editing with coordinate or sketch markers\n- Layer decomposition into a base image plus up to 16 layers\n\n**Interactive editing**\n\nMark the region to change directly on the input image with a sketch, circle, or arrow, then describe it in the prompt. For exact placement, use coordinate tags on a 0 to 1000 normalized grid:\n\n```text\nPlace the subject from image 1 <bbox>179 283 796 986</bbox> at the position in image 2 <bbox>118 331 933 871</bbox>.\n```\n\n**Layer decomposition**\n\nSet layer_decomposition to true with exactly one input image to split it into a base image plus up to 16 transparent PNG layers. Every returned image carries its stacking order as z_index, and each layer also carries its position in the base image as bounding_box.absolute and bounding_box.normalized, plus a name and a description. Leave the prompt empty to let the model choose the elements, or name the elements or coordinate regions to separate. Resolution accepts 1K, 1.5K, or 2K, and matches the input image when unset.\n\n**Limits**\n\n- One output image per request, except layer decomposition, which returns the base image plus its layers\n- Up to 10 reference images, and exactly one for layer decomposition or a transparent background\n- 1K, 1.5K, and 2K resolution tiers\n- PNG or JPEG output, and layers are always PNG\n- A transparent background needs one input image that already has an alpha channel, and PNG output\n- No grouped output, streaming, or web search\n\n**Billing**\n\nEvery resolution tier bills at the same per-image rate, and reference images are free. Layer decomposition bills every returned image, the base image and each layer, at that same rate.\n\n**Content safety**\n\nGenerated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=seedream-5-0-flash","api_url":"https://docs.empiriolabs.ai/models/seedream-5-0-flash","logo":"https://media.empiriolabs.ai/model-logos/seedream-5-0-lite.png","status":"available"},{"id":"soulx-podcast","object":"model","created":1761696000,"owned_by":"soul-ai-lab","display_name":"SoulX Podcast","author":"soul-ai-lab","provider":"soul-ai-lab","description":"Open-source voice model for long-form, multi-speaker podcast dialogue with paralinguistic control (laughter, sighs) and zero-shot voice cloning.","modality":"audio","type":"tts","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text","audio"],"output_modalities":["audio"],"features":["voice_cloning","multi_speaker","dialect","podcast"],"aliases":["soul-ai-lab/soulx-podcast"],"structured_output":null,"native_inference":true,"weight_precision":"BF16","hugging_face_id":"Soul-AILab/SoulX-Podcast-1.7B","batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-10-29","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Podcast script. Use [S1] / [S2] / [S3] / [S4] tags or 'Speaker N:' lines for multi-speaker. Paralinguistic tags supported: <|laughter|>, <|sigh|>, <|breath|>, <|cough|>.","required":true,"metadata":{}},{"name":"voice_model","label":"Voice model","type":"enum","description":"base: English + Mandarin. dialect: adds Sichuan, Henan, and Cantonese.","required":false,"metadata":{},"default":"base","options":["base","dialect"]},{"name":"voice_s1","label":"Voice S1","type":"enum","description":"Voice for [S1]. lj = Emma. custom_s1 requires voice_s1_audio_url.","required":false,"metadata":{},"default":"arthur","options":["arthur","james","lj","xiaomei","zhigang","custom_s1"]},{"name":"voice_s2","label":"Voice S2","type":"enum","description":"Voice for [S2]. lj = Emma.","required":false,"metadata":{},"default":"lj","options":["arthur","james","lj","xiaomei","zhigang","custom_s2"]},{"name":"voice_s3","label":"Voice S3","type":"enum","description":"Voice for [S3].","required":false,"metadata":{},"default":"james","options":["arthur","james","lj","xiaomei","zhigang","custom_s3"]},{"name":"voice_s4","label":"Voice S4","type":"enum","description":"Voice for [S4].","required":false,"metadata":{},"default":"xiaomei","options":["arthur","james","lj","xiaomei","zhigang","custom_s4"]},{"name":"voice_s1_audio_url","label":"Voice S1 Audio Url","type":"string","description":"Reference audio URL for [S1] custom voice cloning: a recording of up to 30 seconds in which the speaker reads this consent statement aloud in English, in their own voice: \"I consent to Empirio Labs cloning my voice for the purpose of generating synthetic speech. I understand that my voice sample will be used to create personalized audio content.\" A recording without the statement is refused. Clone only the voice of a speaker who has given this consent.","required":false,"metadata":{"control":"audio-clip","max_seconds":30,"visible_when":{"op":"eq","field":"voice_s1","value":"custom_s1"},"required_when":{"op":"eq","field":"voice_s1","value":"custom_s1"},"clear_when_hidden":true}},{"name":"voice_s2_audio_url","label":"Voice S2 Audio Url","type":"string","description":"Reference audio URL for [S2] custom voice cloning: a recording of up to 30 seconds in which the speaker reads this consent statement aloud in English, in their own voice: \"I consent to Empirio Labs cloning my voice for the purpose of generating synthetic speech. I understand that my voice sample will be used to create personalized audio content.\" A recording without the statement is refused. Clone only the voice of a speaker who has given this consent.","required":false,"metadata":{"control":"audio-clip","max_seconds":30,"visible_when":{"op":"eq","field":"voice_s2","value":"custom_s2"},"required_when":{"op":"eq","field":"voice_s2","value":"custom_s2"},"clear_when_hidden":true}},{"name":"voice_s3_audio_url","label":"Voice S3 Audio Url","type":"string","description":"Reference audio URL for [S3] custom voice cloning: a recording of up to 30 seconds in which the speaker reads this consent statement aloud in English, in their own voice: \"I consent to Empirio Labs cloning my voice for the purpose of generating synthetic speech. I understand that my voice sample will be used to create personalized audio content.\" A recording without the statement is refused. Clone only the voice of a speaker who has given this consent.","required":false,"metadata":{"control":"audio-clip","max_seconds":30,"visible_when":{"op":"eq","field":"voice_s3","value":"custom_s3"},"required_when":{"op":"eq","field":"voice_s3","value":"custom_s3"},"clear_when_hidden":true}},{"name":"voice_s4_audio_url","label":"Voice S4 Audio Url","type":"string","description":"Reference audio URL for [S4] custom voice cloning: a recording of up to 30 seconds in which the speaker reads this consent statement aloud in English, in their own voice: \"I consent to Empirio Labs cloning my voice for the purpose of generating synthetic speech. I understand that my voice sample will be used to create personalized audio content.\" A recording without the statement is refused. Clone only the voice of a speaker who has given this consent.","required":false,"metadata":{"control":"audio-clip","max_seconds":30,"visible_when":{"op":"eq","field":"voice_s4","value":"custom_s4"},"required_when":{"op":"eq","field":"voice_s4","value":"custom_s4"},"clear_when_hidden":true}},{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature.","required":false,"metadata":{},"default":0.6,"min":0.1,"max":2},{"name":"top_k","label":"Top K","type":"number","description":"Top-k sampling cap.","required":false,"metadata":{},"default":100,"min":1,"max":500},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling.","required":false,"metadata":{},"default":0.9,"min":0.1,"max":1},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing.","required":false,"metadata":{},"default":1.25,"min":1,"max":2},{"name":"seed","label":"Seed","type":"string","description":"Seed for reproducible output.","required":false,"metadata":{},"default":"42"},{"name":"output_format","label":"Output Format","type":"enum","description":"Audio file format.","required":false,"metadata":{},"default":"mp3","options":["mp3","wav"]}],"supported_endpoints":["POST /v1/audio/speech"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per 1k characters, minimum 700 characters per request","label":"Base","value":"$0.015"},{"spec":"per 1k characters, minimum 700 characters per request","label":"Dialect","value":"$0.015"}],"unit_pricing":[{"unit":"1k_characters","usd":"0.015","label":"Base","minimum_usd":"0.0105"},{"unit":"1k_characters","usd":"0.015","label":"Dialect","minimum_usd":"0.0105"}],"limits":{"note":"Open-source voice model for long-form, multi-speaker podcast dialogue with paralinguistic control and zero-shot voice cloning.\n\nBilled per character, with a minimum of 700 characters per request."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=soulx-podcast","api_url":"https://docs.empiriolabs.ai/models/soulx-podcast","logo":"https://media.empiriolabs.ai/model-logos/soulx-podcast.png","status":"available"},{"id":"stable-audio-2-0","object":"model","created":1712102400,"owned_by":"stability","display_name":"Stable Audio 2.0","author":"stability","provider":"stability","description":"Generates audio up to 3 minutes from text prompts, supporting text-to-audio and audio-to-audio with adjustable duration, steps, and CFG scale.","modality":"audio","type":"generation","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["music_generation","text_to_audio","sound_effects"],"aliases":["stability-audio-2.0","stability/audio-2.0"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2024-04-03","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"What to generate. Be specific about genre, instruments, mood, and tempo.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"text-to-audio: generate from prompt only. audio-to-audio: condition on a reference clip.","required":false,"metadata":{},"default":"text-to-audio","options":["text-to-audio","audio-to-audio"]},{"name":"output_format","label":"Output Format","type":"enum","description":"Audio file format.","required":false,"metadata":{},"default":"mp3","options":["mp3","wav"]},{"name":"duration","label":"Duration","type":"number","description":"Seconds. Up to 3 minutes 10 seconds.","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":190,"min":1,"max":190},{"name":"steps","label":"Steps","type":"number","description":"Diffusion steps. More = higher fidelity, slower (and adds per-step credits).","required":false,"metadata":{},"default":50,"min":30,"max":100},{"name":"cfg_scale","label":"Cfg Scale","type":"number","description":"Classifier-free guidance. Higher = follows prompt more strictly.","required":false,"metadata":{},"default":7,"min":1,"max":25},{"name":"strength","label":"Strength","type":"number","description":"Audio-to-audio only. 0 = ignore reference, 1 = stay close to reference.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"audio-to-audio"},"clear_when_hidden":true},"default":1,"min":0,"max":1},{"name":"random_seed","label":"Random Seed","type":"boolean","description":"If true, use a random seed each call.","required":false,"metadata":{},"default":true},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed. Used unless random_seed is true.","required":false,"metadata":{"visible_when":{"op":"eq","field":"random_seed","value":false},"clear_when_hidden":true}},{"name":"audio_url","label":"Audio Url","type":"string","description":"Reference audio URL for audio-to-audio mode.","required":false,"metadata":{"ui":{"hide_in_playground":true}}}],"supported_endpoints":["POST /v1/audio/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per generation","label":"Base Cost","value":"$0.58"},{"spec":"per step","label":"Per Step Cost","value":"$0.00"}],"unit_pricing":[{"unit":"request","usd":"0.58","label":"Base Cost"},{"unit":"step","usd":"0","label":"Per Step Cost"}],"limits":{"note":"Generates up to 3 minutes 10 seconds of audio from text or via audio-to-audio transformation.\n\n**Audio-to-audio mode**\n\n- Requires BOTH a prompt and an uploaded audio file\n- Recommended CFG scale: 7-15\n- Recommended steps: 6-8\n- Typical strength: 0.3-0.7"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=stable-audio-2-0","api_url":"https://docs.empiriolabs.ai/models/stable-audio-2-0","logo":"https://media.empiriolabs.ai/model-logos/stable-audio-2-0.png","status":"available"},{"id":"stable-audio-2-5","object":"model","created":1757462400,"owned_by":"stability","display_name":"Stable Audio 2.5","author":"stability","provider":"stability","description":"Up-to-3-minute audio from text with text-to-audio, audio-to-audio, and audio inpainting for music production, sound design, and remixing.","modality":"audio","type":"generation","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["music_generation","text_to_audio","sound_effects"],"aliases":["stability-audio-2.5","stability/audio-2.5"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-09-10","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"What to generate.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"audio-inpaint regenerates a [mask_start, mask_end] window of an existing clip while keeping the rest.","required":false,"metadata":{},"default":"text-to-audio","options":["text-to-audio","audio-to-audio","audio-inpaint"]},{"name":"output_format","label":"Output Format","type":"enum","description":"Audio file format.","required":false,"metadata":{},"default":"mp3","options":["mp3","wav"]},{"name":"duration","label":"Duration","type":"number","description":"Seconds. Up to 3 minutes 10 seconds.","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":190,"min":1,"max":190},{"name":"steps","label":"Steps","type":"number","description":"Diffusion steps. The 2.5 turbo model is tuned for very low step counts.","required":false,"metadata":{},"default":8,"min":4,"max":8},{"name":"cfg_scale","label":"Cfg Scale","type":"number","description":"Classifier-free guidance. The turbo model uses small CFG by default.","required":false,"metadata":{},"default":1,"min":1,"max":25},{"name":"strength","label":"Strength","type":"number","description":"Audio-to-audio only. 0.01 = ignore reference, 1 = stay close to reference.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"audio-to-audio"},"clear_when_hidden":true},"default":1,"min":0.01,"max":1},{"name":"mask_start","label":"Mask Start","type":"number","description":"Inpaint window start in seconds, for audio-inpaint.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"audio-inpaint"},"clear_when_hidden":true},"default":30,"min":0,"max":190},{"name":"mask_end","label":"Mask End","type":"number","description":"Inpaint window end in seconds, for audio-inpaint.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"audio-inpaint"},"clear_when_hidden":true},"default":190,"min":0,"max":190},{"name":"random_seed","label":"Random Seed","type":"boolean","description":"If true, use a random seed each call.","required":false,"metadata":{},"default":true},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed. Used unless random_seed is true.","required":false,"metadata":{"visible_when":{"op":"eq","field":"random_seed","value":false},"clear_when_hidden":true}},{"name":"audio_url","label":"Audio Url","type":"string","description":"Reference audio URL for audio-to-audio / inpaint.","required":false,"metadata":{"ui":{"hide_in_playground":true}}}],"supported_endpoints":["POST /v1/audio/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per generation","label":"Generation","value":"$0.68"}],"unit_pricing":[{"unit":"request","usd":"0.68","label":"Generation"}],"limits":{"note":"Adds **audio-inpaint** mode (regenerate a time window) on top of Stable Audio 2.0.\n\n**Mode requirements**\n\n- Audio-to-audio and audio-inpaint both require BOTH a prompt and an uploaded audio file\n- Audio-to-audio uses the reference audio for style/conditioning, NOT for voice cloning"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=stable-audio-2-5","api_url":"https://docs.empiriolabs.ai/models/stable-audio-2-5","logo":"https://media.empiriolabs.ai/model-logos/stable-audio-2-5.png","status":"available"},{"id":"svi-2-0-pro","object":"model","created":1766707200,"owned_by":"vita-epfl","display_name":"SVI 2.0 Pro","author":"vita-epfl","provider":"vita-epfl","description":"Stable Video Infinity 2.0 Pro on WAN 2.2: extends still images into theoretically infinite-length video while keeping consistent character IDs.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image"],"output_modalities":["video"],"features":["infinite_length","character_consistency"],"aliases":["svi-2.0-pro","winfunc/svi-2.0-pro"],"structured_output":null,"native_inference":true,"weight_precision":"Mixed FP8/BF16/FP16","hugging_face_id":"epfl-vita/svi-model","batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-12-26","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"resolution","label":"Resolution","type":"enum","description":"480p is fast; 720p is slower but sharper.","required":false,"metadata":{},"default":"832x480","options":["832x480","480x832","720x1280","1280x720"]},{"name":"duration","label":"Duration (Estimate)","type":"number","description":"Estimated clip length in seconds. At 720p, duration is at most 40.5 seconds.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"step":4.5,"variants":[{"max":40.5,"when":{"op":"in","field":"resolution","values":["720x1280","1280x720"]}}]},"default":18,"min":18,"max":121.5},{"name":"cfg","label":"CFG Scale","type":"number","description":"Prompt adherence strength.","required":false,"metadata":{"step":0.1},"default":1,"min":1,"max":2},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"Text describing what to avoid.","required":false,"metadata":{"ui":{"control":"textarea"}},"default":"vibrant tone, overexposed, static, blurry details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, still picture, messy background, three legs, background crowd, walking backwards"},{"name":"t2v_quality","label":"Quality (T2V)","type":"enum","description":"Text-to-video only: quality gives higher fidelity, fast is quicker and costs less.","required":false,"metadata":{"visible_when":{"op":"falsy","field":"image"},"clear_when_hidden":true},"default":"quality","options":["fast","quality"]}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"480p Video","value":"$0.057"},{"spec":"per second","label":"720p Video","value":"$0.17"},{"spec":"additional fee","label":"T2V Fast","value":"$0.065"},{"spec":"additional fee","label":"T2V Quality","value":"$0.13"}],"unit_pricing":[{"unit":"second","usd":"0.057","label":"480p Video"},{"unit":"second","usd":"0.17","label":"720p Video"}],"limits":{"note":"Videos up to 121.5 seconds at 480p and 40.5 seconds at 720p, with a consistent character identity. Image-to-Video typically yields superior results to text-to-video.\n\n**Constraints**\n\n- Generation can take 45+ minutes for long videos\n- For best motion: describe consecutive actions per segment in your prompt\n\n**Image formats**\n\n- jpg, jpeg, png, webp, heic, heif, bmp, tiff, tif\n\n**Multi-scene mode**\n\n- When describing several scenes in one prompt, lower CFG (1.0-1.3) gives the model more freedom to interpret distinct scene transitions\n- Raise CFG (1.5-2.0) when each scene must follow the prompt literally"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=svi-2-0-pro","api_url":"https://docs.empiriolabs.ai/models/svi-2-0-pro","logo":"https://media.empiriolabs.ai/model-logos/svi-2-0-pro.png","status":"available"},{"id":"tavily-research","object":"model","created":1735689600,"owned_by":"tavily","display_name":"Tavily Research","author":"tavily","provider":"tavily","description":"Multi-search research assistant that explores a topic, analyzes sources, and produces a detailed research report with citations.","modality":"text","type":"research","category":"research","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["web_search","citations","multi_search"],"aliases":[],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"query","label":"Query","type":"string","description":"The natural-language query to search/research/answer.","required":true,"metadata":{}},{"name":"tavily_model","label":"Tavily model","type":"enum","description":"auto = let Tavily pick. mini = cheaper. pro = deeper.","required":false,"metadata":{},"default":"auto","options":["mini","pro","auto"]},{"name":"citation_format","label":"Citation Format","type":"enum","description":"Citation style in the answer: numbered, mla, apa, or chicago.","required":false,"metadata":{},"default":"numbered","options":["numbered","mla","apa","chicago"]},{"name":"include_domains","label":"Include domains","type":"string","description":"Array of domains to allow-list. Tavily restricts results to these domains when set.","required":false,"metadata":{}},{"name":"exclude_domains","label":"Exclude domains","type":"string","description":"Array of domains to block-list. Tavily skips any results from these domains.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/research","POST /v1/search"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per task","label":"Mini","value":"$0.083 - $2.29"},{"spec":"per task","label":"Pro","value":"$0.31 - $5.20"}],"unit_pricing":[],"limits":{"note":"Always uses advanced search depth. Returns synthesized answer plus citations."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=tavily-research","api_url":"https://docs.empiriolabs.ai/models/tavily-research","logo":"https://media.empiriolabs.ai/model-logos/tavily-research.png","status":"available"},{"id":"tavily-search","object":"model","created":1735689600,"owned_by":"tavily","display_name":"Tavily Search","author":"tavily","provider":"tavily","description":"Web search with crawl, extract, and URL mapping for fast, structured retrieval across pages and domains for downstream pipelines.","modality":"text","type":"search","category":"research","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["web_search","crawl","extract","map"],"aliases":[],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"query","label":"Query","type":"string","description":"The natural-language search query.","required":true,"metadata":{}},{"name":"operation_mode","label":"Operation Mode","type":"enum","description":"Search queries the web. Crawl reads pages from a starting URL. Extract returns the content of the given URLs. Map lists the URLs of a site.","required":false,"metadata":{},"default":"Search","options":["Search","Crawl","Extract","Map"]},{"name":"search_depth","label":"Search Depth","type":"enum","description":"basic = fast and cheap, advanced = deeper crawl per result with full content.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Search"},"clear_when_hidden":true},"default":"basic","options":["basic","advanced","fast","ultra-fast"]},{"name":"search_chunks_per_source","label":"Search Chunks Per Source","type":"number","description":"Advanced search depth only. Number of relevant content chunks to extract per source.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Search"},"clear_when_hidden":true},"default":3,"min":1,"max":3},{"name":"search_topic","label":"Search Topic","type":"enum","description":"Search topic preset (general, news, finance, etc.). Alias of topic.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Search"},"clear_when_hidden":true},"default":"general","options":["general","news","finance"]},{"name":"include_answer","label":"Include Answer","type":"boolean","description":"basic | advanced | false. Returns a synthesized answer alongside the results.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Search"},"clear_when_hidden":true},"default":false},{"name":"include_raw_content","label":"Include Raw Content","type":"boolean","description":"Include the raw HTML content alongside cleaned text. Search mode only.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Search"},"clear_when_hidden":true},"default":false},{"name":"include_images","label":"Include Images","type":"boolean","description":"Include image URLs from the search results.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Search"},"clear_when_hidden":true},"default":false},{"name":"include_image_descriptions","label":"Include Image Descriptions","type":"boolean","description":"Include AI-generated descriptions of returned images. Search mode only. Requires include_images.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Search"},"clear_when_hidden":true},"default":false},{"name":"include_favicon","label":"Include Favicon","type":"boolean","description":"Include the favicon URL of each source. Search mode only.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Search"},"clear_when_hidden":true},"default":false},{"name":"auto_parameters","label":"Auto Parameters","type":"boolean","description":"Let Tavily auto-pick search_depth and other knobs based on the query. Search mode only.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Search"},"clear_when_hidden":true},"default":false},{"name":"max_results","label":"Max Results","type":"number","description":"Maximum number of results to return (1-20).","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Search"},"clear_when_hidden":true},"default":5,"min":1,"max":20},{"name":"time_range","label":"Time Range","type":"enum","description":"day | week | month | year. Restrict results to this recency window.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Search"},"clear_when_hidden":true},"options":["day","week","month","year"]},{"name":"start_date","label":"Start Date","type":"string","description":"Only include sources published after this date (YYYY-MM-DD).","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Search"},"clear_when_hidden":true}},{"name":"end_date","label":"End Date","type":"string","description":"Only include sources published before this date (YYYY-MM-DD).","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Search"},"clear_when_hidden":true}},{"name":"country","label":"Country","type":"string","description":"Two-letter ISO 3166-1 code (US, GB, etc.) for biasing results to a country.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Search"},"clear_when_hidden":true}},{"name":"include_domains","label":"Include Domains","type":"string","description":"Comma-separated allowlist of domains. Only results from these domains are returned.","required":false,"metadata":{"visible_when":{"op":"in","field":"operation_mode","values":["Search","Crawl"]},"clear_when_hidden":true}},{"name":"exclude_domains","label":"Exclude Domains","type":"string","description":"Comma-separated denylist of domains to filter out.","required":false,"metadata":{"visible_when":{"op":"in","field":"operation_mode","values":["Search","Crawl"]},"clear_when_hidden":true}},{"name":"topic","label":"Topic","type":"enum","description":"Search topic preset. general (default), news (recent news), or finance (markets / business). Also accepted as search_topic.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Search"},"clear_when_hidden":true},"default":"general","options":["general","news","finance"]},{"name":"days","label":"Days","type":"number","description":"Recency window for the news topic, in days back from today.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Search"},"clear_when_hidden":true},"min":1,"max":365},{"name":"crawl_limit","label":"Crawl Limit","type":"number","description":"Max number of pages to crawl from the starting URL.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Crawl"},"clear_when_hidden":true},"default":50,"min":1,"max":100},{"name":"crawl_max_depth","label":"Crawl Max Depth","type":"number","description":"Maximum link-depth from the starting URL.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Crawl"},"clear_when_hidden":true},"default":1,"min":1,"max":5},{"name":"crawl_max_breadth","label":"Crawl Max Breadth","type":"number","description":"Maximum number of links to follow per page.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Crawl"},"clear_when_hidden":true},"default":20,"min":1,"max":50},{"name":"crawl_extract_depth","label":"Crawl Extract Depth","type":"enum","description":"How deeply to extract content from each crawled page.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Crawl"},"clear_when_hidden":true},"default":"basic","options":["basic","advanced"]},{"name":"crawl_format","label":"Crawl Format","type":"enum","description":"Output format for crawled content: markdown or text.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Crawl"},"clear_when_hidden":true},"default":"markdown","options":["markdown","text"]},{"name":"crawl_instructions","label":"Crawl Instructions","type":"string","description":"Natural-language instructions for what to look for during crawl.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Crawl"},"clear_when_hidden":true}},{"name":"crawl_chunks_per_source","label":"Crawl Chunks Per Source","type":"number","description":"Number of content chunks to extract from each crawled page.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Crawl"},"clear_when_hidden":true},"min":1,"max":5},{"name":"crawl_select_paths","label":"Crawl Select Paths","type":"string","description":"Comma-separated URL paths to include in the crawl.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Crawl"},"clear_when_hidden":true}},{"name":"crawl_exclude_paths","label":"Crawl Exclude Paths","type":"string","description":"Comma-separated URL paths to exclude from the crawl.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Crawl"},"clear_when_hidden":true}},{"name":"crawl_select_domains","label":"Crawl Select Domains","type":"string","description":"Comma-separated domains the crawl is restricted to.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Crawl"},"clear_when_hidden":true}},{"name":"crawl_exclude_domains","label":"Crawl Exclude Domains","type":"string","description":"Comma-separated domains the crawl will skip.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Crawl"},"clear_when_hidden":true}},{"name":"crawl_allow_external","label":"Crawl Allow External","type":"boolean","description":"Allow the crawler to follow links to external domains.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Crawl"},"clear_when_hidden":true},"default":true},{"name":"crawl_include_images","label":"Crawl Include Images","type":"boolean","description":"Include image URLs in the crawl output.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Crawl"},"clear_when_hidden":true},"default":false},{"name":"crawl_include_favicon","label":"Crawl Include Favicon","type":"boolean","description":"Include each crawled page's favicon URL.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Crawl"},"clear_when_hidden":true},"default":false},{"name":"crawl_timeout","label":"Crawl Timeout","type":"number","description":"Crawl timeout in seconds.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Crawl"},"clear_when_hidden":true},"default":150,"min":10,"max":150},{"name":"extract_depth","label":"Extract Depth","type":"enum","description":"basic | advanced. Advanced extraction reads JavaScript-rendered content.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Extract"},"clear_when_hidden":true},"default":"basic","options":["basic","advanced"]},{"name":"extract_format","label":"Extract Format","type":"enum","description":"Output format for extracted content: markdown or text.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Extract"},"clear_when_hidden":true},"default":"markdown","options":["markdown","text"]},{"name":"extract_query","label":"Extract Query","type":"string","description":"Natural-language query to filter / focus the extracted content.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Extract"},"clear_when_hidden":true}},{"name":"extract_chunks_per_source","label":"Extract Chunks Per Source","type":"number","description":"Number of content chunks to extract from each URL.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Extract"},"clear_when_hidden":true},"min":1,"max":5},{"name":"extract_include_images","label":"Extract Include Images","type":"boolean","description":"Include image URLs in the extract output.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Extract"},"clear_when_hidden":true},"default":false},{"name":"extract_include_favicon","label":"Extract Include Favicon","type":"boolean","description":"Include the source page's favicon URL. Extract mode only.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Extract"},"clear_when_hidden":true},"default":false},{"name":"extract_timeout","label":"Extract Timeout","type":"number","description":"Extract timeout in seconds.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Extract"},"clear_when_hidden":true},"default":10,"min":1,"max":60},{"name":"map_limit","label":"Map Limit","type":"number","description":"Max number of URLs to map from the starting site.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Map"},"clear_when_hidden":true},"default":50,"min":1,"max":100},{"name":"map_depth","label":"Map Depth","type":"number","description":"Maximum link-depth from the starting URL.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Map"},"clear_when_hidden":true},"default":1,"min":1,"max":5},{"name":"map_breadth","label":"Map Breadth","type":"number","description":"Maximum number of links to follow per page during mapping.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Map"},"clear_when_hidden":true},"default":20,"min":1,"max":50},{"name":"map_instructions","label":"Map Instructions","type":"string","description":"Natural-language instructions for what URLs to find during mapping.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Map"},"clear_when_hidden":true}},{"name":"map_select_paths","label":"Map Select Paths","type":"string","description":"Comma-separated URL paths the map is restricted to.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Map"},"clear_when_hidden":true}},{"name":"map_exclude_paths","label":"Map Exclude Paths","type":"string","description":"Comma-separated URL paths the map will skip.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Map"},"clear_when_hidden":true}},{"name":"map_select_domains","label":"Map Select Domains","type":"string","description":"Comma-separated domains the map is restricted to.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Map"},"clear_when_hidden":true}},{"name":"map_exclude_domains","label":"Map Exclude Domains","type":"string","description":"Comma-separated domains the map will skip.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Map"},"clear_when_hidden":true}},{"name":"map_allow_external","label":"Map Allow External","type":"boolean","description":"Allow the mapper to follow links to external domains.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Map"},"clear_when_hidden":true},"default":true},{"name":"map_timeout","label":"Map Timeout","type":"number","description":"Map timeout in seconds.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation_mode","value":"Map"},"clear_when_hidden":true},"default":150,"min":10,"max":150},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the results as JSON instead of formatted Markdown. Search mode only.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/search"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per search","label":"Search (Basic/Fast/Ultra-Fast)","value":"$0.0096"},{"spec":"per search","label":"Search (Advanced)","value":"$0.019"},{"spec":"per search","label":"Search (Advanced + Answer)","value":"$0.029"},{"spec":"per 5 URLs","label":"Extract (Basic)","value":"$0.0096"},{"spec":"per 5 URLs","label":"Extract (Advanced)","value":"$0.019"},{"spec":"per 10 pages","label":"Crawl/Map (basic)","value":"$0.0096"},{"spec":"per 10 pages","label":"Crawl/Map (with instructions)","value":"$0.019"}],"unit_pricing":[{"unit":"search","usd":"0.0096","label":"Search (Basic/Fast/Ultra-Fast)"},{"unit":"search","usd":"0.019","label":"Search (Advanced)"},{"unit":"search","usd":"0.029","label":"Search (Advanced + Answer)"},{"unit":"5_urls","usd":"0.0096","label":"Extract (Basic)"},{"unit":"5_urls","usd":"0.019","label":"Extract (Advanced)"},{"unit":"10_pages","usd":"0.0096","label":"Crawl/Map (basic)"},{"unit":"10_pages","usd":"0.019","label":"Crawl/Map (with instructions)"}],"limits":{"note":"**Operations**\n\n- Search, Crawl, Extract, Map\n\n**Search depths**\n\n- basic, advanced, fast, ultra-fast\n\n**Topics**\n\n- general, news, finance"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=tavily-search","api_url":"https://docs.empiriolabs.ai/models/tavily-search","logo":"https://media.empiriolabs.ai/model-logos/tavily-search.png","status":"available"},{"id":"text-embedding-v4","object":"model","created":1748995200,"owned_by":"alibaba","display_name":"Text Embedding v4","author":"alibaba","provider":"alibaba","description":"Multilingual text embedding with selectable output dimensions (64–2048). Up to 8,192 tokens per input.","modality":null,"type":null,"category":"embedding","category_label":null,"modality_label":null,"modalities":["text","embedding"],"input_modalities":["text"],"output_modalities":["embedding"],"features":["custom dimensions","sparse vectors","task instructions","batch"],"aliases":[],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":8192,"context_length":8192,"max_output_tokens":null,"model_released_at":"2025-06-04","is_new":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Text or array of up to 2,048 texts to embed, 8,192 tokens each.","required":true,"metadata":{}},{"name":"dimensions","label":"Dimensions","type":"number","description":"Vector dimension. Higher = more semantic info, more storage cost.","required":false,"metadata":{},"default":1024},{"name":"encoding_format","label":"Encoding Format","type":"enum","description":"Embedding output format: float (default array of floats) or base64.","required":false,"metadata":{},"default":"float","options":["float","base64"]},{"name":"user","label":"User","type":"string","description":"Optional identifier for the end user making the request.","required":false,"metadata":{}},{"name":"output_type","label":"Output Type","type":"enum","description":"dense returns the vector in embedding, sparse returns token weights in sparse_embedding, and dense_and_sparse returns both. Every output type bills the same tokens.","required":false,"metadata":{"ui":{"control":"segmented","section":"Output","hide_in_playground":true}},"default":"dense","options":["dense","sparse","dense_and_sparse"]},{"name":"instruct","label":"Query Instruction","type":"string","description":"An instruction describing the search task, such as: Given a web search query, retrieve relevant passages that answer the query. Set it when embedding search queries and leave it out for documents. Its tokens bill as input.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/embeddings"],"pricing":{"prompt":"0.00000007","completion":"0","image":"0","request":"0","input_cache_read":"0.00000007"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.07"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.07","label":"Input"}],"limits":{"note":"**Output dimensions** (selectable per request)\n\n- 64, 128, 256, 512, 768, 1024 (default), 1536, 2048\n- Higher dimensions retain more semantic detail at higher storage cost\n\n**Sparse vectors** (`output_type`)\n\n- `dense` (default) returns the vector in `embedding`\n- `sparse` returns token weights in `sparse_embedding`, each with `index`, `value` and `token`, and an empty `embedding`\n- `dense_and_sparse` returns both\n- Every output type bills the same tokens\n\n**Query instructions** (`instruct`)\n\n- Describes the search task for a query embedding, such as \"Given a web search query, retrieve relevant passages that answer the query\"\n- Set it when embedding search queries; leave it out for documents\n- Its tokens bill as input\n\n**Batch**\n\n- Up to 2,048 inputs per request, 8,192 tokens each\n\n**Languages**\n\n- 100+ natural languages including Chinese, English, Spanish, French, Japanese, Korean, German, Russian, plus most common programming languages"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=text-embedding-v4","api_url":"https://docs.empiriolabs.ai/models/text-embedding-v4","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"tongyi-embedding-vision-flash","object":"model","created":1758585600,"owned_by":"alibaba","display_name":"Tongyi Embedding Vision Flash","author":"alibaba","provider":"alibaba","description":"Speed-optimised multimodal embedding, same shape as Vision-Plus, 3× cheaper image/video tokens.","modality":null,"type":null,"category":"embedding","category_label":null,"modality_label":null,"modalities":["text","image","video","embedding"],"input_modalities":["text","image","video"],"output_modalities":["embedding"],"features":["multimodal","independent vectors","low cost"],"aliases":[],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1024,"context_length":1024,"max_output_tokens":null,"model_released_at":"2025-09-23","is_new":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"A string, an array of up to 2,048 strings (one embedding each), an OpenAI-style part array `[{type:'image',url:...},{type:'text',text:...}]`, or a native part list `{contents:[{image:'...'},{text:'...'}]}`. Up to 8 images at 3 MB each, video up to 10 MB, text up to 1024 tokens.","required":true,"metadata":{}},{"name":"user","label":"User","type":"string","description":"Optional caller identifier.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/embeddings"],"pricing":{"prompt":"0.00000009","completion":"0","image":"0","request":"0","input_cache_read":"0.00000009"},"pricing_rows":[{"spec":"per 1M tokens","label":"Text input","value":"$0.09"},{"spec":"per 1M tokens","label":"Image / video input","value":"$0.03"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.09","label":"Text input"},{"unit":"1m_tokens","usd":"0.03","label":"Image / video input"}],"limits":{"note":"**Output**\n\n- Fixed 768-dim vector per input\n- An array of strings returns one embedding per string, up to 2,048 per request\n\n**Per-input limits**\n\n- Text: up to 1,024 tokens\n- Image: up to 8 per request, 3 MB each (JPG, PNG, BMP)\n- Video: up to 10 MB per file (MP4, MPEG, MOV, MPG, WEBM, AVI, FLV, MKV)\n\n**Languages**\n\n- Chinese, English"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=tongyi-embedding-vision-flash","api_url":"https://docs.empiriolabs.ai/models/tongyi-embedding-vision-flash","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"tongyi-embedding-vision-plus","object":"model","created":1758585600,"owned_by":"alibaba","display_name":"Tongyi Embedding Vision Plus","author":"alibaba","provider":"alibaba","description":"Multimodal embedding producing independent vectors for text, image, and video inputs.","modality":null,"type":null,"category":"embedding","category_label":null,"modality_label":null,"modalities":["text","image","video","embedding"],"input_modalities":["text","image","video"],"output_modalities":["embedding"],"features":["multimodal","independent vectors"],"aliases":[],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1024,"context_length":1024,"max_output_tokens":null,"model_released_at":"2025-09-23","is_new":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"A string, an array of up to 2,048 strings (one embedding each), an OpenAI-style part array `[{type:'image',url:...},{type:'text',text:...}]`, or a native part list `{contents:[{image:'...'},{text:'...'}]}`. Up to 8 images at 3 MB each, video up to 10 MB, text up to 1024 tokens.","required":true,"metadata":{}},{"name":"user","label":"User","type":"string","description":"Optional caller identifier.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/embeddings"],"pricing":{"prompt":"0.00000009","completion":"0","image":"0","request":"0","input_cache_read":"0.00000009"},"pricing_rows":[{"spec":"per 1M tokens","label":"Text input","value":"$0.09"},{"spec":"per 1M tokens","label":"Image / video input","value":"$0.09"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.09","label":"Text input"},{"unit":"1m_tokens","usd":"0.09","label":"Image / video input"}],"limits":{"note":"**Output**\n\n- Fixed 1152-dim vector per input (no fusion across modalities)\n- An array of strings returns one embedding per string, up to 2,048 per request\n\n**Per-input limits**\n\n- Text: up to 1,024 tokens\n- Image: up to 8 per request, 3 MB each (JPG, PNG, BMP)\n- Video: up to 10 MB per file (MP4, MPEG, MOV, MPG, WEBM, AVI, FLV, MKV)\n\n**Languages**\n\n- Chinese, English"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=tongyi-embedding-vision-plus","api_url":"https://docs.empiriolabs.ai/models/tongyi-embedding-vision-plus","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"wan-2-6","object":"model","created":1768176000,"owned_by":"alibaba","display_name":"Wan 2.6","author":"alibaba","provider":"alibaba","description":"Multimodal video generation model for cinematic, multi-shot stories with native audio-visual sync (lip-sync, dialogue, music, SFX).","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image","audio"],"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"features":["audio_sync","character_consistency","multi_shot"],"aliases":["alibaba/wan-2.6","wan-2.6"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-01-12","is_new":false,"is_featured":false,"discount":{"label":"Save up to 10%","percent":10},"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"auto picks the mode from your attachments. t2v: text-to-video. i2v: animate the attached image. r2v: reference-to-video, generated from reference images.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v","r2v"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution. Larger = higher fidelity but slower / more expensive.","required":false,"metadata":{},"default":"1080p","options":["720p","1080p"]},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds: 5, 10 or 15. Reference-to-video is capped at 10.","required":false,"metadata":{"ui":{"step":5,"control":"slider"},"variants":[{"max":10,"when":{"op":"eq","field":"mode","value":"r2v"}}]},"default":5,"min":5,"max":15},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio for text-to-video and reference-to-video. Image-to-video follows the source image.","required":false,"metadata":{"ui":{"control":"segmented"},"hidden_when":{"op":"eq","field":"mode","value":"i2v"},"clear_when_hidden":true},"default":"16:9","options":["16:9","9:16","1:1","4:3","3:4"]},{"name":"shot_type","label":"Shot Type","type":"enum","description":"single: one continuous shot. multi: multi-shot narrative.","required":false,"metadata":{},"default":"multi","options":["single","multi"]},{"name":"image","label":"Image","type":"string","description":"Reference image URL. Required for i2v / r2v.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid.","required":false,"metadata":{},"default":""},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed.","required":false,"metadata":{}},{"name":"audio","label":"Audio","type":"boolean","description":"Generate native audio with the video, in image-to-video and reference-to-video; text-to-video always has audio. With flash_mode, turning it off lowers the price.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":true},{"name":"flash_mode","label":"Flash Mode","type":"boolean","description":"Faster generation at reduced cost. Applies to i2v and r2v only.","required":false,"metadata":{"visible_when":{"op":"in","field":"mode","values":["auto","i2v","r2v"]},"clear_when_hidden":true},"default":false},{"name":"prompt_extend","label":"Prompt Extend","type":"boolean","description":"Automatically expand and refine the prompt for better results.","required":false,"metadata":{},"default":true}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"Standard 720P","value":"$0.09 (was $0.10)"},{"spec":"per second","label":"Standard 1080P","value":"$0.138 (was $0.15)"},{"spec":"per second","label":"Flash 720P (audio)","value":"$0.045 (was $0.050)"},{"spec":"per second","label":"Flash 720P (no audio)","value":"$0.0225 (was $0.0250)"},{"spec":"per second","label":"Flash 1080P (audio)","value":"$0.069 (was $0.0750)"},{"spec":"per second","label":"Flash 1080P (no audio)","value":"$0.0345 (was $0.03750)"}],"unit_pricing":[{"unit":"second","usd":"0.09","label":"Standard 720P"},{"unit":"second","usd":"0.138","label":"Standard 1080P"},{"unit":"second","usd":"0.045","label":"Flash 720P (audio)"},{"unit":"second","usd":"0.0225","label":"Flash 720P (no audio)"},{"unit":"second","usd":"0.069","label":"Flash 1080P (audio)"},{"unit":"second","usd":"0.0345","label":"Flash 1080P (no audio)"}],"limits":{"note":"Generation can take 5+ minutes. Modes: t2v, i2v (image-to-video), r2v (reference-to-video). Flash Mode (i2v/r2v only), faster generation at reduced cost.\n\n**Image inputs**\n\n- Auto-resized: i2v 360-2000px, r2v 240-5000px\n- HEIC/HEIF auto-converted\n\n**Reference videos**\n\n- MP4 or MOV\n- 1-30s (the first 15s of each video is used)\n- Max 100 MB\n- r2v output capped at 10s\n\n**Optional audio (t2v / i2v only)**\n\n- 3-30s, max 15 MB, .mp3 or .wav\n- Silently ignored in r2v (audio is extracted from the reference video instead)\n\n**Billing**\n\n- R2V with reference videos is billed for input + output duration combined.\n\n**Uploaded media preprocessing**\n\n- Reference and edit videos are normalized to provider-compatible MP4 when needed.\n- Reference-video duration follows the mode limits shown above."},"notes":"Generation can take 5+ minutes. Modes: t2v, i2v (image-to-video), r2v (reference-to-video). Flash Mode (i2v/r2v only), faster generation at reduced cost.\n\n**Image inputs**\n\n- Auto-resized: i2v 360-2000px, r2v 240-5000px\n- HEIC/HEIF auto-converted\n\n**Reference videos**\n\n- MP4 or MOV\n- 1-30s (the first 15s of each video is used)\n- Max 100 MB\n- r2v output capped at 10s\n\n**Optional audio (t2v / i2v only)**\n\n- 3-30s, max 15 MB, .mp3 or .wav\n- Silently ignored in r2v (audio is extracted from the reference video instead)\n\n**Billing**\n\n- R2V with reference videos is billed for input + output duration combined.\n\n**Uploaded media preprocessing**\n\n- Reference and edit videos are normalized to provider-compatible MP4 when needed.\n- Reference-video duration follows the mode limits shown above.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=wan-2-6","api_url":"https://docs.empiriolabs.ai/models/wan-2-6","logo":"https://media.empiriolabs.ai/model-logos/wan.png","status":"available"},{"id":"wan-2-7","object":"model","created":1777161600,"owned_by":"alibaba","display_name":"Wan 2.7","author":"alibaba","provider":"alibaba","description":"Multimodal video model supporting T2V, I2V, video editing, and reference-to-video, with high-fidelity output from text, image, or video inputs.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image","audio"],"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"features":["audio_sync","character_consistency","multi_shot"],"aliases":["alibaba/wan-2.7","wan-2.7"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-04-26","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"t2v: text-to-video. i2v: animate the attached image. videoedit: edit the attached video. r2v: reference-to-video.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v","videoedit","r2v"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution. Larger = higher fidelity but slower / more expensive.","required":false,"metadata":{},"default":"1080p","options":["720p","1080p"]},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds. Video edit and reference-to-video are capped at 10 seconds, and video edit never exceeds the input clip. Image-to-video with an attached audio clip matches the audio length.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"variants":[{"max":10,"when":{"op":"in","field":"mode","values":["videoedit","r2v"]}}]},"default":5,"min":2,"max":15},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Optional. If omitted, the model picks based on input.","required":false,"metadata":{"ui":{"control":"segmented"},"hidden_when":{"op":"eq","field":"mode","value":"i2v"},"clear_when_hidden":true},"options":["16:9","9:16","1:1","4:3","3:4"]},{"name":"image","label":"Image","type":"string","description":"Reference image URL. Required for i2v / r2v / videoedit.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"video","label":"Video","type":"string","description":"Reference video URL. Required for videoedit / r2v.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid.","required":false,"metadata":{},"default":""},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed.","required":false,"metadata":{}},{"name":"audio_setting","label":"Audio Setting","type":"enum","description":"auto: generate native audio. origin: keep the audio of the source video (video edit only).","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"videoedit"},"clear_when_hidden":true},"default":"auto","options":["auto","origin"]},{"name":"prompt_extend","label":"Prompt Extend","type":"boolean","description":"Automatically expand and refine the prompt for better results.","required":false,"metadata":{},"default":true}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"All Modes 720P","value":"$0.10"},{"spec":"per second","label":"All Modes 1080P","value":"$0.150"}],"unit_pricing":[{"unit":"second","usd":"0.1","label":"All Modes 720P"},{"unit":"second","usd":"0.15","label":"All Modes 1080P"}],"limits":{"note":"Generation can take 30+ minutes. Modes auto-detected from attachments, or override with the `mode` parameter.\n\n**Modes**\n\n- T2V: no attachments\n- I2V (First Frame): 1 image\n- I2V (First + Last): exactly 2 images\n- I2V Continuation: 1 video (2-10s) + optional last-frame image\n- Video Edit: 1 video (2-10s, ≤100 MB, MP4/MOV) + up to 3 reference images\n- R2V: up to 5 references combined (the first 15s of each reference video is used); reference subjects in your prompt with `Video1`, `Image1`, etc.\n\n**Optional audio**\n\n- T2V/I2V: 2-30s\n- R2V: 1-10s (used as a voice timbre sample)\n- Max 15 MB, .mp3 or .wav\n\n**Billing**\n\n- Video Edit and R2V are billed for input + output duration combined.\n\n**Uploaded media preprocessing**\n\n- Reference and edit videos are normalized to provider-compatible MP4 when needed.\n- Reference-video duration follows the mode limits shown above."},"notes":"Generation can take 30+ minutes. Modes auto-detected from attachments, or override with the `mode` parameter.\n\n**Modes**\n\n- T2V: no attachments\n- I2V (First Frame): 1 image\n- I2V (First + Last): exactly 2 images\n- I2V Continuation: 1 video (2-10s) + optional last-frame image\n- Video Edit: 1 video (2-10s, ≤100 MB, MP4/MOV) + up to 3 reference images\n- R2V: up to 5 references combined (the first 15s of each reference video is used); reference subjects in your prompt with `Video1`, `Image1`, etc.\n\n**Optional audio**\n\n- T2V/I2V: 2-30s\n- R2V: 1-10s (used as a voice timbre sample)\n- Max 15 MB, .mp3 or .wav\n\n**Billing**\n\n- Video Edit and R2V are billed for input + output duration combined.\n\n**Uploaded media preprocessing**\n\n- Reference and edit videos are normalized to provider-compatible MP4 when needed.\n- Reference-video duration follows the mode limits shown above.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=wan-2-7","api_url":"https://docs.empiriolabs.ai/models/wan-2-7","logo":"https://media.empiriolabs.ai/model-logos/wan.png","status":"available"},{"id":"wan2-7-image","object":"model","created":1775001600,"owned_by":"alibaba","display_name":"Wan2.7 Image","author":"alibaba","provider":"alibaba","description":"Image generation and editing companion model: text-to-image, bounding-box edits, and cohesive image sets, with up to 4K output on Pro.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text","image"],"output_modalities":["image"],"features":["image_editing","4k"],"aliases":["alibaba/wan-2.7-image","wan-2.7-image"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-04-01","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Text prompt. For Image Set mode, describe each image in sequence (e.g. 'First image: ... Second image: ...').","required":true,"metadata":{}},{"name":"model_variant","label":"Variant","type":"enum","description":"Pro: 4K + Thinking Mode + higher quality. Standard: faster, cheaper.","required":false,"metadata":{},"default":"wan2.7-image-pro","options":["wan2.7-image-pro","wan2.7-image"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Optional. If omitted, text-to-image defaults to 16:9; image-edit matches the last input image's native ratio.","required":false,"metadata":{"ui":{"control":"segmented"}},"options":["16:9","1:1","9:16","3:2","2:3","4:3","3:4","5:4","4:5"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Quality tier. 1K ~1MP, 2K ~4MP, 4K ~16MP (Pro text-to-image only).","required":false,"metadata":{},"default":"2K","options":["1K","2K","4K"]},{"name":"use_custom_size","label":"Use Custom Size","type":"boolean","description":"Override aspect_ratio + resolution with explicit pixel dimensions.","required":false,"metadata":{},"default":false},{"name":"custom_width","label":"Custom Width","type":"number","description":"Pixels (768–2048; Pro text-to-image up to 4096). Only when use_custom_size=true. Aspect must be in [1:8, 8:1].","required":false,"metadata":{"ui":{"step":1,"control":"text_field"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":768,"max":4096},{"name":"custom_height","label":"Custom Height","type":"number","description":"Pixels (768–2048; Pro text-to-image up to 4096). Only when use_custom_size=true.","required":false,"metadata":{"ui":{"step":1,"control":"text_field"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":768,"max":4096},{"name":"enable_sequential","label":"Enable Sequential","type":"boolean","description":"Image Set Mode. Generate up to 12 cohesive related images. Disables thinking_mode and color_palette.","required":false,"metadata":{},"default":false},{"name":"num_images","label":"Num Images","type":"number","description":"Standard mode only. Number of images to generate. Each is billed separately.","required":false,"metadata":{"visible_when":{"op":"eq","field":"enable_sequential","value":false},"clear_when_hidden":true},"default":1,"min":1,"max":4},{"name":"num_images_set","label":"Num Images Set","type":"number","description":"Image Set Mode only. Maximum images in the set. The model decides the actual count; you're billed only for images generated.","required":false,"metadata":{"visible_when":{"op":"eq","field":"enable_sequential","value":true},"clear_when_hidden":true},"default":1,"min":1,"max":12},{"name":"thinking_mode","label":"Thinking Mode","type":"boolean","description":"Pro only. Enhanced inference for higher quality at the cost of latency. Auto-ignored when input images are attached or sequential mode is on.","required":false,"metadata":{"visible_when":{"op":"eq","field":"enable_sequential","value":false},"clear_when_hidden":true},"default":true},{"name":"image","label":"Image","type":"string","description":"Up to 9 input image URLs for editing. Triggers image-edit mode automatically.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"color_palette","label":"Color Palette","type":"string","description":"Optional JSON array of 3–10 {hex, ratio} objects (ratios sum to 100%). Standard mode only. Example: [{\"hex\":\"#C2D1E6\",\"ratio\":\"60.00%\"},{\"hex\":\"#636574\",\"ratio\":\"40.00%\"}]","required":false,"metadata":{"control":"color-palette","visible_when":{"op":"eq","field":"enable_sequential","value":false},"clear_when_hidden":true}},{"name":"bbox_list","label":"Bounding Box List","type":"string","description":"Interactive editing boxes as JSON. Use [] for no box, or [[x1,y1,x2,y2]] for one box.","required":false,"metadata":{"control":"bounding-box"}},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed. Leave empty for random.","required":false,"metadata":{},"min":0,"max":2147483647},{"name":"watermark","label":"Watermark","type":"boolean","description":"Add a provenance watermark to the output.","required":false,"metadata":{},"default":false},{"name":"response_format","label":"Response Format","type":"enum","description":"Return signed image URLs by default, or include base64 image data when b64_json is requested.","required":false,"metadata":{},"default":"url","options":["url","b64_json"]}],"supported_endpoints":["POST /v1/images/generations"],"pricing":{"prompt":"0","completion":"0","image":"0.03","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Standard","value":"$0.030"},{"spec":"per image","label":"Pro","value":"$0.075"}],"unit_pricing":[{"unit":"image","usd":"0.03","label":"Standard"},{"unit":"image","usd":"0.075","label":"Pro"}],"limits":{"note":"Upload 1-9 images for editing mode; without images, operates as text-to-image.\n\n**Constraints**\n\n- Prompt max 5,000 characters\n- Generation: 10-60s depending on resolution, image count, model variant, and thinking mode\n\n**Image inputs (editing mode)**\n\n- JPEG, PNG, BMP, or WEBP\n- 240-8000 px per side\n- Aspect ratio 1:8 to 8:1\n- Max 20 MB per image\n\n**Capabilities**\n\n- Style transfer, object placement, scene blending, background replacement, multi-reference composition, interactive editing with bounding boxes\n- Pro variant supports up to 4K output\n\n**Content safety**\n\n- Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=wan2-7-image","api_url":"https://docs.empiriolabs.ai/models/wan2-7-image","logo":"https://media.empiriolabs.ai/model-logos/wan.png","status":"available"},{"id":"whisper-large-v3-turbo","object":"model","created":1727740800,"owned_by":"openai","display_name":"Whisper Large v3 Turbo","author":"openai","provider":"openai","description":"Controlled Whisper Large v3 Turbo transcription with multilingual ASR, translation, VAD, timestamps, subtitles, hotwords, and decoder controls.","modality":"audio","type":"stt","category":"transcription","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio"],"output_modalities":["text"],"features":["transcription","translation","multilingual","word_timestamps","hotwords","srt_vtt"],"aliases":["openai/whisper-large-v3-turbo"],"structured_output":null,"native_inference":true,"weight_precision":"FP16","hugging_face_id":"openai/whisper-large-v3-turbo","batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2024-10-01","is_new":false,"is_featured":true,"discount":{"label":"Save up to 88%","percent":88},"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"audio_url","label":"audio_url","type":"string","description":"URL of the audio file to transcribe. Mutually exclusive with audio_base64.","required":false,"metadata":{"ui":{"hide_in_playground":true},"aliases":["url"]}},{"name":"audio_base64","label":"audio_base64","type":"string","description":"Base64-encoded audio bytes. Mutually exclusive with audio_url.","required":false,"metadata":{"aliases":["audio","b64_json","base64"]}},{"name":"audio_suffix","label":"audio_suffix","type":"string","description":"File extension hint (mp3, wav, m4a, etc.) when the audio source has no recognizable extension.","required":false,"metadata":{"aliases":["extension"]},"default":".audio"},{"name":"language","label":"language","type":"string","description":"ISO 639-1 language code (en, es, fr, etc.). Leave blank for auto-detection.","required":false,"metadata":{}},{"name":"task","label":"task","type":"enum","description":"transcribe = same language, translate = translate to English.","required":false,"metadata":{},"default":"transcribe","options":["transcribe","translate"]},{"name":"beam_size","label":"beam_size","type":"number","description":"Beam search width. Higher = more accurate but slower.","required":false,"metadata":{},"default":5,"min":1,"max":32},{"name":"best_of","label":"best_of","type":"number","description":"Number of candidates to sample with temperature > 0.","required":false,"metadata":{},"default":5,"min":1,"max":32},{"name":"patience","label":"patience","type":"number","description":"Beam search patience factor. Higher = explore more candidates.","required":false,"metadata":{},"default":1,"min":0,"max":10},{"name":"length_penalty","label":"length_penalty","type":"number","description":"Penalty applied to longer transcripts. Negative encourages shorter output.","required":false,"metadata":{},"default":1,"min":-10,"max":10},{"name":"repetition_penalty","label":"repetition_penalty","type":"number","description":"Penalty for repeating tokens. >1 reduces repetition.","required":false,"metadata":{},"default":1,"min":0.1,"max":5},{"name":"no_repeat_ngram_size","label":"no_repeat_ngram_size","type":"number","description":"Block any n-gram of this size from repeating in the output.","required":false,"metadata":{},"default":0,"min":0,"max":20},{"name":"temperature","label":"temperature","type":"string","description":"Sampling temperature. 0 = deterministic, higher = more variation.","required":false,"metadata":{},"default":"0,0.2,0.4,0.6,0.8,1"},{"name":"compression_ratio_threshold","label":"compression_ratio_threshold","type":"number","description":"Treat output with compression ratio above this as failed and retry.","required":false,"metadata":{},"default":2.4},{"name":"log_prob_threshold","label":"log_prob_threshold","type":"number","description":"Treat segments with average log-prob below this as failed and retry.","required":false,"metadata":{},"default":-1},{"name":"no_speech_threshold","label":"no_speech_threshold","type":"number","description":"Mark a segment as silent when no-speech probability exceeds this AND log-prob is below threshold.","required":false,"metadata":{},"default":0.6},{"name":"condition_on_previous_text","label":"condition_on_previous_text","type":"boolean","description":"Use prior transcript as conditioning for the next segment.","required":false,"metadata":{},"default":true},{"name":"prompt_reset_on_temperature","label":"prompt_reset_on_temperature","type":"number","description":"Reset the conditioning prompt when temperature falls back during retry.","required":false,"metadata":{},"default":0.5,"min":0,"max":1},{"name":"initial_prompt","label":"initial_prompt","type":"string","description":"Initial text prompt to guide vocabulary and style.","required":false,"metadata":{"aliases":["prompt"]}},{"name":"prefix","label":"prefix","type":"string","description":"Text to prepend to the first segment's transcript.","required":false,"metadata":{}},{"name":"suppress_blank","label":"suppress_blank","type":"boolean","description":"Suppress empty outputs at the start of each segment.","required":false,"metadata":{},"default":true},{"name":"suppress_tokens","label":"suppress_tokens","type":"string","description":"Comma-separated token IDs to suppress during decoding.","required":false,"metadata":{},"default":"-1"},{"name":"without_timestamps","label":"without_timestamps","type":"boolean","description":"Decode without timestamp tokens. Segments still carry their start and end times.","required":false,"metadata":{},"default":false},{"name":"word_timestamps","label":"word_timestamps","type":"boolean","description":"Include per-word timestamps in the response.","required":false,"metadata":{},"default":false},{"name":"prepend_punctuations","label":"prepend_punctuations","type":"string","description":"Punctuation characters to merge with the following word.","required":false,"metadata":{}},{"name":"append_punctuations","label":"append_punctuations","type":"string","description":"Punctuation characters to merge with the preceding word.","required":false,"metadata":{}},{"name":"max_initial_timestamp","label":"max_initial_timestamp","type":"number","description":"Cap the first segment's start time to this many seconds.","required":false,"metadata":{},"default":1,"min":0,"max":30},{"name":"multilingual","label":"multilingual","type":"boolean","description":"Allow language switching within a single audio file.","required":false,"metadata":{},"default":false},{"name":"vad_filter","label":"vad_filter","type":"boolean","description":"Apply Silero VAD to remove silence before decoding.","required":false,"metadata":{},"default":true},{"name":"vad_parameters","label":"vad_parameters","type":"string","description":"VAD configuration as JSON (threshold, min_speech_duration_ms, etc.).","required":false,"metadata":{}},{"name":"max_new_tokens","label":"max_new_tokens","type":"number","description":"Cap on decoded tokens per segment.","required":false,"metadata":{}},{"name":"chunk_length","label":"chunk_length","type":"number","description":"Length of each audio chunk in seconds before decoding.","required":false,"metadata":{}},{"name":"clip_timestamps","label":"clip_timestamps","type":"string","description":"Only decode within these (start, end) second ranges. Format: \"0.5,12.3,15.0,30.0\".","required":false,"metadata":{},"default":"0"},{"name":"hallucination_silence_threshold","label":"hallucination_silence_threshold","type":"number","description":"Treat long silent sections above this many seconds as hallucinations and skip them.","required":false,"metadata":{}},{"name":"hotwords","label":"hotwords","type":"string","description":"Comma-separated hotwords to bias decoding toward (proper nouns, jargon).","required":false,"metadata":{}},{"name":"language_detection_threshold","label":"language_detection_threshold","type":"number","description":"Confidence threshold for auto language detection.","required":false,"metadata":{},"default":0.5},{"name":"language_detection_segments","label":"language_detection_segments","type":"number","description":"Number of leading segments to use for language detection.","required":false,"metadata":{},"default":1,"min":1,"max":20},{"name":"include_tokens","label":"include_tokens","type":"boolean","description":"Include raw token IDs alongside each word/segment.","required":false,"metadata":{},"default":false},{"name":"response_format","label":"response_format","type":"enum","description":"json | verbose_json | text | srt | vtt.","required":false,"metadata":{"aliases":["format"]},"default":"verbose_json","options":["verbose_json","json","text","srt","vtt"]}],"supported_endpoints":["POST /v1/audio/transcriptions"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per minute of audio","label":"Controlled transcription","value":"$0.005 (was $0.042)"}],"unit_pricing":[{"unit":"minute","usd":"0.005","label":"Controlled transcription"}],"limits":{"note":"Supports URL/base64 audio, language/task, beam and temperature fallback controls, VAD/chunking, hotwords, prompts, word timestamps, punctuation controls, token debug output, and JSON/text/SRT/VTT formats."},"notes":"Supports URL/base64 audio, language/task, beam and temperature fallback controls, VAD/chunking, hotwords, prompts, word timestamps, punctuation controls, token debug output, and JSON/text/SRT/VTT formats.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=whisper-large-v3-turbo","api_url":"https://docs.empiriolabs.ai/models/whisper-large-v3-turbo","logo":"https://media.empiriolabs.ai/model-logos/whisper-large-v3-turbo.png","status":"available"},{"id":"manus","object":"model","created":1735689600,"owned_by":"manus","display_name":"Manus","author":"manus","provider":"manus","description":"Autonomous AI agent that turns a high-level prompt into subtasks, calls tools and APIs, and delivers end-to-end results without manual orchestration.","modality":"text","type":"agent","category":"tools","category_label":null,"modality_label":null,"modalities":["text","image","video","audio","document"],"input_modalities":["text","image","video","audio","document"],"output_modalities":["text","image","video","audio","document"],"features":["autonomous","multi_step","tool_use"],"aliases":[],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Task description for the agent","required":true,"metadata":{}},{"name":"attachments","label":"Attachments","type":"string","description":"Files for the agent to work with (any type: audio, video, images, documents, data). Each item is a URL string or an object with url, filename, and mime_type. Files are placed in the agent's workspace before the task starts. Up to 10 files per message.","required":false,"metadata":{"group":"input"}},{"name":"agent_profile","label":"Agent Profile","type":"enum","description":"Capability profile for the task: `standard` for most work, `lite` for quicker, lower-cost tasks, or `max` for the most complex work. `max` also takes a thinking level, `max-medium`, `max-high`, `max-extra` (the level plain `max` runs) or `max-ultra`, the deepest and slowest; a higher level reasons longer and uses more credits. A follow-up sent with `task_id` can switch profiles.","required":false,"metadata":{"option_labels":{"max":"Max","lite":"Lite","max-high":"Max, high thinking","standard":"Standard","max-extra":"Max, extra thinking","max-ultra":"Max, ultra thinking","max-medium":"Max, medium thinking"}},"default":"standard","options":["standard","lite","max","max-medium","max-high","max-extra","max-ultra"]},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the agent's output without added Markdown formatting. Applies to streamed runs only.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/agents/run","GET /v1/agents/{task_id}","GET /v1/agents/{task_id}/messages","POST /v1/agents/{task_id}/stop"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per task","label":"Lite profile","value":"$1.44 - $2.63"},{"spec":"per task","label":"Standard profile","value":"$2.89 - $5.25"},{"spec":"per task","label":"Max profile","value":"$5.25 - $9.19"},{"spec":"per task","label":"Max, ultra thinking","value":"$13.57 - $23.75"}],"unit_pricing":[],"limits":null,"notes":"**Content safety**\n\nGenerated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=manus","api_url":"https://docs.empiriolabs.ai/models/manus","logo":"https://media.empiriolabs.ai/model-logos/manus.png","status":"available"},{"id":"deepseek-v4-pro:variant1","object":"model","created":1776988800,"owned_by":"deepseek","display_name":"DeepSeek V4 Pro (Variant 1)","author":"deepseek","provider":"deepseek","description":"Flagship MoE LLM with 1.6T total / 49B active parameters and native 1M context for advanced math, logical inference, and specialized coding.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","web_search","function_calling"],"aliases":[],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":393216,"model_released_at":"2026-04-24","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 2 = maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":393216},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable step-by-step reasoning before answering.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":32768,"min":1,"max":393216},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable live web search. Adds $0.02 to the request cost when enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/deepseek-v4-pro:variant1:generateContent"],"pricing":{"prompt":"0.0000024","completion":"0.0000048","image":"0","request":"0","input_cache_read":"0.0000024"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$2.40"},{"spec":"per 1M generated tokens","label":"Output","value":"$4.80"},{"spec":"per request when enabled","label":"Web search","value":"$0.02"}],"unit_pricing":[{"unit":"1m_tokens","usd":"2.4","label":"Input"},{"unit":"1m_tokens","usd":"4.8","label":"Output"},{"unit":"request","usd":"0.02","label":"Web search"}],"limits":null,"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=deepseek-v4-pro:variant1","api_url":"https://docs.empiriolabs.ai/models/deepseek-v4-pro#variant1","logo":"https://media.empiriolabs.ai/model-logos/deepseek.png","status":"available"},{"id":"grok-imagine-video-1-5","object":"model","created":1781568000,"owned_by":"xai","display_name":"Grok Imagine Video 1.5","author":"xai","provider":"xai","description":"Text-to-video, image-to-video, and reference-to-video generation with up to seven reference images for consistent characters, up to 15 seconds at 1080p.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image"],"output_modalities":["video"],"features":["text_to_video","image_to_video","reference_to_video","video_generation"],"aliases":["grok-imagine-video-1.5","xai/grok-imagine-video-1-5","xai/grok-imagine-video-1.5"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-06-16","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Describe the scene, motion, and action to generate.","required":true,"metadata":{"ui":{"control":"textarea","section":"Input"}}},{"name":"mode","label":"Mode","type":"enum","description":"Auto detects from attachments. t2v: text-to-video. i2v: animate one image. r2v: reference-to-video from up to 7 images.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v","r2v"]},{"name":"image","label":"Image","type":"string","description":"Image URL or upload. Optional: one image for image-to-video, up to 7 for reference-to-video. Leave empty for text-to-video.","required":false,"metadata":{"ui":{"accept":"image/*","control":"file","section":"Input"}}},{"name":"duration","label":"Duration","type":"number","description":"Length of the generated video in seconds.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Generation"}},"default":10,"min":1,"max":15},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution. 480p renders fastest, 1080p is the highest definition. Reference-to-video supports up to 720p.","required":false,"metadata":{"ui":{"control":"segmented","section":"Generation"},"variants":[{"when":{"op":"eq","field":"mode","value":"r2v"},"default":"720p","description":"Output resolution. Reference-to-video supports up to 720p.","allowed_values":["480p","720p"]}]},"default":"720p","options":["480p","720p","1080p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio. Defaults to the source image aspect ratio for image-to-video, otherwise 16:9.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Generation"}},"options":["1:1","16:9","9:16","4:3","3:4","3:2","2:3"]},{"name":"reference_images","label":"Reference Images","type":"string","description":"Comma-separated image URLs for reference-to-video (up to 7). Alternative to uploading images.","required":false,"metadata":{"ui":{"hide_in_playground":true}}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"480p","value":"$0.096"},{"spec":"per second","label":"720p","value":"$0.168"},{"spec":"per second","label":"1080p","value":"$0.300"},{"spec":"per image","label":"Image input","value":"$0.05"}],"unit_pricing":[{"unit":"second","usd":"0.096","label":"480p"},{"unit":"second","usd":"0.168","label":"720p"},{"unit":"second","usd":"0.3","label":"1080p"},{"unit":"image","usd":"0.05","label":"Image input"}],"limits":{"note":"Generates video from a text prompt on its own, from a source image, or from up to seven reference images that keep characters and objects consistent across the shot.\n\n**Modes**\n\n- Text-to-video: send a prompt with no image.\n- Image-to-video: add one image and it becomes the starting frame.\n- Reference-to-video: add two or more images (up to seven) to carry their subjects into a new scene. Tag them in the prompt as <IMAGE_1>, <IMAGE_2>, and so on.\n\n**Example reference-to-video prompt**\n\n```\n<IMAGE_1> and <IMAGE_2> walking together through a neon-lit street at night.\n```\n\nThe mode is detected from what you send, and can be set explicitly with the mode parameter.\n\n**Defaults**\n\n- 10 second duration (1 to 15 seconds supported)\n- 720p output (480p, 720p, or 1080p)\n- Aspect ratio follows the source image for image-to-video, otherwise 16:9\n\n**Resolution**\n\n1080p is available for text-to-video and image-to-video. Reference-to-video supports up to 720p.\n\n**Controls**\n\nSupports prompt, mode, a source image or reference images (URL or upload), duration, resolution, and aspect ratio.\n\n**Billing**\n\n- Charged per second of generated video at the selected resolution (higher resolutions cost more per second), plus a per-image fee for each image you supply. Text-to-video has no image fee.\n- A request that fails validation or errors out before any video is produced is not billed.\n- A video that is produced but then blocked by content policy is still billed. This follows xAI usage policy, which charges for the generation even when the output is blocked by the content safety check. Keep prompts and source images within the usage policy to avoid this."},"notes":"Generates video from a text prompt on its own, from a source image, or from up to seven reference images that keep characters and objects consistent across the shot.\n\n**Modes**\n\n- Text-to-video: send a prompt with no image.\n- Image-to-video: add one image and it becomes the starting frame.\n- Reference-to-video: add two or more images (up to seven) to carry their subjects into a new scene. Tag them in the prompt as <IMAGE_1>, <IMAGE_2>, and so on.\n\n**Example reference-to-video prompt**\n\n```\n<IMAGE_1> and <IMAGE_2> walking together through a neon-lit street at night.\n```\n\nThe mode is detected from what you send, and can be set explicitly with the mode parameter.\n\n**Defaults**\n\n- 10 second duration (1 to 15 seconds supported)\n- 720p output (480p, 720p, or 1080p)\n- Aspect ratio follows the source image for image-to-video, otherwise 16:9\n\n**Resolution**\n\n1080p is available for text-to-video and image-to-video. Reference-to-video supports up to 720p.\n\n**Controls**\n\nSupports prompt, mode, a source image or reference images (URL or upload), duration, resolution, and aspect ratio.\n\n**Billing**\n\n- Charged per second of generated video at the selected resolution (higher resolutions cost more per second), plus a per-image fee for each image you supply. Text-to-video has no image fee.\n- A request that fails validation or errors out before any video is produced is not billed.\n- A video that is produced but then blocked by content policy is still billed. This follows xAI usage policy, which charges for the generation even when the output is blocked by the content safety check. Keep prompts and source images within the usage policy to avoid this.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=grok-imagine-video-1-5","api_url":"https://docs.empiriolabs.ai/models/grok-imagine-video-1-5","logo":"https://media.empiriolabs.ai/model-logos/grok-imagine-video-1-5.png","status":"available"},{"id":"glm-5-2:variant1","object":"model","created":1781568000,"owned_by":"zhipu","display_name":"GLM 5.2 (Variant 1)","author":"zhipu","provider":"zhipu","description":"Reasoning and coding model with a 1M token context, 128K output, adjustable reasoning effort, and tool calling.","modality":"text","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","function_calling","cache","web_search"],"aliases":[],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1048576,"context_length":1048576,"max_output_tokens":131072,"model_released_at":"2026-06-16","is_new":false,"is_featured":false,"discount":{"label":"Save up to 21%","percent":21},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 1.99 = maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable step-by-step reasoning before answering.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for reasoning when thinking is enabled.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Model"},"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":32768,"min":1,"max":131071},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/glm-5-2:variant1:generateContent"],"pricing":{"prompt":"0.0000011","completion":"0.000003851","image":"0","request":"0","input_cache_read":"0.000000275"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.10 (was $1.40)"},{"spec":"per 1M generated tokens","label":"Output","value":"$3.851 (was $4.40)"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.275"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.1","label":"Input"},{"unit":"1m_tokens","usd":"3.851","label":"Output"},{"unit":"1m_tokens","usd":"0.275","label":"Implicit cache read"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":null,"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=glm-5-2:variant1","api_url":"https://docs.empiriolabs.ai/models/glm-5-2#variant1","logo":"https://media.empiriolabs.ai/model-logos/glm.png","status":"available"},{"id":"kimi-k2-7-code:variant1","object":"model","created":1781568000,"owned_by":"moonshot","display_name":"Kimi K2.7 Code (Variant 1)","author":"moonshot","provider":"moonshot","description":"Kimi K2.7 Code is Moonshot's trillion-parameter agentic coding model with 256K context, always-on reasoning, and text, image, and video inputs.","modality":"multimodal","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","function_calling","multimodal","agentic_coding","cache","web_search"],"aliases":[],"structured_output":"none","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":262144,"context_length":262144,"max_output_tokens":16384,"model_released_at":"2026-06-16","is_new":false,"is_featured":false,"discount":{"label":"Save up to 7%","percent":7},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. Reasoning tokens count toward this limit.","required":false,"metadata":{},"default":16384,"min":1,"max":16384},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"response_format","label":"Response Format","type":"string","description":"OpenAI-compatible JSON mode or JSON schema response format.","required":false,"metadata":{"ui":{"control":"json","section":"Output"}}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/kimi-k2-7-code:variant1:generateContent"],"pricing":{"prompt":"0.0000008939","completion":"0.0000037131","image":"0","request":"0","input_cache_read":"0.0000001788"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.8939 (was $0.95)"},{"spec":"per 1M generated tokens","label":"Output","value":"$3.7131 (was $4.00)"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.1788"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.8939","label":"Input"},{"unit":"1m_tokens","usd":"3.7131","label":"Output"},{"unit":"1m_tokens","usd":"0.1788","label":"Implicit cache read"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":null,"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=kimi-k2-7-code:variant1","api_url":"https://docs.empiriolabs.ai/models/kimi-k2-7-code#variant1","logo":"https://media.empiriolabs.ai/model-logos/kimi.png","status":"available"},{"id":"happyhorse-1-1","object":"model","created":1782086400,"owned_by":"alibaba","display_name":"HappyHorse 1.1","author":"alibaba","provider":"alibaba","description":"Text, image, and reference-to-video in one model. Cinematic motion, character consistency across up to 9 references, and synchronized native audio.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image"],"output_modalities":["video"],"features":["video_generation","image_to_video","reference_to_video","audio_sync"],"aliases":["alibaba/happyhorse-1-1","alibaba/happyhorse-1.1","happyhorse-1.1"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-06-22","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Describe the scene to generate. Up to 2,500 characters.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"Auto detects from attachments. t2v: text-to-video. i2v: animate one image. r2v: reference-to-video from up to 9 images.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v","r2v"]},{"name":"image","label":"Image","type":"string","description":"Image URL or upload. One image for image-to-video, up to 9 for reference-to-video. Reference them in the prompt as character1, character2.","required":false,"metadata":{}},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Aspect ratio of the output. Used by text-to-video and reference-to-video; image-to-video follows the source image.","required":false,"metadata":{},"default":"16:9","options":["16:9","9:16","1:1","4:3","3:4"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution. 720p renders faster; 1080p is higher fidelity.","required":false,"metadata":{},"default":"720p","options":["720p","1080p"]},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds (3 to 15).","required":false,"metadata":{},"default":5,"min":3,"max":15},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed. Reuse the same seed for a repeatable result.","required":false,"metadata":{},"min":0,"max":2147483647},{"name":"watermark","label":"Watermark","type":"boolean","description":"Add a watermark to the generated video. Off by default.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"720p","value":"$0.14"},{"spec":"per second","label":"1080p","value":"$0.18"}],"unit_pricing":[{"unit":"second","usd":"0.14","label":"720p"},{"unit":"second","usd":"0.18","label":"1080p"}],"limits":{"note":"**Modes** (in one model)\n\n- Text-to-video\n- Image-to-video\n- Reference-to-video (up to 9 images)\n\n**Constraints**\n\n- 720p / 1080p, 3 to 15 seconds per generation\n- Prompt up to 2,500 characters\n\n**Aspect ratios**\n\n- Text and reference modes: 16:9, 9:16, 1:1, 4:3, 3:4\n- Image-to-video follows the source image\n\nNative audio is generated automatically."},"notes":"**Modes** (in one model)\n\n- Text-to-video\n- Image-to-video\n- Reference-to-video (up to 9 images)\n\n**Constraints**\n\n- 720p / 1080p, 3 to 15 seconds per generation\n- Prompt up to 2,500 characters\n\n**Aspect ratios**\n\n- Text and reference modes: 16:9, 9:16, 1:1, 4:3, 3:4\n- Image-to-video follows the source image\n\nNative audio is generated automatically.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=happyhorse-1-1","api_url":"https://docs.empiriolabs.ai/models/happyhorse-1-1","logo":"https://media.empiriolabs.ai/model-logos/happyhorse-1-1.png","status":"available"},{"id":"seedance-2-0-mini","object":"model","created":1781481600,"owned_by":"bytedance","display_name":"Seedance 2.0 Mini","author":"bytedance","provider":"bytedance","description":"The fastest, most affordable Seedance 2.0 tier for short cinematic clips with native audio, camera control, and image or video inputs at 480p and 720p.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image","audio"],"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"features":["audio_sync","camera_control","image_to_video","video_editing"],"aliases":["bytedance/seedance-2.0-mini","seedance-2.0-mini"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-06-15","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"auto: detect from inputs. t2v: text-to-video. i2v_first: animate first frame. i2v_both: morph between start (image) and end (image_end). reference: use image as visual reference. edit: edit attached video. extend: extend attached video.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v_first","i2v_both","reference","edit","extend"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution.","required":false,"metadata":{},"default":"720p","options":["480p","720p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio. adaptive lets the model choose from your inputs.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"adaptive","options":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]},{"name":"custom_duration","label":"Custom Duration","type":"boolean","description":"If false, the model decides clip length. If true, use the duration field.","required":false,"metadata":{},"default":true},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds. Only used when custom_duration=true.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"visible_when":{"op":"eq","field":"custom_duration","value":true},"clear_when_hidden":true},"default":5,"min":4,"max":15},{"name":"generate_audio","label":"Generate Audio","type":"boolean","description":"Generate native audio with the video.","required":false,"metadata":{},"default":true},{"name":"image","label":"Image","type":"string","description":"Reference / first-frame image URL.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"image_end","label":"Image End","type":"string","description":"End-frame image URL for i2v_both / extend.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"video","label":"Video","type":"string","description":"Reference video URL for edit / extend / reference.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid.","required":false,"metadata":{},"default":""}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"T2V/I2V 480P","value":"$0.070"},{"spec":"per second","label":"T2V/I2V 720P","value":"$0.150"},{"spec":"per second","label":"Video Input 480P","value":"$0.167"},{"spec":"per second","label":"Video Input 720P","value":"$0.359"}],"unit_pricing":[{"unit":"second","usd":"0.07","label":"T2V/I2V 480P"},{"unit":"second","usd":"0.15","label":"T2V/I2V 720P"},{"unit":"second","usd":"0.167","label":"Video Input 480P"},{"unit":"second","usd":"0.359","label":"Video Input 720P"}],"limits":{"note":"Lightweight, lowest-cost tier in the Seedance 2.0 family: the fastest and most affordable option, ideal for drafts and high-volume short-form. 480p and 720p only (no 1080p or 4K).\n\n**Tip**\n\n- Uploaded images and videos that show a real person's face are blocked. To feature a person, start from an image made with Seedream 5.5. To use your own face, verify it in [My face](https://platform.empiriolabs.ai/dashboard/verified-portrait).\n\n**Uploaded media preprocessing**\n\n- Video inputs are capped to 15 seconds for reference, edit, and extend workflows.\n- Uploaded video inputs are normalized to provider-compatible MP4 when needed."},"notes":"Lightweight, lowest-cost tier in the Seedance 2.0 family: the fastest and most affordable option, ideal for drafts and high-volume short-form. 480p and 720p only (no 1080p or 4K).\n\n**Tip**\n\n- Uploaded images and videos that show a real person's face are blocked. To feature a person, start from an image made with Seedream 5.5. To use your own face, verify it in [My face](https://platform.empiriolabs.ai/dashboard/verified-portrait).\n\n**Uploaded media preprocessing**\n\n- Video inputs are capped to 15 seconds for reference, edit, and extend workflows.\n- Uploaded video inputs are normalized to provider-compatible MP4 when needed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=seedance-2-0-mini","api_url":"https://docs.empiriolabs.ai/models/seedance-2-0-mini","logo":"https://media.empiriolabs.ai/model-logos/seedance-2-0-mini.png","status":"available"},{"id":"minimax-m3:priority","object":"model","created":1780272000,"owned_by":"minimax","display_name":"MiniMax M3 (Priority)","author":"minimax","provider":"minimax","description":"MiniMax M3 is a multimodal reasoning model for coding, agents, and long-context analysis with text, image, and video input.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","video","web_search","function_calling","cache","long_context"],"aliases":[],"structured_output":"none","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1048458,"context_length":1048458,"max_output_tokens":524288,"model_released_at":"2026-06-01","is_new":false,"is_featured":false,"discount":{"label":"Save up to 25%","percent":25},"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_completion_tokens","label":"Max Completion Tokens","type":"number","description":"Maximum generated tokens, including reasoning tokens when thinking is enabled.","required":false,"metadata":{"aliases":["max_tokens"]},"default":4096,"min":1,"max":524288},{"name":"stop","label":"Stop","type":"string","description":"Optional stop sequence or list of stop sequences.","required":false,"metadata":{"items":"string"}},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.01 to the request cost for each invoked call.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.01}},"default":false},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable adaptive model thinking before answering. Set false to request a direct answer without a reasoning phase.","required":false,"metadata":{"true_value":"adaptive","false_value":"disabled","provider_field":"thinking.type"},"default":true},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible tool definitions for function calling.","required":false,"metadata":{"advanced":true}},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"Optional OpenAI-compatible tool_choice value.","required":false,"metadata":{"advanced":true}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/minimax-m3:priority:generateContent"],"pricing":[{"prompt":"0.0000003375","completion":"0.00000135","image":"0","request":"0","input_cache_read":"0.0000000675"},{"prompt":"0.000000675","completion":"0.0000027","image":"0","request":"0","input_cache_read":"0.000000135","min_context":512000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=512K $0.3375 (was $0.45); >512K $0.675 (was $0.90)"},{"spec":"per 1M generated tokens","label":"Output","value":"<=512K $1.35 (was $1.80); >512K $2.70 (was $3.60)"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"<=512K $0.0675 (was $0.09); >512K $0.135 (was $0.18)"},{"spec":"per call when invoked","label":"Web search","value":"$0.01"}],"unit_pricing":[{"unit":"call","usd":"0.01","label":"Web search"}],"limits":{"note":"This is the priority service tier: requests receive priority admission for faster response times and improved reliability, priced above the standard MiniMax M3 route. Text, image, and video input with text output. Thinking defaults to adaptive and can be disabled. Pricing is tiered by input tokens including cache hits, with <=512K cheaper than >512K. Supports up to 1M input tokens. Set tool_web_search to true to let the model search the web; each executed search is billed, and one request can run several searches. Answers that used web search end with a Sources list unless disable_formatting is true. Structured output through response_format is not supported; ask for JSON in the prompt instead.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes tools (web search, code interpreter, etc.) inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape, exact field names, units, and which tools appear can vary slightly per provider:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nThe tool counts are already factored into `cost_usd`, they are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=minimax-m3:priority","api_url":"https://docs.empiriolabs.ai/models/minimax-m3#priority","logo":"https://media.empiriolabs.ai/model-logos/minimax.png","status":"available"},{"id":"step-3-7-flash","object":"model","created":1779926400,"owned_by":"stepfun","display_name":"Step 3.7 Flash","author":"stepfun","provider":"stepfun","description":"StepFun multimodal reasoning model with image and video input, tool calling, adjustable reasoning effort, and 256K context.","modality":"multimodal","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","function_calling","structured_output","vision","video","prompt_cache","agentic_coding","web_search"],"aliases":["step-3.7-flash","stepfun/step-3-7-flash","stepfun/step-3.7-flash"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":262144,"context_length":262144,"max_output_tokens":131072,"model_released_at":"2026-05-28","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0.5,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0.9,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. Reasoning tokens count toward this limit.","required":false,"metadata":{"ui":{"control":"number","section":"Output"}},"default":4096,"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Stop sequences.","required":false,"metadata":{"ui":{"control":"stop-sequences","section":"Output"}}},{"name":"frequency_penalty","label":"Frequency Penalty","type":"number","description":"Penalty for repeated tokens.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0,"min":-2,"max":2},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Controls how much the model reasons before it answers. Higher effort spends more tokens on reasoning.","required":false,"metadata":{"ui":{"control":"segmented","section":"Reasoning"}},"default":"low","options":["low","medium","high"]},{"name":"response_format","label":"Response Format","type":"string","description":"OpenAI-compatible response format. Use {\"type\":\"json_object\"} for JSON object mode.","required":false,"metadata":{"ui":{"control":"json","section":"Output"}}},{"name":"reasoning_format","label":"Reasoning Format","type":"enum","description":"Format of the reasoning trace returned alongside the answer.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Reasoning"}},"default":"general","options":["general","deepseek-style"]},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function tools.","required":false,"metadata":{"ui":{"control":"json","section":"Tools"}}},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible tool choice.","required":false,"metadata":{"ui":{"control":"text_field","section":"Tools"}}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/step-3-7-flash:generateContent"],"pricing":{"prompt":"0.0000002","completion":"0.00000115","image":"0","request":"0","input_cache_read":"0.00000004"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.20"},{"spec":"per 1M generated tokens","label":"Output","value":"$1.15"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.04"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.2","label":"Input"},{"unit":"1m_tokens","usd":"1.15","label":"Output"},{"unit":"1m_tokens","usd":"0.04","label":"Implicit cache read"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Supports text, image, and video input with 256K context, function tools, JSON object mode, reasoning_effort low, medium, or high, and optional Linkup web search. Video input supports MP4 under 128 MB, with clips under 5 minutes recommended."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=step-3-7-flash","api_url":"https://docs.empiriolabs.ai/models/step-3-7-flash","logo":"https://media.empiriolabs.ai/model-logos/step-3-7-flash.png","status":"available"},{"id":"step-3-5-flash","object":"model","created":1770854400,"owned_by":"stepfun","display_name":"Step 3.5 Flash","author":"stepfun","provider":"stepfun","description":"StepFun text reasoning model for agents, coding, tool calling, and long-context analysis.","modality":"text","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","function_calling","prompt_cache","agentic_coding","web_search"],"aliases":["step-3.5-flash","stepfun/step-3-5-flash","stepfun/step-3.5-flash"],"structured_output":"none","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":262144,"context_length":262144,"max_output_tokens":131072,"model_released_at":"2026-02-12","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0.5,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0.9,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. Reasoning tokens count toward this limit.","required":false,"metadata":{"ui":{"control":"number","section":"Output"}},"default":4096,"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Stop sequences.","required":false,"metadata":{"ui":{"control":"stop-sequences","section":"Output"}}},{"name":"frequency_penalty","label":"Frequency Penalty","type":"number","description":"Penalty for repeated tokens.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0,"min":-2,"max":2},{"name":"reasoning_format","label":"Reasoning Format","type":"enum","description":"Format of the reasoning trace returned alongside the answer.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Reasoning"}},"default":"general","options":["general","deepseek-style"]},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function tools.","required":false,"metadata":{"ui":{"control":"json","section":"Tools"}}},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible tool choice.","required":false,"metadata":{"ui":{"control":"text_field","section":"Tools"}}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/step-3-5-flash:generateContent"],"pricing":{"prompt":"0.0000001","completion":"0.0000003","image":"0","request":"0","input_cache_read":"0.00000002"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.10"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.30"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.02"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.1","label":"Input"},{"unit":"1m_tokens","usd":"0.3","label":"Output"},{"unit":"1m_tokens","usd":"0.02","label":"Implicit cache read"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Text-only reasoning with 256K context, function tools, prompt-cache billing, and optional Linkup web search."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=step-3-5-flash","api_url":"https://docs.empiriolabs.ai/models/step-3-5-flash","logo":"https://media.empiriolabs.ai/model-logos/step-3-5-flash.png","status":"available"},{"id":"step-3-5-flash-2603","object":"model","created":1775088000,"owned_by":"stepfun","display_name":"Step 3.5 Flash 2603","author":"stepfun","provider":"stepfun","description":"Agent-optimized Step 3.5 Flash variant with low and high reasoning effort modes.","modality":"text","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","function_calling","prompt_cache","agentic_coding","web_search"],"aliases":["step-3.5-flash-2603","stepfun/step-3-5-flash-2603","stepfun/step-3.5-flash-2603"],"structured_output":"none","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":262144,"context_length":262144,"max_output_tokens":131072,"model_released_at":"2026-04-02","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":false,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0.5,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0.9,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. Reasoning tokens count toward this limit.","required":false,"metadata":{"ui":{"control":"number","section":"Output"}},"default":4096,"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Stop sequences.","required":false,"metadata":{"ui":{"control":"stop-sequences","section":"Output"}}},{"name":"frequency_penalty","label":"Frequency Penalty","type":"number","description":"Penalty for repeated tokens.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0,"min":-2,"max":2},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Controls how much the model reasons before it answers. Higher effort spends more tokens on reasoning.","required":false,"metadata":{"ui":{"control":"segmented","section":"Reasoning"}},"default":"low","options":["low","high"]},{"name":"reasoning_format","label":"Reasoning Format","type":"enum","description":"Format of the reasoning trace returned alongside the answer.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Reasoning"}},"default":"general","options":["general","deepseek-style"]},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function tools.","required":false,"metadata":{"ui":{"control":"json","section":"Tools"}}},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible tool choice.","required":false,"metadata":{"ui":{"control":"text_field","section":"Tools"}}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/step-3-5-flash-2603:generateContent"],"pricing":{"prompt":"0.0000001","completion":"0.0000003","image":"0","request":"0","input_cache_read":"0.00000002"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.10"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.30"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.02"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.1","label":"Input"},{"unit":"1m_tokens","usd":"0.3","label":"Output"},{"unit":"1m_tokens","usd":"0.02","label":"Implicit cache read"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Text-only agent model with 256K context, function tools, prompt-cache billing, reasoning_effort low or high, and optional Linkup web search."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=step-3-5-flash-2603","api_url":"https://docs.empiriolabs.ai/models/step-3-5-flash-2603","logo":"https://media.empiriolabs.ai/model-logos/step-3-5-flash-2603.png","status":"available"},{"id":"stepaudio-2-5-chat","object":"model","created":1735689600,"owned_by":"stepfun","display_name":"StepAudio 2.5 Chat","author":"stepfun","provider":"stepfun","description":"StepFun audio and text conversation model with text output and paralinguistic understanding.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","audio"],"input_modalities":["text","audio"],"output_modalities":["text"],"features":["audio_input","speech_understanding","prompt_cache","multimodal","web_search"],"aliases":["stepaudio-2.5-chat","stepfun/stepaudio-2-5-chat","stepfun/stepaudio-2.5-chat"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":262144,"context_length":262144,"max_output_tokens":131072,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0.5,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0.9,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{"ui":{"control":"number","section":"Output"}},"default":4096,"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Stop sequences.","required":false,"metadata":{"ui":{"control":"stop-sequences","section":"Output"}}},{"name":"frequency_penalty","label":"Frequency Penalty","type":"number","description":"Penalty for repeated tokens.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0,"min":-2,"max":2},{"name":"modalities","label":"Modalities","type":"string","description":"Response modalities. Text output is currently exposed.","required":false,"metadata":{"ui":{"control":"json","section":"Audio chat"}},"default":["text"]},{"name":"response_format","label":"Response Format","type":"string","description":"OpenAI-compatible response format. Use {\"type\":\"json_object\"} for JSON object mode.","required":false,"metadata":{"ui":{"control":"json","section":"Output"}}},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function tools.","required":false,"metadata":{"ui":{"control":"json","section":"Tools"}}},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible tool choice.","required":false,"metadata":{"ui":{"control":"text_field","section":"Tools"}}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/stepaudio-2-5-chat:generateContent"],"pricing":{"prompt":"0.0000015","completion":"0.0000035","image":"0","request":"0","input_cache_read":"0.0000003"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.50"},{"spec":"per 1M generated tokens","label":"Output","value":"$3.50"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.30"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.5","label":"Input"},{"unit":"1m_tokens","usd":"3.5","label":"Output"},{"unit":"1m_tokens","usd":"0.3","label":"Implicit cache read"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Accepts text or base64 audio input and returns text. Linkup web search is available for text prompts."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=stepaudio-2-5-chat","api_url":"https://docs.empiriolabs.ai/models/stepaudio-2-5-chat","logo":"https://media.empiriolabs.ai/model-logos/stepaudio-2-5-chat.png","status":"available"},{"id":"stepaudio-2-5-tts","object":"model","created":1776729600,"owned_by":"stepfun","display_name":"StepAudio 2.5 TTS","author":"stepfun","provider":"stepfun","description":"Contextual StepFun text-to-speech model with natural-language voice direction and expressive delivery.","modality":"audio","type":"tts","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["text_to_speech","contextual_tts","voice_control","multilingual"],"aliases":["stepaudio-2.5-tts","stepfun/stepaudio-2-5-tts","stepfun/stepaudio-2.5-tts"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-04-21","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Text to synthesize. Maximum 1,000 characters.","required":true,"metadata":{"ui":{"control":"textarea","section":"Input"}},"max":1000},{"name":"voice","label":"Voice","type":"enum","description":"Voice for the generated speech.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Voice"}},"default":"lively-girl","options":["lively-girl","vibrant-youth","soft-spoken-gentleman","magnetic-voiced-male","elegantgentle-female","livelybreezy-female","zixinnansheng"]},{"name":"response_format","label":"Response Format","type":"enum","description":"Output audio format.","required":false,"metadata":{"ui":{"control":"segmented","section":"Output"}},"default":"mp3","options":["mp3","wav","flac","opus","pcm"]},{"name":"speed","label":"Speed","type":"number","description":"Speech speed.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Voice"}},"default":1,"min":0.5,"max":2},{"name":"volume","label":"Volume","type":"number","description":"Output volume.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Voice"}},"default":1,"min":0.1,"max":2},{"name":"sample_rate","label":"Sample Rate","type":"enum","description":"Output sample rate in Hz.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Output"}},"default":24000,"options":["8000","16000","22050","24000"]},{"name":"instruction","label":"Instruction","type":"string","description":"Global emotion or style guidance. Maximum 200 characters.","required":false,"metadata":{"ui":{"control":"textarea","section":"Voice"}},"max":200},{"name":"pronunciation_map","label":"Pronunciation Map","type":"string","description":"Optional pronunciation mapping.","required":false,"metadata":{"ui":{"control":"json","section":"Advanced"}}},{"name":"markdown_filter","label":"Markdown Filter","type":"boolean","description":"Strip Markdown syntax from the input before it is spoken.","required":false,"metadata":{"ui":{"control":"toggle","section":"Advanced"}},"default":false}],"supported_endpoints":["POST /v1/audio/speech","POST /v1/audio/speech:stream"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per 10,000 characters","label":"Synthesis","value":"$0.85"}],"unit_pricing":[{"unit":"10k_characters","usd":"0.85","label":"Synthesis"}],"limits":{"note":"Maximum input is 1,000 characters. Content in parentheses is treated as direction and is not spoken. Use instruction for global emotion or style guidance. StepAudio 2.5 TTS does not support voice_label."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=stepaudio-2-5-tts","api_url":"https://docs.empiriolabs.ai/models/stepaudio-2-5-tts","logo":"https://media.empiriolabs.ai/model-logos/stepaudio-2-5-tts.png","status":"available"},{"id":"stepaudio-2-5-asr","object":"model","created":1776988800,"owned_by":"stepfun","display_name":"StepAudio 2.5 ASR","author":"stepfun","provider":"stepfun","description":"StepFun streaming speech recognition model for Chinese and English audio transcription.","modality":"audio","type":"stt","category":"transcription","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio"],"output_modalities":["text"],"features":["transcription","speech_to_text","streaming_asr","timestamps"],"aliases":["stepaudio-2.5-asr","stepfun/stepaudio-2-5-asr","stepfun/stepaudio-2.5-asr"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-04-24","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"file","label":"File","type":"string","description":"Audio file upload for transcription.","required":false,"metadata":{"ui":{"accept":"audio/*","control":"file","section":"Input"}}},{"name":"file_url","label":"File URL","type":"string","description":"Public URL to an audio file.","required":false,"metadata":{"ui":{"control":"text_field","section":"Input"}}},{"name":"audio_base64","label":"Audio Base64","type":"string","description":"Base64 audio payload for JSON requests.","required":false,"metadata":{"ui":{"hidden":true}}},{"name":"language","label":"Language","type":"enum","description":"Recognition language.","required":false,"metadata":{"ui":{"control":"segmented","section":"Recognition"}},"default":"en","options":["en","zh"]},{"name":"hotwords","label":"Hotwords","type":"string","description":"Optional hotword list.","required":false,"metadata":{"ui":{"control":"tags","section":"Recognition"}}},{"name":"enable_itn","label":"Enable ITN","type":"boolean","description":"Enable inverse text normalization, which writes numbers, dates, and currency in their written form.","required":false,"metadata":{"ui":{"control":"toggle","section":"Recognition"}},"default":true},{"name":"format","label":"Format","type":"enum","description":"Audio container format. When omitted, it is detected from the uploaded file.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Format"}},"options":["wav","mp3","ogg","pcm"]},{"name":"codec","label":"Codec","type":"string","description":"PCM codec such as pcm_s16le.","required":false,"metadata":{"ui":{"control":"text_field","section":"Format"}}},{"name":"rate","label":"Sample Rate","type":"number","description":"PCM sample rate in Hz.","required":false,"metadata":{"ui":{"control":"number","section":"Format"}},"default":16000,"min":8000,"max":48000},{"name":"bits","label":"Bits","type":"number","description":"PCM bit depth.","required":false,"metadata":{"ui":{"control":"number","section":"Format"}},"default":16,"min":8,"max":32},{"name":"channel","label":"Channels","type":"number","description":"PCM channel count.","required":false,"metadata":{"ui":{"control":"number","section":"Format"}},"default":1,"min":1,"max":8}],"supported_endpoints":["POST /v1/audio/transcriptions"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per hour of audio","label":"Transcription","value":"$0.05"}],"unit_pricing":[{"unit":"hour","usd":"0.05","label":"Transcription"}],"limits":{"note":"Supports wav, mp3, ogg, and pcm input. PCM requests should include codec, sample rate, bit depth, and channel count. Recognition language supports Chinese and English. Timestamp output is available through enable_timestamp."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=stepaudio-2-5-asr","api_url":"https://docs.empiriolabs.ai/models/stepaudio-2-5-asr","logo":"https://media.empiriolabs.ai/model-logos/stepaudio-2-5-asr.png","status":"available"},{"id":"seed-2-1-turbo","object":"model","created":1783900800,"owned_by":"bytedance","display_name":"Seed 2.1 Turbo","author":"bytedance","provider":"bytedance","description":"Next-generation coding and agent model with engineering-grade code delivery, long-horizon autonomy, and multimodal understanding.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","vision","agentic_coding","function_calling"],"aliases":["bytedance/seed-2-1-turbo","dola-seed-2.1-turbo","dola-seed-2-1-turbo-260628"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":229093,"context_length":229093,"max_output_tokens":65536,"model_released_at":"2026-07-13","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"max_tokens","type":"number","description":"Maximum output tokens. When omitted, the model's own default applies.","required":false,"metadata":{},"min":1,"max":65536},{"name":"frequency_penalty","label":"frequency_penalty","type":"number","description":"Penalty for repeated tokens. >0 reduces repetition, <0 encourages it. Not applied when web search is on or a document is attached.","required":false,"metadata":{},"default":0,"min":-2,"max":2},{"name":"presence_penalty","label":"presence_penalty","type":"number","description":"Penalty for new vs. seen tokens. >0 encourages new topics, <0 encourages staying on topic. Not applied when web search is on or a document is attached.","required":false,"metadata":{},"default":0,"min":-2,"max":2},{"name":"stop","label":"stop","type":"string","description":"Comma-separated stop sequences","required":false,"metadata":{"control":"stop-sequences"}},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable deep thinking / reasoning mode.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"reasoning_effort","type":"enum","description":"Reasoning effort tier. Use enable_thinking=false to disable reasoning entirely.","required":false,"metadata":{"visible_when":{"op":"eq","field":"enable_thinking","value":true},"clear_when_hidden":true},"default":"high","options":["low","medium","high"]},{"name":"enable_web_search","label":"Web Search","type":"boolean","description":"Enable web search: retrieves live web results and provides them to the model as additional context.","required":false,"metadata":{},"default":false},{"name":"max_tool_calls","label":"Max Web Searches","type":"number","description":"Max number of web search rounds the model can run in one request.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"visible_when":{"op":"eq","field":"enable_web_search","value":true},"clear_when_hidden":true},"default":3,"min":1,"max":10},{"name":"image_detail","label":"image_detail","type":"enum","description":"Image visual quality tier for vision input.","required":false,"metadata":{},"default":"high","options":["low","high","xhigh"]},{"name":"video_fps","label":"video_fps","type":"number","description":"Frames per second extracted from video input.","required":false,"metadata":{},"min":0.2,"max":5},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/seed-2-1-turbo:generateContent"],"pricing":{"prompt":"0.00000063","completion":"0.00000313","image":"0","request":"0","input_cache_read":"0.00000063"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.63"},{"spec":"per 1M generated tokens","label":"Output","value":"$3.13"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.63","label":"Input"},{"unit":"1m_tokens","usd":"3.13","label":"Output"}],"limits":{"note":"Per-token pricing is flat across the full context window, with no higher rate above 128K. Reasoning is on by default; set enable_thinking to false to answer directly without it."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=seed-2-1-turbo","api_url":"https://docs.empiriolabs.ai/models/seed-2-1-turbo","logo":"https://media.empiriolabs.ai/model-logos/seed-2-1-turbo.png","status":"available"},{"id":"qwen-audio-3-0-tts","object":"model","created":1784505600,"owned_by":"alibaba","display_name":"Qwen Audio 3.0 TTS","author":"alibaba","provider":"alibaba","description":"Tiered speech synthesis with over 1,000 voices, 16 languages, 20 Chinese dialects, natural-language delivery direction, and inline emotion tags.","modality":"audio","type":"tts","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["text_to_speech","multilingual","expressive_prosody","emotion_control","voice_tags","dialect","low_latency","voice_cloning"],"aliases":["qwen-audio-3.0-tts","alibaba/qwen-audio-3-0-tts","qwen-audio-3.0-tts-plus","qwen-audio-3.0-tts-flash"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-07-20","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Text to synthesize. Up to 20,000 characters per request. Supports inline expression tags placed directly in the text, for example [excited], [laughing], [whispers], [sighing], [gasp], and [sarcastic].","required":true,"metadata":{"ui":{"control":"textarea","section":"Input"}},"max":20000},{"name":"model_tier","label":"Model Tier","type":"enum","description":"plus: highest audio quality and expressiveness, best for content creation, audiobooks, dubbing, and brand voice work. flash: tuned for real-time interaction with lower first-packet latency, best for voice assistants and live agents. Each tier is billed at its own rate.","required":false,"metadata":{"ui":{"control":"segmented","section":"Tier"}},"default":"plus","options":["plus","flash"]},{"name":"voice","label":"Voice","type":"enum","description":"Voice preset. The base voices work on BOTH tiers, so changing model_tier keeps your selection. Six flagship voices are tier locked: longanlingxin and longanlufeng on Plus, and longanhuan_v3.6, longjielidou_v3.6, loongeva_v3.6, loongjohn on Flash. For the full 1,026 voice catalog use voice_id. custom clones a voice from voice_audio_url, and the response's voice_id then works here or in voice_id for 7 days on the same model_tier. GET /v1/voices lists your custom voices with their ids.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Voice"},"variants":[{"when":{"field":"model_tier","equals":"plus"},"allowed_values":["loongjameszhao","loongolivialin","loonglunawang","loongnorahu","loongivyhu","loongryanma","loongsebastianzhou","loongtheoyang","loongadriangao","loongjacksun","longcanzhuyue","longlanghongmo","longmohuiling","longlanqinluan","longyiyusong","longjufuhe","longchuanyunling","longlanlianlan","longxianzhenghe","longluliuche","longrongtaolian","longbaikehui","longjiquexue","longluxiaohui","longanlingxin","longanlufeng","custom"]},{"when":{"field":"model_tier","equals":"flash"},"allowed_values":["loongjameszhao","loongolivialin","loonglunawang","loongnorahu","loongivyhu","loongryanma","loongsebastianzhou","loongtheoyang","loongadriangao","loongjacksun","longcanzhuyue","longlanghongmo","longmohuiling","longlanqinluan","longyiyusong","longjufuhe","longchuanyunling","longlanlianlan","longxianzhenghe","longluliuche","longrongtaolian","longbaikehui","longjiquexue","longluxiaohui","longanhuan_v3.6","longjielidou_v3.6","loongeva_v3.6","loongjohn","custom"]}],"saved_voices":true,"option_labels":{"custom":"Custom","loongjohn":"John (English, Male) - flagship","longjufuhe":"Ju Fu He (Chinese, Female)","loongivyhu":"Ivy Hu (English, Female)","loongnorahu":"Nora Hu (English, Female)","loongryanma":"Ryan Ma (English, Male)","longanlufeng":"An Lu Feng (Chinese + English, Male) - flagship","longbaikehui":"Bai Ke Hui (Chinese, Male)","longjiquexue":"Ji Que Xue (Chinese, Male)","longluliuche":"Lu Liu Che (Chinese, Male)","longyiyusong":"Yi Yu Song (Chinese, Female)","loongjacksun":"Jack Sun (English, Male)","longanlingxin":"An Ling Xin (Chinese + English, Female) - flagship","longcanzhuyue":"Can Zhu Yue (Chinese, Female)","longluxiaohui":"Lu Xiao Hui (Chinese, Male)","longmohuiling":"Mo Hui Ling (Chinese, Female)","loongeva_v3.6":"Eva (English, Female) - flagship","loonglunawang":"Luna Wang (English, Female)","loongtheoyang":"Theo Yang (English, Male)","longlanghongmo":"Lang Hong Mo (Chinese, Female)","longlanlianlan":"Lan Lian Lan (Chinese, Female)","longlanqinluan":"Lan Qin Luan (Chinese, Female)","loongadriangao":"Adrian Gao (English, Male)","loongjameszhao":"James Zhao (English, Male)","loongolivialin":"Olivia Lin (English, Female)","longanhuan_v3.6":"An Huan (Chinese + English, Female) - flagship","longrongtaolian":"Rong Tao Lian (Chinese, Male)","longxianzhenghe":"Xian Zheng He (Chinese, Female)","longchuanyunling":"Chuan Yun Ling (Chinese, Female)","longjielidou_v3.6":"Jie Li Dou (Chinese + English, Male, child) - flagship","loongsebastianzhou":"Sebastian Zhou (English, Male)"}},"default":"loongjameszhao","options":["loongjameszhao","loongolivialin","loonglunawang","loongnorahu","loongivyhu","loongryanma","loongsebastianzhou","loongtheoyang","loongadriangao","loongjacksun","longcanzhuyue","longlanghongmo","longmohuiling","longlanqinluan","longyiyusong","longjufuhe","longchuanyunling","longlanlianlan","longxianzhenghe","longluliuche","longrongtaolian","longbaikehui","longjiquexue","longluxiaohui","longanlingxin","longanlufeng","longanhuan_v3.6","longjielidou_v3.6","loongeva_v3.6","loongjohn","custom"]},{"name":"voice_audio_url","label":"Reference audio URL","type":"string","description":"voice=custom only: an https URL to a 10 to 20 second recording of clear speech from one speaker, the voice to clone (WAV, MP3, M4A, OGG, WEBM or FLAC, up to 15 MB). Record it in a quiet room, without music or other voices.","required":false,"metadata":{"control":"audio-clip","max_seconds":20,"min_seconds":10,"visible_when":{"op":"eq","field":"voice","value":"custom"},"required_when":{"op":"eq","field":"voice","value":"custom"},"clear_when_hidden":true}},{"name":"voice_id","label":"Voice ID","type":"string","description":"Free-form voice id, which overrides voice when set. Accepts any base voice from GET /v1/voices, either as the bare id (recommended, works on both tiers) or fully qualified. A fully qualified id is automatically matched to the selected model_tier. The voice_id of a custom voice also works here.","required":false,"metadata":{"ui":{"control":"text_field","section":"Voice","placeholder":"loongolivialin"},"hidden_when":{"op":"eq","field":"voice","value":"custom"},"clear_when_hidden":true}},{"name":"response_format","label":"Response Format","type":"enum","description":"Audio container. mp3 and opus are compressed, wav is uncompressed PCM in a RIFF header, and pcm is headerless raw samples for chunked playback.","required":false,"metadata":{"ui":{"control":"segmented","section":"Output"}},"default":"mp3","options":["mp3","wav","pcm","opus"]},{"name":"sample_rate","label":"Sample Rate","type":"enum","description":"Output sample rate in Hz. 24000 suits speech playback, and 48000 gives broadcast-quality output at a larger file size.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Output"}},"default":24000,"options":["8000","16000","22050","24000","44100","48000"]},{"name":"speed","label":"Speed","type":"number","description":"Speaking rate multiplier. 0.5 is half speed and 2.0 is double speed.","required":false,"metadata":{"ui":{"step":0.05,"control":"slider","section":"Delivery"}},"default":1,"min":0.5,"max":2},{"name":"pitch","label":"Pitch","type":"number","description":"Pitch multiplier. Values below 1.0 lower the voice and values above raise it. Pitch also shifts the pace of the rendered audio, so pair it with speed when you want to keep the original duration.","required":false,"metadata":{"ui":{"step":0.05,"control":"slider","section":"Delivery"}},"default":1,"min":0.5,"max":2},{"name":"volume","label":"Volume","type":"number","description":"Output loudness, where 50 is the reference level.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Delivery"}},"default":50,"min":0,"max":100},{"name":"instruction","label":"Instruction","type":"string","description":"Natural-language direction for delivery, up to 128 characters. Controls emotion, tone, character, pace, and speaking style, for example 'Speak quickly in an excited, upbeat tone' or 'Read slowly like a late-night radio host'.","required":false,"metadata":{"ui":{"control":"textarea","section":"Delivery","placeholder":"Speak quickly in an excited, upbeat tone"}},"max":128},{"name":"language_hints","label":"Language Hints","type":"string","description":"Language codes that bias pronunciation for mixed-language text, for example [\"zh\", \"en\"]. Leave unset to let the model detect the language.","required":false,"metadata":{"ui":{"control":"json","section":"Delivery"}}},{"name":"seed","label":"Seed","type":"number","description":"Sampling seed. Reuse a seed with identical input and settings for a repeatable render.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced"}},"default":0,"min":0,"max":65535},{"name":"bit_rate","label":"Bit Rate","type":"number","description":"Encoder bitrate in bps. Applies to the opus format only, and is ignored for mp3, wav, and pcm.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced"}},"default":32000,"min":16000,"max":64000},{"name":"pronunciation","label":"Pronunciation","type":"string","description":"Pronunciation overrides keyed by the written form, for example {\"重要\": \"zhong4 yao4\"}. Use it to fix names, acronyms, and homographs.","required":false,"metadata":{"ui":{"control":"json","section":"Advanced"}}},{"name":"replace","label":"Replace","type":"string","description":"Literal text substitutions applied before synthesis, for example {\"EmpirioLabs\": \"Empirio Labs\"}. Useful for brand names and abbreviations.","required":false,"metadata":{"ui":{"control":"json","section":"Advanced"}}},{"name":"enable_markdown_filter","label":"Markdown Filter","type":"boolean","description":"Strip Markdown syntax such as asterisks and underscores before synthesis so formatting characters are not read aloud.","required":false,"metadata":{"ui":{"control":"toggle","section":"Advanced"}},"default":false}],"supported_endpoints":["POST /v1/audio/speech","POST /v1/audio/speech:stream","GET /v1/voices"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per 10,000 characters","label":"Plus synthesis","value":"$0.20"},{"spec":"per 10,000 characters","label":"Flash synthesis","value":"$0.15"}],"unit_pricing":[{"unit":"10k_characters","usd":"0.2","label":"Plus synthesis"},{"unit":"10k_characters","usd":"0.15","label":"Flash synthesis"}],"limits":{"note":"**Tiers**\n\n- Plus: highest audio quality and expressiveness, for content creation, audiobooks, dubbing, and brand voice work\n- Flash: tuned for real-time interaction with lower first-packet latency, for voice assistants and live agents\n- Switch with the `model_tier` parameter, or send `qwen-audio-3.0-tts-plus` or `qwen-audio-3.0-tts-flash` as the model id\n\n**Voices**\n\n- Over 1,000 base voices, all available on both tiers, so changing tier keeps your selected voice\n- Six flagship system voices are tier specific: `longanlingxin` and `longanlufeng` on Plus, and `longanhuan_v3.6`, `longjielidou_v3.6`, `loongeva_v3.6`, `loongjohn` on Flash\n- Browse the full catalog with `GET /v1/voices`, and pass any voice through `voice_id`\n\n**Custom voices**\n\n- Set `voice` to `custom` and pass `voice_audio_url`, an https URL to 10 to 20 seconds of clear speech from one speaker.\n- WAV, MP3, M4A, OGG, WEBM and FLAC are accepted, up to 15 MB. Record in a quiet room, without music or other voices.\n- The voice is made for the selected `model_tier`. The response includes `voice_id` and `voice_id_expires_at`: pass the `voice_id` as `voice` or `voice_id`, with the same `model_tier`, to reuse the voice for 7 days. Only the account that created it can use it.\n- Each account can hold 10 custom voices on this model at a time.\n- `GET /v1/voices?model=qwen-audio-3-0-tts` lists the model's voices, including your custom voices with their ids. Add `type=custom` to list custom voices alone.\n- `DELETE /v1/voices/{voice_id}?model=qwen-audio-3-0-tts` deletes a custom voice, which frees its place at once.\n- In the Playground, set Voice to Custom to use a saved voice again, copy its id, or delete it.\n- Creating, listing and deleting custom voices adds no charge.\n\n**Input limits**\n\n- Up to 20,000 characters per request\n- `instruction` accepts up to 128 characters\n- SSML input is not supported. Use `instruction` for delivery direction, and inline tags such as `[excited]` or `[whispers]` inside the text\n\n**Billing**\n\n- Billed per character of input text at the selected tier's rate"},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen-audio-3-0-tts","api_url":"https://docs.empiriolabs.ai/models/qwen-audio-3-0-tts","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"minimax-h3","object":"model","created":1785456000,"owned_by":"minimax","display_name":"MiniMax H3","author":"minimax","provider":"minimax","description":"Generates 4 to 15 second clips at up to 2K with native stereo audio, following text, image, video, and audio references in one request.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image","audio"],"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"features":["video_generation","image_to_video","audio_out","audio_in","multimodal"],"aliases":["minimax/minimax-h3","hailuo-3","minimax/hailuo-3"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-07-31","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description, up to 7000 characters. Can describe action, camera work, dialogue, sound effects, and on-screen text.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"auto: detect from the inputs. t2v: text-to-video. i2v: animate one image as the opening frame. flf: transition from a first frame to a last frame. r2v: reference-to-video from images, videos, and audio. regenerate: re-render a 768p clip from this model at 2K.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v","flf","r2v","regenerate"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution. 2K is billed at a higher per-second rate than 768p.","required":false,"metadata":{},"default":"768p","options":["768p","2k"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio. Adaptive follows the supplied input media.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"adaptive","options":["adaptive","21:9","16:9","4:3","1:1","3:4","9:16"]},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds, whole numbers only.","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":6,"min":4,"max":15},{"name":"image","label":"Image","type":"string","description":"Image URL. One opening frame for image-to-video, or up to 9 reference images for reference-to-video.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"last_frame","label":"Last Frame","type":"string","description":"Closing frame image URL. Supplying it selects first and last frame mode.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"video","label":"Video","type":"string","description":"Reference video URL, up to 3 clips of 2 to 15 seconds each. Reference video is billed for its own duration in addition to the generated clip.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"audio","label":"Audio","type":"string","description":"Reference audio URL, up to 3 clips of 2 to 15 seconds each. Requires an accompanying reference image or video.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"base_video","label":"Base Video","type":"string","description":"A 768p clip previously generated by this model, to re-render at 2K. Supplying it selects regeneration, which is billed at its own lower per-second rate on the source clip and the output.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"watermark","label":"Watermark","type":"boolean","description":"Add the AI-generated content watermark to the output.","required":false,"metadata":{},"default":false},{"name":"enhance_prompt","label":"Enhance Prompt","type":"boolean","description":"Expand your brief into a full prompt before rendering, adding shot structure, camera work and a soundscape. Any reference media you attach informs the expansion. Adds a per-token charge on top of the per-second video cost. Not used by regenerate.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"0.0000018","completion":"0.0000072","image":"0","request":"0","input_cache_read":"0.0000018"},"pricing_rows":[{"spec":"per second","label":"768p","value":"$0.18"},{"spec":"per second","label":"2K","value":"$0.26"},{"spec":"per second","label":"2K regeneration","value":"$0.10"},{"spec":"per input image after the first 5","label":"Reference image input","value":"$0.08"},{"spec":"per 1M prompt tokens","label":"Prompt expansion input","value":"$1.80"},{"spec":"per 1M generated tokens","label":"Prompt expansion output","value":"$7.20"}],"unit_pricing":[{"unit":"second","usd":"0.18","label":"768p"},{"unit":"second","usd":"0.26","label":"2K"},{"unit":"second","usd":"0.1","label":"2K regeneration"},{"unit":"1m_tokens","usd":"1.8","label":"Prompt expansion input"},{"unit":"1m_tokens","usd":"7.2","label":"Prompt expansion output"}],"limits":{"note":"MiniMax H3 generates 4 to 15 second clips at 24 fps in 768p or 2K, each with a native stereo audio track.\n\n**Modes**\n\n- Text to video: prompt only.\n- Image to video: one image becomes the opening frame.\n- First and last frame: supply an opening and a closing image.\n- Reference to video: up to 9 images, 3 videos and 3 audio clips, 12 reference files in total.\n- Regeneration: re-render a 768p clip you generated earlier at 2K. Send the original prompt plus the source clip as base_video.\n\n**Prompt expansion**\n\nSet `enhance_prompt` to true and the model first rewrites your brief into a full prompt, adding shot-by-shot structure, camera moves, lighting and a soundscape, then renders from that. Any reference media you attach informs the expansion. It adds a per-token charge on top of the per-second video cost, and is skipped for regeneration because that path reproduces the original request.\n\n**Reference media**\n\n- Images 256 to 5760 px per side, aspect ratio between 0.4 and 2.5, up to 30 MB each.\n- Videos 2 to 15 seconds, H.264 or H.265, up to 50 MB each.\n- Audio 2 to 15 seconds, WAV or MP3, up to 15 MB each. Reference audio requires an accompanying image or video reference.\n- Reference video and audio apply to reference-to-video only.\n- Prompts can be up to 7000 characters and may describe dialogue, sound effects, on-screen text, and camera work.\n\n**Billing**\n\n- Billed per second of the generated clip at the resolution you request.\n- A reference video is billed for its own duration in addition to the generated clip, so a 5 second reference used to make a 6 second clip bills 11 seconds.\n- Regeneration is billed at its own lower per-second rate, on the source clip duration plus the regenerated output. Reference images carried over from the original request are not charged again.\n- The first 5 reference images are included. Each additional reference image is charged separately.\n- Prompt expansion, when enabled, is billed per token."},"notes":"MiniMax H3 generates 4 to 15 second clips at 24 fps in 768p or 2K, each with a native stereo audio track.\n\n**Modes**\n\n- Text to video: prompt only.\n- Image to video: one image becomes the opening frame.\n- First and last frame: supply an opening and a closing image.\n- Reference to video: up to 9 images, 3 videos and 3 audio clips, 12 reference files in total.\n- Regeneration: re-render a 768p clip you generated earlier at 2K. Send the original prompt plus the source clip as base_video.\n\n**Prompt expansion**\n\nSet `enhance_prompt` to true and the model first rewrites your brief into a full prompt, adding shot-by-shot structure, camera moves, lighting and a soundscape, then renders from that. Any reference media you attach informs the expansion. It adds a per-token charge on top of the per-second video cost, and is skipped for regeneration because that path reproduces the original request.\n\n**Reference media**\n\n- Images 256 to 5760 px per side, aspect ratio between 0.4 and 2.5, up to 30 MB each.\n- Videos 2 to 15 seconds, H.264 or H.265, up to 50 MB each.\n- Audio 2 to 15 seconds, WAV or MP3, up to 15 MB each. Reference audio requires an accompanying image or video reference.\n- Reference video and audio apply to reference-to-video only.\n- Prompts can be up to 7000 characters and may describe dialogue, sound effects, on-screen text, and camera work.\n\n**Billing**\n\n- Billed per second of the generated clip at the resolution you request.\n- A reference video is billed for its own duration in addition to the generated clip, so a 5 second reference used to make a 6 second clip bills 11 seconds.\n- Regeneration is billed at its own lower per-second rate, on the source clip duration plus the regenerated output. Reference images carried over from the original request are not charged again.\n- The first 5 reference images are included. Each additional reference image is charged separately.\n- Prompt expansion, when enabled, is billed per token.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=minimax-h3","api_url":"https://docs.empiriolabs.ai/models/minimax-h3","logo":"https://media.empiriolabs.ai/model-logos/minimax.png","status":"available"},{"id":"gpt-image-2","object":"model","created":1776729600,"owned_by":"openai","display_name":"GPT Image 2","author":"openai","provider":"openai","description":"OpenAI's flagship image model with strong prompt fidelity, crisp text rendering, and instruction-based editing across up to 16 reference images.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text","image"],"output_modalities":["image"],"features":["image_generation","image_editing","text_rendering","multi_image"],"aliases":["openai/gpt-image-2"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-04-21","deprecation_date":"2027-02-09","deprecated":true,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Text prompt. With input images attached, becomes an editing or compositing instruction.","required":true,"metadata":{}},{"name":"quality","label":"Quality","type":"enum","description":"Rendering quality tier. Higher tiers produce more detail and cost more per image.","required":false,"metadata":{},"default":"medium","options":["low","medium","high"]},{"name":"size","label":"Size","type":"enum","description":"Output resolution: square, landscape, or portrait.","required":false,"metadata":{},"default":"1024x1024","options":["1024x1024","1536x1024","1024x1536"]},{"name":"image","label":"Image","type":"string","description":"Up to 16 input image URLs for editing or multi-reference composition.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"num_images","label":"Num Images","type":"number","description":"Number of images to generate. Each is billed separately.","required":false,"metadata":{},"default":1,"min":1,"max":4},{"name":"moderation","label":"Moderation","type":"enum","description":"Content filtering strictness applied by the model service.","required":false,"metadata":{},"default":"auto","options":["auto","low"]},{"name":"response_format","label":"Response Format","type":"enum","description":"Return signed URLs or base64 image data.","required":false,"metadata":{},"default":"url","options":["url","b64_json"]}],"supported_endpoints":["POST /v1/images/generations"],"pricing":{"prompt":"0","completion":"0","image":"0.012","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Low","value":"$0.012"},{"spec":"per image","label":"Medium","value":"$0.106"},{"spec":"per image","label":"High","value":"$0.422"}],"unit_pricing":[{"unit":"image","usd":"0.012","label":"Low"},{"unit":"image","usd":"0.106","label":"Medium"},{"unit":"image","usd":"0.422","label":"High"}],"limits":{"note":"Quality tiers Low, Medium, and High set the rendering fidelity and the per-image price. Output sizes are 1024x1024, 1536x1024, and 1024x1536. Attach up to 16 images to edit or composite them, with the prompt as the instruction.\n\n**Content safety**\n\n- Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=gpt-image-2","api_url":"https://docs.empiriolabs.ai/models/gpt-image-2","logo":"https://media.empiriolabs.ai/model-logos/gpt-image-2.png","status":"available"},{"id":"kling-v3","object":"model","created":1770249600,"owned_by":"kling","display_name":"Kling V3","author":"kling","provider":"kling","description":"Kuaishou's Kling 3.0 video generator with text-to-video, first and last frame image-to-video, native audio, and 720p, 1080p, or 4K output.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image"],"output_modalities":["video"],"features":["text_to_video","image_to_video","audio","video_generation"],"aliases":["kling/kling-v3"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-02-05","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Text prompt describing the video (text-to-video) or the motion to apply to the source image (image-to-video).","required":true,"metadata":{}},{"name":"model_tier","label":"Model Tier","type":"enum","description":"standard: 720p, fastest. pro: 1080p, higher fidelity. 4k: 3840x2160, highest fidelity and cost.","required":false,"metadata":{},"default":"standard","options":["standard","pro","4k"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Aspect ratio for text-to-video. Image-to-video follows the source image.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"16:9","options":["16:9","9:16","1:1"]},{"name":"duration","label":"Duration","type":"number","description":"Video length in seconds (3 to 15).","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":5,"min":3,"max":15},{"name":"sound","label":"Sound","type":"boolean","description":"Generate native audio with the video. Standard and pro bill a higher rate with sound on; 4k includes audio.","required":false,"metadata":{},"default":true},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid in the output.","required":false,"metadata":{},"default":""},{"name":"image","label":"Image","type":"string","description":"Source image URL for image-to-video. One image animates from that frame; two set the first and last frame.","required":false,"metadata":{"ui":{"hide_in_playground":true}}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"Standard T2V/I2V","value":"$0.168"},{"spec":"per second","label":"Standard T2V/I2V Sound","value":"$0.252"},{"spec":"per second","label":"Pro T2V/I2V","value":"$0.224"},{"spec":"per second","label":"Pro T2V/I2V Sound","value":"$0.336"},{"spec":"per second","label":"4K T2V/I2V","value":"$0.84"}],"unit_pricing":[{"unit":"second","usd":"0.168","label":"Standard T2V/I2V"},{"unit":"second","usd":"0.252","label":"Standard T2V/I2V Sound"},{"unit":"second","usd":"0.224","label":"Pro T2V/I2V"},{"unit":"second","usd":"0.336","label":"Pro T2V/I2V Sound"},{"unit":"second","usd":"0.84","label":"4K T2V/I2V"}],"limits":{"note":"Model tiers: standard renders 720p, pro renders 1080p, 4k renders 3840x2160. Durations run 3 to 15 seconds. Native audio is on by default; turning Sound off bills the lower rate on standard and pro, while 4K includes audio at one flat rate. Image-to-video accepts one or two images (first and last frame) and follows the source image size."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=kling-v3","api_url":"https://docs.empiriolabs.ai/models/kling-v3","logo":"https://media.empiriolabs.ai/model-logos/kling-v3.png","status":"available"},{"id":"wan-2-5","object":"model","created":1758672000,"owned_by":"alibaba","display_name":"Wan 2.5","author":"alibaba","provider":"alibaba","description":"Alibaba's Wan 2.5 video model with text-to-video and image-to-video, native audio, optional custom audio tracks, and 480p to 1080p output.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image"],"output_modalities":["video"],"features":["text_to_video","image_to_video","audio"],"aliases":["alibaba/wan-2.5","wan2.5"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-09-24","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"Auto detects from attachments. t2v: text-to-video. i2v: animate one image.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution.","required":false,"metadata":{},"default":"1080p","options":["480p","720p","1080p"]},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds: 5 or 10.","required":false,"metadata":{"ui":{"step":5,"control":"slider"}},"default":5,"min":5,"max":10},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Used for text-to-video; image-to-video follows the source image. 480p supports 16:9, 9:16, and 1:1 only.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"16:9","options":["16:9","9:16","1:1","4:3","3:4"]},{"name":"image","label":"Image","type":"string","description":"Source image URL for i2v.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"audio_url","label":"Audio URL","type":"string","description":"Optional custom audio track URL (WAV or MP3, about 3 to 30 seconds). Without it the model generates native audio.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid.","required":false,"metadata":{},"default":""},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed.","required":false,"metadata":{}},{"name":"prompt_extend","label":"Prompt Extend","type":"boolean","description":"Let the service rewrite the prompt for better results.","required":false,"metadata":{},"default":true},{"name":"watermark","label":"Watermark","type":"boolean","description":"Add a provenance watermark to the output.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"480P","value":"$0.05"},{"spec":"per second","label":"720P","value":"$0.10"},{"spec":"per second","label":"1080P","value":"$0.15"}],"unit_pricing":[{"unit":"second","usd":"0.05","label":"480P"},{"unit":"second","usd":"0.1","label":"720P"},{"unit":"second","usd":"0.15","label":"1080P"}],"limits":{"note":"Modes: text-to-video and image-to-video with native audio, or supply audio_url for a custom track (WAV or MP3, about 3 to 30 seconds). Durations are 5 or 10 seconds. 480p output supports 16:9, 9:16, and 1:1."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=wan-2-5","api_url":"https://docs.empiriolabs.ai/models/wan-2-5","logo":"https://media.empiriolabs.ai/model-logos/wan.png","status":"available"},{"id":"wan-2-2","object":"model","created":1753660800,"owned_by":"alibaba","display_name":"Wan 2.2","author":"alibaba","provider":"alibaba","description":"Alibaba's Wan 2.2 video family with standard and flash tiers, first and last frame interpolation, and 480p to 1080p output at low cost.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image"],"output_modalities":["video"],"features":["text_to_video","image_to_video"],"aliases":["alibaba/wan-2.2","wan2.2"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-07-28","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"Auto detects from attachments. t2v: text-to-video. i2v: animate one image. kf2v: interpolate between a first and last frame (two images).","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v","kf2v"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Standard text-to-video and image-to-video: 480p or 1080p (default 1080p). Flash image-to-video: 480p or 720p (default 720p). First-last frame: 480p, 720p or 1080p (default 720p). Mode auto: 480p or 1080p, or 480p with flash_mode on.","required":false,"metadata":{"variants":[{"when":{"op":"eq","field":"mode","value":"t2v"},"default":"1080p","allowed_values":["480p","1080p"]},{"when":[{"op":"eq","field":"mode","value":"i2v"},{"op":"falsy","field":"flash_mode"}],"default":"1080p","allowed_values":["480p","1080p"]},{"when":[{"op":"eq","field":"mode","value":"i2v"},{"op":"truthy","field":"flash_mode"}],"default":"720p","allowed_values":["480p","720p"]},{"when":{"op":"eq","field":"mode","value":"kf2v"},"default":"720p","allowed_values":["480p","720p","1080p"]},{"when":[{"op":"eq","field":"mode","value":"auto"},{"op":"falsy","field":"flash_mode"}],"default":"1080p","allowed_values":["480p","1080p"]},{"when":[{"op":"eq","field":"mode","value":"auto"},{"op":"truthy","field":"flash_mode"}],"allowed_values":["480p"]}]},"default":"1080p","options":["480p","720p","1080p"]},{"name":"flash_mode","label":"Flash Mode","type":"boolean","description":"Faster, cheaper i2v at 480p or 720p. Applies to i2v only.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"i2v"},"clear_when_hidden":true},"default":false},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Used for text-to-video; image modes follow the source image. 480p supports 16:9, 9:16, and 1:1 only.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"16:9","options":["16:9","9:16","1:1","4:3","3:4"]},{"name":"image","label":"Image","type":"string","description":"Source image URL. i2v uses one image; kf2v uses two (first and last frame).","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid.","required":false,"metadata":{},"default":""},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed.","required":false,"metadata":{}},{"name":"prompt_extend","label":"Prompt Extend","type":"boolean","description":"Let the service rewrite the prompt for better results.","required":false,"metadata":{},"default":true},{"name":"watermark","label":"Watermark","type":"boolean","description":"Add a provenance watermark to the output.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"Standard 480P","value":"$0.02"},{"spec":"per second","label":"Standard 1080P","value":"$0.10"},{"spec":"per second","label":"Flash 480P","value":"$0.015"},{"spec":"per second","label":"Flash 720P","value":"$0.036"},{"spec":"per second","label":"Flash 1080P","value":"$0.07"}],"unit_pricing":[{"unit":"second","usd":"0.02","label":"Standard 480P"},{"unit":"second","usd":"0.1","label":"Standard 1080P"},{"unit":"second","usd":"0.015","label":"Flash 480P"},{"unit":"second","usd":"0.036","label":"Flash 720P"},{"unit":"second","usd":"0.07","label":"Flash 1080P"}],"limits":{"note":"Clips render 5 seconds without audio. Standard text-to-video and image-to-video output 480p or 1080p. Flash image-to-video outputs 480p or 720p. Two attached images run first and last frame interpolation at Flash rates, up to 1080p."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=wan-2-2","api_url":"https://docs.empiriolabs.ai/models/wan-2-2","logo":"https://media.empiriolabs.ai/model-logos/wan.png","status":"available"},{"id":"wan-2-1","object":"model","created":1740441600,"owned_by":"alibaba","display_name":"Wan 2.1","author":"alibaba","provider":"alibaba","description":"Alibaba's Wan 2.1 video model with turbo and plus tiers for text-to-video, image-to-video, and first and last frame clips at 480p or 720p.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image"],"output_modalities":["video"],"features":["text_to_video","image_to_video"],"aliases":["alibaba/wan-2.1","wan2.1"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-02-25","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"Auto detects from attachments. t2v: text-to-video. i2v: animate one image. kf2v: interpolate between a first and last frame (two images).","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v","kf2v"]},{"name":"model_tier","label":"Model Tier","type":"enum","description":"turbo: faster and cheaper, 480p or 720p. plus: higher fidelity, 720p only. First-last frame runs on plus only. When this is not set, first-last frame runs plus and every other mode runs turbo.","required":false,"metadata":{"variants":[{"when":{"op":"eq","field":"mode","value":"kf2v"},"default":"plus","allowed_values":["plus"]}]},"default":"turbo","options":["turbo","plus"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution. turbo renders 480p or 720p; plus and first-last frame render 720p.","required":false,"metadata":{"variants":[{"when":{"op":"eq","field":"model_tier","value":"plus"},"default":"720p","allowed_values":["720p"]},{"when":{"op":"eq","field":"mode","value":"kf2v"},"default":"720p","allowed_values":["720p"]}]},"default":"720p","options":["480p","720p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Used for text-to-video; image modes follow the source image. 480p supports 16:9, 9:16, and 1:1 only.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"16:9","options":["16:9","9:16","1:1","4:3","3:4"]},{"name":"image","label":"Image","type":"string","description":"Source image URL. i2v uses one image; kf2v uses two (first and last frame).","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"duration","label":"Duration","type":"number","description":"Clip length in whole seconds: 5, or 3 to 5 for image-to-video on turbo (mode i2v).","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"variants":[{"max":5,"min":3,"when":[{"op":"eq","field":"mode","value":"i2v"},{"op":"ne","field":"model_tier","value":"plus"}]}]},"default":5,"min":5,"max":5},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid.","required":false,"metadata":{},"default":""},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed.","required":false,"metadata":{}},{"name":"prompt_extend","label":"Prompt Extend","type":"boolean","description":"Let the service rewrite the prompt for better results.","required":false,"metadata":{},"default":true},{"name":"watermark","label":"Watermark","type":"boolean","description":"Add a provenance watermark to the output.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"Turbo","value":"$0.036"},{"spec":"per second","label":"Plus","value":"$0.10"}],"unit_pricing":[{"unit":"second","usd":"0.036","label":"Turbo"},{"unit":"second","usd":"0.1","label":"Plus"}],"limits":{"note":"Clips render about 5 seconds without audio; turbo image-to-video supports 3 to 5 seconds. Turbo outputs 480p or 720p, plus outputs 720p. Two attached images run first and last frame interpolation on the plus tier."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=wan-2-1","api_url":"https://docs.empiriolabs.ai/models/wan-2-1","logo":"https://media.empiriolabs.ai/model-logos/wan.png","status":"available"},{"id":"wan2-5-image","object":"model","created":1758672000,"owned_by":"alibaba","display_name":"Wan2.5 Image","author":"alibaba","provider":"alibaba","description":"Alibaba's Wan 2.5 image model with text-to-image and multi-reference editing of up to 3 images at about 1.7 megapixels.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text","image"],"output_modalities":["image"],"features":["image_generation","image_editing"],"aliases":["alibaba/wan-2.5-image","wan2.5-image"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-09-24","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Text prompt (up to 2000 characters). With input images attached, becomes the editing instruction.","required":true,"metadata":{}},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"1:1","options":["1:1","16:9","9:16","4:3","3:4","3:2","2:3"]},{"name":"image","label":"Image","type":"string","description":"Up to 3 input image URLs. Triggers editing mode.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"num_images","label":"Num Images","type":"number","description":"Number of images to generate. Each is billed separately.","required":false,"metadata":{},"default":1,"min":1,"max":4},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid in the output.","required":false,"metadata":{},"default":""},{"name":"prompt_extend","label":"Prompt Extend","type":"boolean","description":"Let the service rewrite the prompt for better results.","required":false,"metadata":{},"default":true},{"name":"watermark","label":"Watermark","type":"boolean","description":"Add a provenance watermark to the output.","required":false,"metadata":{},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed. Leave empty for random.","required":false,"metadata":{},"min":0,"max":2147483647},{"name":"response_format","label":"Response Format","type":"enum","description":"Return signed image URLs by default, or include base64 image data when b64_json is requested.","required":false,"metadata":{},"default":"url","options":["url","b64_json"]}],"supported_endpoints":["POST /v1/images/generations"],"pricing":{"prompt":"0","completion":"0","image":"0.03","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Standard","value":"$0.030"}],"unit_pricing":[{"unit":"image","usd":"0.03","label":"Standard"}],"limits":{"note":"Text-to-image renders about 1.7 megapixels at the chosen aspect ratio; attach 1 to 3 images for editing and fusion at about 1 megapixel. Prompts up to 2000 characters.\n\n**Content safety**\n\n- Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=wan2-5-image","api_url":"https://docs.empiriolabs.ai/models/wan2-5-image","logo":"https://media.empiriolabs.ai/model-logos/wan.png","status":"available"},{"id":"wan2-2-image","object":"model","created":1753660800,"owned_by":"alibaba","display_name":"Wan2.2 Image","author":"alibaba","provider":"alibaba","description":"Alibaba's Wan 2.2 text-to-image model with plus and flash tiers and up to 1440x1440 output at low per-image pricing.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text"],"output_modalities":["image"],"features":["image_generation"],"aliases":["alibaba/wan-2.2-image","wan2.2-image"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-07-28","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Text prompt (up to 500 characters).","required":true,"metadata":{}},{"name":"model_tier","label":"Model Tier","type":"enum","description":"plus: higher fidelity. flash: faster and cheaper.","required":false,"metadata":{},"default":"plus","options":["plus","flash"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"1:1","options":["1:1","16:9","9:16","4:3","3:4","3:2","2:3"]},{"name":"num_images","label":"Num Images","type":"number","description":"Number of images to generate. Each is billed separately.","required":false,"metadata":{},"default":1,"min":1,"max":4},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid in the output.","required":false,"metadata":{},"default":""},{"name":"prompt_extend","label":"Prompt Extend","type":"boolean","description":"Let the service rewrite the prompt for better results.","required":false,"metadata":{},"default":true},{"name":"watermark","label":"Watermark","type":"boolean","description":"Add a provenance watermark to the output.","required":false,"metadata":{},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed. Leave empty for random.","required":false,"metadata":{},"min":0,"max":2147483647},{"name":"response_format","label":"Response Format","type":"enum","description":"Return signed image URLs by default, or include base64 image data when b64_json is requested.","required":false,"metadata":{},"default":"url","options":["url","b64_json"]}],"supported_endpoints":["POST /v1/images/generations"],"pricing":{"prompt":"0","completion":"0","image":"0.05","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Plus","value":"$0.05"},{"spec":"per image","label":"Flash","value":"$0.025"}],"unit_pricing":[{"unit":"image","usd":"0.05","label":"Plus"},{"unit":"image","usd":"0.025","label":"Flash"}],"limits":{"note":"Text-to-image only. Plus is the higher-fidelity tier; flash is faster and cheaper. Each aspect ratio has one output size, up to 1280 pixels on the long side (1024x1024 at 1:1), with prompts up to 500 characters.\n\n**Content safety**\n\n- Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=wan2-2-image","api_url":"https://docs.empiriolabs.ai/models/wan2-2-image","logo":"https://media.empiriolabs.ai/model-logos/wan.png","status":"available"},{"id":"wan2-1-image","object":"model","created":1740441600,"owned_by":"alibaba","display_name":"Wan2.1 Image","author":"alibaba","provider":"alibaba","description":"Alibaba's Wan 2.1 text-to-image model with turbo and plus tiers and up to 1440x1440 output at low per-image pricing.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text"],"output_modalities":["image"],"features":["image_generation"],"aliases":["alibaba/wan-2.1-image","wan2.1-image"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-02-25","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Text prompt (up to 500 characters).","required":true,"metadata":{}},{"name":"model_tier","label":"Model Tier","type":"enum","description":"turbo: faster and cheaper. plus: higher fidelity.","required":false,"metadata":{},"default":"turbo","options":["turbo","plus"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"1:1","options":["1:1","16:9","9:16","4:3","3:4","3:2","2:3"]},{"name":"num_images","label":"Num Images","type":"number","description":"Number of images to generate. Each is billed separately.","required":false,"metadata":{},"default":1,"min":1,"max":4},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid in the output.","required":false,"metadata":{},"default":""},{"name":"prompt_extend","label":"Prompt Extend","type":"boolean","description":"Let the service rewrite the prompt for better results.","required":false,"metadata":{},"default":true},{"name":"watermark","label":"Watermark","type":"boolean","description":"Add a provenance watermark to the output.","required":false,"metadata":{},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed. Leave empty for random.","required":false,"metadata":{},"min":0,"max":2147483647},{"name":"response_format","label":"Response Format","type":"enum","description":"Return signed image URLs by default, or include base64 image data when b64_json is requested.","required":false,"metadata":{},"default":"url","options":["url","b64_json"]}],"supported_endpoints":["POST /v1/images/generations"],"pricing":{"prompt":"0","completion":"0","image":"0.025","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Turbo","value":"$0.025"},{"spec":"per image","label":"Plus","value":"$0.05"}],"unit_pricing":[{"unit":"image","usd":"0.025","label":"Turbo"},{"unit":"image","usd":"0.05","label":"Plus"}],"limits":{"note":"Text-to-image only. Turbo is faster and cheaper; plus is the higher-fidelity tier. Each aspect ratio has one output size, up to 1280 pixels on the long side (1024x1024 at 1:1), with prompts up to 500 characters.\n\n**Content safety**\n\n- Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=wan2-1-image","api_url":"https://docs.empiriolabs.ai/models/wan2-1-image","logo":"https://media.empiriolabs.ai/model-logos/wan.png","status":"available"},{"id":"seedance-2-5-flash","object":"model","created":1794441600,"owned_by":"bytedance","display_name":"Seedance 2.5 Flash","author":"bytedance","provider":"bytedance","description":"Faster, lower-cost Seedance 2.5 for coherent clips up to 30 seconds at 480p or 720p, with image, video, and audio references, native audio, editing, and extension.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image","audio"],"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"features":["text_to_video","image_to_video","reference_to_video","video_editing","multimodal","audio_sync","camera_control","character_consistency"],"aliases":["bytedance/seedance-2.5-flash","seedance-2.5-flash"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-11-12","is_new":true,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description. Address a specific attachment inline as @Image1, @Video1, or @Audio1 to say which reference a shot should follow.","required":true,"metadata":{}},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution.","required":false,"metadata":{},"default":"720p","options":["480p","720p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio. adaptive lets the model choose. With a first frame, the video always follows that image's aspect ratio. Editing an attached video keeps that video's aspect ratio and length. Other reference jobs, including ones with a reference video, accept any ratio.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"adaptive","options":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]},{"name":"custom_duration","label":"Custom Duration","type":"boolean","description":"If false, the model decides clip length.","required":false,"metadata":{},"default":true},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds. Only used when custom_duration=true. Video editing always keeps the source clip length, and the clip being edited must be 4 to 30 seconds long.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"visible_when":{"op":"eq","field":"custom_duration","value":true},"clear_when_hidden":true},"default":5,"min":4,"max":30},{"name":"generate_audio","label":"Generate Audio","type":"boolean","description":"Generate native audio with the video.","required":false,"metadata":{},"default":true},{"name":"output_format","label":"Output Format","type":"enum","description":"mp4 plays everywhere. mov carries higher color precision for color grading, keying, and compositing, and some players cannot open it.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"mp4","options":["mp4","mov"]},{"name":"return_last_frame","label":"Return Last Frame","type":"boolean","description":"Also return the final frame as an image, ready to use as the first frame of the next clip.","required":false,"metadata":{},"default":false},{"name":"image","label":"Image","type":"string","description":"First frame image URL. The video starts on this image.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"image_end","label":"Image End","type":"string","description":"Last frame image URL. Send it with image, and the video moves from the first frame to this one.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"reference_images","label":"Reference Images","type":"string","description":"Reference image URLs for characters, objects, scenes or style, as a list. Up to 10 images. Images sent with reference images, a video or audio are all references.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"videos","label":"Videos","type":"string","description":"Reference video URLs, as a list. Up to 5 clips and 30 seconds in all. Say in the prompt whether to edit a clip, continue it, or follow it as a reference.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"audios","label":"Audios","type":"string","description":"Reference audio URLs, as a list. Up to 5 clips. Audio works without any image or video.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid.","required":false,"metadata":{},"default":""},{"name":"seed","label":"Seed","type":"number","description":"Integer seed for reproducible-style output. Same seed gives similar, not identical, results.","required":false,"metadata":{},"min":-1,"max":2147483647}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"T2V/I2V 480P","value":"$0.135"},{"spec":"per second","label":"T2V/I2V 720P","value":"$0.302"},{"spec":"per second of input plus output","label":"Video Input 480P","value":"$0.083"},{"spec":"per second of input plus output","label":"Video Input 720P","value":"$0.186"}],"unit_pricing":[{"unit":"second","usd":"0.135","label":"T2V/I2V 480P"},{"unit":"second","usd":"0.302","label":"T2V/I2V 720P"}],"limits":{"note":"A faster, lower-cost Seedance 2.5 that keeps most of its creative range: one request can produce a coherent clip of up to 30 seconds at 480p or 720p, draw on up to 20 reference assets, and edit or extend existing footage.\n\n**Inputs**\n\n- Text to video from the prompt alone.\n- A first frame as `image`, with an optional last frame as `image_end`.\n- Up to 10 `reference_images`, 5 `videos`, and 5 `audios` in one request. Audio works on its own, and images sent with a video or audio are references.\n- To edit an attached clip or continue it, describe that in your prompt. The model reads the intent from your wording.\n\n**Output**\n\n- 480p and 720p at 24fps, 4 to 30 seconds, with native synchronized audio.\n- MP4 by default. MOV carries higher color precision for grading and compositing, and some players cannot open it.\n- When you supply a first frame, the output follows that image's aspect ratio, so aspect_ratio stays adaptive. Reference jobs, including ones with a reference video, accept any ratio.\n\n**Input limits**\n\n- Images: jpeg, png, webp, bmp, tiff, gif, heic, or heif, 300 to 6000 px per side, under 30 MB each.\n- Videos: MP4 or MOV, 2 to 30 seconds each and 30 seconds in total, under 200 MB each.\n- Audio: WAV or MP3, 2 to 30 seconds each and 30 seconds in total, under 15 MB each.\n- Uploaded images and videos that show a real person's face are blocked. To feature a person, start from an image made with Seedream 5.5. To use your own face, verify it in [My face](https://platform.empiriolabs.ai/dashboard/verified-portrait).\n\n**Billing**\n\n- Without a reference video, you are billed per second of generated video at the rate for the output resolution.\n- With a reference video, the model prices the reference clip's seconds alongside the generated seconds, at the lower video-input rate. Billed seconds are therefore reference duration plus output duration, so a request that includes a reference video costs more in total than the same output generated from text alone.\n- Worked example at 480p: a 4 second clip from a text prompt bills 4 seconds. A 4 second clip generated from a 5 second reference video bills 9 seconds at the video-input rate.\n\n**Uploaded media preprocessing**\n\n- Video inputs are capped to 30 seconds.\n- Uploaded video inputs are normalized to provider-compatible MP4 when needed. Set preprocess_video to false to send a clip through untouched."},"notes":"A faster, lower-cost Seedance 2.5 that keeps most of its creative range: one request can produce a coherent clip of up to 30 seconds at 480p or 720p, draw on up to 20 reference assets, and edit or extend existing footage.\n\n**Inputs**\n\n- Text to video from the prompt alone.\n- A first frame as `image`, with an optional last frame as `image_end`.\n- Up to 10 `reference_images`, 5 `videos`, and 5 `audios` in one request. Audio works on its own, and images sent with a video or audio are references.\n- To edit an attached clip or continue it, describe that in your prompt. The model reads the intent from your wording.\n\n**Output**\n\n- 480p and 720p at 24fps, 4 to 30 seconds, with native synchronized audio.\n- MP4 by default. MOV carries higher color precision for grading and compositing, and some players cannot open it.\n- When you supply a first frame, the output follows that image's aspect ratio, so aspect_ratio stays adaptive. Reference jobs, including ones with a reference video, accept any ratio.\n\n**Input limits**\n\n- Images: jpeg, png, webp, bmp, tiff, gif, heic, or heif, 300 to 6000 px per side, under 30 MB each.\n- Videos: MP4 or MOV, 2 to 30 seconds each and 30 seconds in total, under 200 MB each.\n- Audio: WAV or MP3, 2 to 30 seconds each and 30 seconds in total, under 15 MB each.\n- Uploaded images and videos that show a real person's face are blocked. To feature a person, start from an image made with Seedream 5.5. To use your own face, verify it in [My face](https://platform.empiriolabs.ai/dashboard/verified-portrait).\n\n**Billing**\n\n- Without a reference video, you are billed per second of generated video at the rate for the output resolution.\n- With a reference video, the model prices the reference clip's seconds alongside the generated seconds, at the lower video-input rate. Billed seconds are therefore reference duration plus output duration, so a request that includes a reference video costs more in total than the same output generated from text alone.\n- Worked example at 480p: a 4 second clip from a text prompt bills 4 seconds. A 4 second clip generated from a 5 second reference video bills 9 seconds at the video-input rate.\n\n**Uploaded media preprocessing**\n\n- Video inputs are capped to 30 seconds.\n- Uploaded video inputs are normalized to provider-compatible MP4 when needed. Set preprocess_video to false to send a clip through untouched.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=seedance-2-5-flash","api_url":"https://docs.empiriolabs.ai/models/seedance-2-5-flash","logo":"https://media.empiriolabs.ai/model-logos/seedance-2-5.png","status":"available"},{"id":"seedance-2-5","object":"model","created":1786060800,"owned_by":"bytedance","display_name":"Seedance 2.5","author":"bytedance","provider":"bytedance","description":"Long-form video model for coherent clips up to 30 seconds, with up to 50 reference images, videos, and audio clips, native audio, editing, and extension.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image","audio"],"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"features":["text_to_video","image_to_video","reference_to_video","video_editing","multimodal","audio_sync","camera_control","character_consistency","draft_mode"],"aliases":["bytedance/seedance-2.5","seedance-2.5"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-08-07","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description. Address a specific attachment inline as @Image1, @Video1, or @Audio1 to say which reference a shot should follow.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"Selects how your inputs are used. auto detects it from what you attach. t2v is text to video. i2v_first animates a first frame. i2v_both animates between a first and a last frame. reference builds from up to 30 images, 10 videos and 10 audio clips. To edit or continue an attached clip, say so in the prompt.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v_first","i2v_both","reference"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution. 4K is 3840x2160 at 16:9 and is encoded as 10-bit H.265/HEVC, which some players cannot open. Draft mode always renders at 480p, so this is ignored on a draft. A draft's final renders at 1080p, or at 4K when this is 4k.","required":false,"metadata":{"hidden_when":{"op":"eq","field":"draft","value":true},"clear_when_hidden":true,"value_when_hidden":"480p"},"default":"720p","options":["480p","720p","1080p","4k"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio. adaptive lets the model choose. With a first frame, the video always follows that image's aspect ratio. Editing an attached video keeps that video's aspect ratio and length. Other reference jobs, including ones with a reference video, accept any ratio.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"adaptive","options":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]},{"name":"custom_duration","label":"Custom Duration","type":"boolean","description":"If false, the model decides clip length.","required":false,"metadata":{},"default":true},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds. Only used when custom_duration=true. Video editing always keeps the source clip length, and the clip being edited must be 4 to 30 seconds long.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"visible_when":{"op":"eq","field":"custom_duration","value":true},"clear_when_hidden":true},"default":5,"min":4,"max":30},{"name":"generate_audio","label":"Generate Audio","type":"boolean","description":"Generate native audio with the video.","required":false,"metadata":{},"default":true},{"name":"output_format","label":"Output Format","type":"enum","description":"mp4 plays everywhere. mov carries higher color precision for color grading, keying, and compositing, and some players cannot open it.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"mp4","options":["mp4","mov"]},{"name":"draft","label":"Draft Mode","type":"boolean","description":"Render a 480p draft to try the shot cheaply, then render the one you like at native 1080p or 4K from the same prompt, references and seed.","required":false,"metadata":{},"default":false},{"name":"draft_task_id","label":"Draft ID","type":"string","description":"The ID of a draft to render at native 1080p, or at 4K with resolution set to 4k. The draft keeps its prompt, references, length, aspect ratio, seed and audio. Drafts stay available for 14 days, and each draft's result shows its ID.","required":false,"metadata":{"ui":{"placeholder":"Paste a draft ID"},"hidden_when":{"op":"eq","field":"draft","value":true},"clear_when_hidden":true}},{"name":"return_last_frame","label":"Return Last Frame","type":"boolean","description":"Also return the final frame as an image, ready to use as the first frame of the next clip.","required":false,"metadata":{},"default":false},{"name":"image","label":"Image","type":"string","description":"Reference / first-frame image URL.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"image_end","label":"Image End","type":"string","description":"End-frame image URL for i2v_both.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"video","label":"Video","type":"string","description":"Reference video URL for reference / edit / extend.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid.","required":false,"metadata":{},"default":""},{"name":"seed","label":"Seed","type":"number","description":"Integer seed for reproducible-style output. Same seed gives similar, not identical, results.","required":false,"metadata":{},"min":-1,"max":2147483647}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"T2V/I2V 480P","value":"$0.206"},{"spec":"per second","label":"T2V/I2V 720P","value":"$0.462"},{"spec":"per second","label":"T2V/I2V 1080P","value":"$1.137"},{"spec":"per second","label":"T2V/I2V 4K","value":"$1.827"},{"spec":"per second of input plus output","label":"Video Input 480P","value":"$0.123"},{"spec":"per second of input plus output","label":"Video Input 720P","value":"$0.276"},{"spec":"per second of input plus output","label":"Video Input 1080P","value":"$0.680"},{"spec":"per second of input plus output","label":"Video Input 4K","value":"$1.128"}],"unit_pricing":[{"unit":"second","usd":"0.206","label":"T2V/I2V 480P"},{"unit":"second","usd":"0.462","label":"T2V/I2V 720P"},{"unit":"second","usd":"1.137","label":"T2V/I2V 1080P"},{"unit":"second","usd":"1.827","label":"T2V/I2V 4K"}],"limits":{"note":"Next-generation Seedance built for long-form storytelling: one request can produce a coherent clip of up to 30 seconds, draw on up to 50 reference assets, and edit or extend existing footage.\n\n**Modes**\n\n- Text to video, first frame, or first and last frame.\n- Multimodal reference to video from up to 30 images, 10 videos, and 10 audio clips. Audio-only input works on its own.\n- To edit an attached clip or continue it, describe that in your prompt. The model reads the intent from your wording.\n\n**Output**\n\n- 480p, 720p, 1080p, and 4K at 24fps, 4 to 30 seconds, with native synchronized audio.\n- 4K is 3840x2160 at 16:9 and is encoded as 10-bit H.265/HEVC, which some players cannot open.\n- MP4 by default. MOV carries higher color precision for grading and compositing, and some players cannot open it.\n- When you supply a first frame, the output follows that image's aspect ratio, so aspect_ratio stays adaptive. Reference jobs, including ones with a reference video, accept any ratio.\n\n**Draft mode**\n\n- Set draft to true to render a 480p draft while you are still trying shots. Drafts render at 480p only.\n- The response returns the draft's id as usage.draft_task_id. Send that back as draft_task_id to render the same shot at 1080p, or at 4K with resolution set to 4k.\n- The final render takes the prompt, reference assets, duration, aspect ratio, seed and audio setting from the draft, so only resolution, output_format and return_last_frame apply alongside draft_task_id. A draft stays promotable for 14 days.\n\n**Input limits**\n\n- Images: jpeg, png, webp, bmp, tiff, gif, heic, or heif, 300 to 6000 px per side, under 30 MB each.\n- Videos: MP4 or MOV, 2 to 30 seconds each and 30 seconds in total, under 200 MB each.\n- Audio: WAV or MP3, 2 to 30 seconds each and 30 seconds in total, under 15 MB each.\n- Uploaded images and videos that show a real person's face are blocked. To feature a person, start from an image made with Seedream 5.5. To use your own face, verify it in [My face](https://platform.empiriolabs.ai/dashboard/verified-portrait).\n\n**Billing**\n\n- Without a reference video, you are billed per second of generated video at the rate for the output resolution.\n- With a reference video, the model prices the reference clip's seconds alongside the generated seconds, at the lower video-input rate. Billed seconds are therefore reference duration plus output duration, so a request that includes a reference video costs more in total than the same output generated from text alone.\n- Draft mode is not a discounted rate. A draft bills as a normal 480p generation and its final bills as a normal generation at the final's resolution, 1080p or 4K, so the saving comes from trying shots at 480p and rendering only your pick.\n- Worked example at 480p: a 4 second clip from a text prompt bills 4 seconds. A 4 second clip generated from a 5 second reference video bills 9 seconds at the video-input rate.\n\n**Uploaded media preprocessing**\n\n- Video inputs are capped to 30 seconds.\n- Uploaded video inputs are normalized to provider-compatible MP4 when needed. Set preprocess_video to false to send a clip through untouched."},"notes":"Next-generation Seedance built for long-form storytelling: one request can produce a coherent clip of up to 30 seconds, draw on up to 50 reference assets, and edit or extend existing footage.\n\n**Modes**\n\n- Text to video, first frame, or first and last frame.\n- Multimodal reference to video from up to 30 images, 10 videos, and 10 audio clips. Audio-only input works on its own.\n- To edit an attached clip or continue it, describe that in your prompt. The model reads the intent from your wording.\n\n**Output**\n\n- 480p, 720p, 1080p, and 4K at 24fps, 4 to 30 seconds, with native synchronized audio.\n- 4K is 3840x2160 at 16:9 and is encoded as 10-bit H.265/HEVC, which some players cannot open.\n- MP4 by default. MOV carries higher color precision for grading and compositing, and some players cannot open it.\n- When you supply a first frame, the output follows that image's aspect ratio, so aspect_ratio stays adaptive. Reference jobs, including ones with a reference video, accept any ratio.\n\n**Input limits**\n\n- Images: jpeg, png, webp, bmp, tiff, gif, heic, or heif, 300 to 6000 px per side, under 30 MB each.\n- Videos: MP4 or MOV, 2 to 30 seconds each and 30 seconds in total, under 200 MB each.\n- Audio: WAV or MP3, 2 to 30 seconds each and 30 seconds in total, under 15 MB each.\n- Uploaded images and videos that show a real person's face are blocked. To feature a person, start from an image made with Seedream 5.5. To use your own face, verify it in [My face](https://platform.empiriolabs.ai/dashboard/verified-portrait).\n\n**Billing**\n\n- Without a reference video, you are billed per second of generated video at the rate for the output resolution.\n- With a reference video, the model prices the reference clip's seconds alongside the generated seconds, at the lower video-input rate. Billed seconds are therefore reference duration plus output duration, so a request that includes a reference video costs more in total than the same output generated from text alone.\n- Worked example at 480p: a 4 second clip from a text prompt bills 4 seconds. A 4 second clip generated from a 5 second reference video bills 9 seconds at the video-input rate.\n\n**Uploaded media preprocessing**\n\n- Video inputs are capped to 30 seconds.\n- Uploaded video inputs are normalized to provider-compatible MP4 when needed. Set preprocess_video to false to send a clip through untouched.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=seedance-2-5","api_url":"https://docs.empiriolabs.ai/models/seedance-2-5","logo":"https://media.empiriolabs.ai/model-logos/seedance-2-5.png","status":"available"},{"id":"grok-imagine-image-2-0","object":"model","created":1786060800,"owned_by":"xai","display_name":"Grok Imagine Image 2.0","author":"xai","provider":"xai","description":"Text-to-image plus multi-reference editing with up to five source images, automatic or pinned quality tiers, and 1K or 2K output resolution.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text","image"],"output_modalities":["image"],"features":["image_generation","image_editing","multi_image","text_rendering"],"aliases":["grok-imagine-image-2","grok-imagine-image-2.0","xai/grok-imagine-image-2-0","xai/grok-imagine-image-2","xai/grok-imagine-image-2.0"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-08-07","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Describe the image to create. With source images attached, this becomes the editing instruction. Refer to multiple images as <IMAGE_0>, <IMAGE_1>, and so on. Up to 8,000 characters.","required":false,"metadata":{"ui":{"control":"text_area","section":"Input"}}},{"name":"image","label":"Images","type":"string","description":"One to five source images to edit, as URLs, data URIs, or uploaded image objects. Leave empty to generate from the prompt alone.","required":false,"metadata":{"ui":{"accept":"image/*","control":"file","section":"Input","multiple":true,"max_files":5}}},{"name":"images","label":"Images","type":"string","description":"Plural alias for multiple uploaded image references.","required":false,"metadata":{"ui":{"hidden":true}}},{"name":"quality","label":"Quality","type":"enum","description":"Rendering quality. Auto lets the model choose the tier for each request, and billing follows the tier it serves. Low returns in a few seconds and costs less per image. Medium takes longer and resolves finer detail.","required":false,"metadata":{"ui":{"control":"segmented","section":"Settings"}},"default":"auto","options":["auto","low","medium"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution tier. 2k renders more pixels and costs more per image than 1k.","required":false,"metadata":{"ui":{"control":"segmented","section":"Settings"}},"default":"1k","options":["1k","2k"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio. Auto lets the model pick the best fit for the prompt. For an edit, auto follows the first source image. Includes the 21:9 and 5:2 widescreen and banner formats.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Settings"}},"default":"auto","options":["auto","1:1","16:9","9:16","4:3","3:4","3:2","2:3","2:1","1:2","21:9","5:2","19.5:9","9:19.5","20:9","9:20"]},{"name":"num_images","label":"Number of Images","type":"number","description":"Number of output images. Each output image is billed separately.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Output"}},"default":1,"min":1,"max":10},{"name":"response_format","label":"Response Format","type":"enum","description":"Return signed image URLs by default, or include base64 image data when b64_json is requested.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Output"}},"default":"url","options":["url","b64_json"]}],"supported_endpoints":["POST /v1/images/generations","POST /v1/images/edits"],"pricing":{"prompt":"0","completion":"0","image":"0.048","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Low quality, 1K","value":"$0.048"},{"spec":"per image","label":"Low quality, 2K","value":"$0.072"},{"spec":"per image","label":"Medium quality, 1K","value":"$0.072"},{"spec":"per image","label":"Medium quality, 2K","value":"$0.096"},{"spec":"per image","label":"Image input","value":"$0.05"}],"unit_pricing":[{"unit":"image","usd":"0.048","label":"Low quality, 1K"},{"unit":"image","usd":"0.072","label":"Low quality, 2K"},{"unit":"image","usd":"0.072","label":"Medium quality, 1K"},{"unit":"image","usd":"0.096","label":"Medium quality, 2K"},{"unit":"image","usd":"0.05","label":"Image input"}],"limits":{"note":"Generates images from a text prompt, or edits up to five source images from a natural-language instruction.\n\n**Modes**\n\n- Text-to-image: send a prompt with no image.\n- Image editing: attach one image and describe the change you want.\n- Multi-image editing: attach two to five images to combine subjects, transfer a style, or compose a scene. Refer to them in the prompt as <IMAGE_0>, <IMAGE_1>, and so on.\n\n**Example multi-image prompt**\n\n```\nPlace the product from <IMAGE_0> onto the marble surface in <IMAGE_1>.\n```\n\n**Defaults**\n\n- Auto quality at 1K resolution\n- Auto aspect ratio, so the model picks the best fit for the prompt\n- One output image per request\n\n**Quality and resolution**\n\nQuality selects how much work goes into the render. Auto lets the model choose the tier for each request and currently serves low for a text prompt and medium for an edit. Low returns in a few seconds. Medium takes longer and resolves finer detail. Resolution selects the 1K or 2K output tier. Quality and resolution combine into four price points, so a low 1K image is the cheapest option and a medium 2K image the most detailed.\n\n**Controls**\n\nSupports prompt, source images (URL or upload), quality, resolution, aspect ratio across sixteen ratios including auto and the 21:9 and 5:2 widescreen formats, number of images, and response format.\n\n**Limits**\n\n- Up to 5 source images per edit\n- Up to 10 output images per request\n- Prompt up to 8,000 characters\n\n**Billing**\n\n- Charged per output image at the quality and resolution served, plus a per-image fee for each source image you attach. Text-to-image has no source-image fee.\n- With auto quality the charge follows the tier the model served for that request. Set quality to low or medium when you want the price fixed in advance.\n- A request that fails validation or is rejected before any image is produced is not billed.\n- An image that is produced but then blocked by content policy is still billed. This follows xAI usage policy, which charges for the generation even when the output is blocked by the content safety check. Keep prompts and source images within the usage policy to avoid this.\n\n**Content safety**\n\nGenerated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed."},"notes":"Generates images from a text prompt, or edits up to five source images from a natural-language instruction.\n\n**Modes**\n\n- Text-to-image: send a prompt with no image.\n- Image editing: attach one image and describe the change you want.\n- Multi-image editing: attach two to five images to combine subjects, transfer a style, or compose a scene. Refer to them in the prompt as <IMAGE_0>, <IMAGE_1>, and so on.\n\n**Example multi-image prompt**\n\n```\nPlace the product from <IMAGE_0> onto the marble surface in <IMAGE_1>.\n```\n\n**Defaults**\n\n- Auto quality at 1K resolution\n- Auto aspect ratio, so the model picks the best fit for the prompt\n- One output image per request\n\n**Quality and resolution**\n\nQuality selects how much work goes into the render. Auto lets the model choose the tier for each request and currently serves low for a text prompt and medium for an edit. Low returns in a few seconds. Medium takes longer and resolves finer detail. Resolution selects the 1K or 2K output tier. Quality and resolution combine into four price points, so a low 1K image is the cheapest option and a medium 2K image the most detailed.\n\n**Controls**\n\nSupports prompt, source images (URL or upload), quality, resolution, aspect ratio across sixteen ratios including auto and the 21:9 and 5:2 widescreen formats, number of images, and response format.\n\n**Limits**\n\n- Up to 5 source images per edit\n- Up to 10 output images per request\n- Prompt up to 8,000 characters\n\n**Billing**\n\n- Charged per output image at the quality and resolution served, plus a per-image fee for each source image you attach. Text-to-image has no source-image fee.\n- With auto quality the charge follows the tier the model served for that request. Set quality to low or medium when you want the price fixed in advance.\n- A request that fails validation or is rejected before any image is produced is not billed.\n- An image that is produced but then blocked by content policy is still billed. This follows xAI usage policy, which charges for the generation even when the output is blocked by the content safety check. Keep prompts and source images within the usage policy to avoid this.\n\n**Content safety**\n\nGenerated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=grok-imagine-image-2-0","api_url":"https://docs.empiriolabs.ai/models/grok-imagine-image-2-0","logo":"https://media.empiriolabs.ai/model-logos/grok-imagine-image-2-0.png","status":"available"},{"id":"pixverse-v6","object":"model","created":1774742400,"owned_by":"pixverse","display_name":"Pixverse v6","author":"pixverse","provider":"pixverse","description":"Generates video from text, images, first and last frames, or up to seven references, with native audio, multi-shot cuts, and clip extension.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image","video"],"output_modalities":["video"],"features":["text_to_video","image_to_video","reference_to_video","audio_sync","multi_shot","character_consistency","multimodal"],"aliases":["pixverse/v6"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-03-29","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description, up to 2048 characters. In reference mode you can address a named reference inline as @name followed by a space.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"How your inputs are used. auto detects it from what you attach. t2v is text to video. i2v animates one image. transition interpolates between a first and last frame. reference combines up to 7 reference images, optionally with reference videos. extend continues an uploaded clip.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v","transition","reference","extend"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution. Higher resolutions bill at a higher per-second rate.","required":false,"metadata":{},"default":"720p","options":["360p","540p","720p","1080p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio. Used by text-to-video and reference modes. Image-driven modes follow the source image instead.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"16:9","options":["16:9","4:3","1:1","3:4","9:16","2:3","3:2","21:9"]},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds. Ignored when a reference video is supplied, because the output length follows the longest reference.","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":5,"min":1,"max":15},{"name":"generate_audio_switch","label":"Generate Audio","type":"boolean","description":"Generate native synchronized audio with the video. Bills at the higher with-audio rate for the chosen resolution. Not used when extending a video.","required":false,"metadata":{},"default":true},{"name":"generate_multi_clip_switch","label":"Multi Shot","type":"boolean","description":"Produce a multi-shot cut instead of one continuous take. Text-to-video and image-to-video only.","required":false,"metadata":{},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed. The same seed with the same inputs returns a similar result.","required":false,"metadata":{},"min":0,"max":2147483647},{"name":"reference_names","label":"Reference Names","type":"string","description":"Comma-separated names for the attached reference images, in order, so the prompt can address them as @name.","required":false,"metadata":{}},{"name":"video_reference_names","label":"Video Reference Names","type":"string","description":"Comma-separated names for the attached reference videos, in order. Supplying reference videos switches the model into omni reference and bills at the video-reference rate.","required":false,"metadata":{}},{"name":"image","label":"Image","type":"string","description":"Source or first-frame image URL.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"image_end","label":"Image End","type":"string","description":"Last-frame image URL for transition mode.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"video","label":"Video","type":"string","description":"Source video URL for extend, or a reference video URL for reference mode.","required":false,"metadata":{"ui":{"hide_in_playground":true}}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"Standard 360p no audio","value":"$0.025556"},{"spec":"per second","label":"Standard 360p with audio","value":"$0.035778"},{"spec":"per second","label":"Standard 540p no audio","value":"$0.035778"},{"spec":"per second","label":"Standard 540p with audio","value":"$0.046"},{"spec":"per second","label":"Standard 720p no audio","value":"$0.046"},{"spec":"per second","label":"Standard 720p with audio","value":"$0.061333"},{"spec":"per second","label":"Standard 1080p no audio","value":"$0.092"},{"spec":"per second","label":"Standard 1080p with audio","value":"$0.117556"},{"spec":"per second","label":"Video reference 360p no audio","value":"$0.051111"},{"spec":"per second","label":"Video reference 360p with audio","value":"$0.071556"},{"spec":"per second","label":"Video reference 540p no audio","value":"$0.071556"},{"spec":"per second","label":"Video reference 540p with audio","value":"$0.092"},{"spec":"per second","label":"Video reference 720p no audio","value":"$0.092"},{"spec":"per second","label":"Video reference 720p with audio","value":"$0.122667"},{"spec":"per second","label":"Video reference 1080p no audio","value":"$0.184"},{"spec":"per second","label":"Video reference 1080p with audio","value":"$0.235111"}],"unit_pricing":[{"unit":"second","usd":"0.025556","label":"Standard 360p no audio"},{"unit":"second","usd":"0.035778","label":"Standard 360p with audio"},{"unit":"second","usd":"0.035778","label":"Standard 540p no audio"},{"unit":"second","usd":"0.046","label":"Standard 540p with audio"},{"unit":"second","usd":"0.046","label":"Standard 720p no audio"},{"unit":"second","usd":"0.061333","label":"Standard 720p with audio"},{"unit":"second","usd":"0.092","label":"Standard 1080p no audio"},{"unit":"second","usd":"0.117556","label":"Standard 1080p with audio"},{"unit":"second","usd":"0.051111","label":"Video reference 360p no audio"},{"unit":"second","usd":"0.071556","label":"Video reference 360p with audio"},{"unit":"second","usd":"0.071556","label":"Video reference 540p no audio"},{"unit":"second","usd":"0.092","label":"Video reference 540p with audio"},{"unit":"second","usd":"0.092","label":"Video reference 720p no audio"},{"unit":"second","usd":"0.122667","label":"Video reference 720p with audio"},{"unit":"second","usd":"0.184","label":"Video reference 1080p no audio"},{"unit":"second","usd":"0.235111","label":"Video reference 1080p with audio"}],"limits":{"note":"PixVerse V6 generates video from a text prompt, a single image, a first and last frame, or up to seven reference images, and can continue an existing clip.\n\n**Modes**\n\n- `t2v`: text to video.\n- `i2v`: animate a single image.\n- `transition`: interpolate between a first-frame and a last-frame image.\n- `reference`: combine up to 7 reference images, optionally with up to 3 reference videos.\n- `extend`: continue an uploaded video.\n\n**Output**\n\n- 360p, 540p, 720p and 1080p, 1 to 15 seconds.\n- Aspect ratios 16:9, 4:3, 1:1, 3:4, 9:16, 2:3, 3:2 and 21:9 on text-to-video and reference modes. Image-driven modes follow the source image.\n- Native synchronized audio is on by default; set `generate_audio_switch` to false for a video without it.\n- Set `generate_multi_clip_switch` to true on text-to-video and image-to-video for a multi-shot cut.\n\n**Reference videos**\n\n- Supplying `videos` in `reference` mode switches the model into omni reference. Output length is taken from the longest reference video, so `duration` is ignored.\n- Name a reference with `reference_names` or `video_reference_names` and address it in the prompt as `@name` followed by a space.\n\n**Billing**\n\n- Billed per second of generated video at the rate for the output resolution, with a higher rate when audio is on.\n- A reference request that carries a reference video bills at the video-reference rate, which is roughly double the standard rate.\n\n**Input limits**\n\n- Images: PNG, JPEG or WebP, up to 20MB and 10000px on the long edge.\n- Videos for extend: MP4, MOV or WebM, up to 30 seconds and 50MB."},"notes":"PixVerse V6 generates video from a text prompt, a single image, a first and last frame, or up to seven reference images, and can continue an existing clip.\n\n**Modes**\n\n- `t2v`: text to video.\n- `i2v`: animate a single image.\n- `transition`: interpolate between a first-frame and a last-frame image.\n- `reference`: combine up to 7 reference images, optionally with up to 3 reference videos.\n- `extend`: continue an uploaded video.\n\n**Output**\n\n- 360p, 540p, 720p and 1080p, 1 to 15 seconds.\n- Aspect ratios 16:9, 4:3, 1:1, 3:4, 9:16, 2:3, 3:2 and 21:9 on text-to-video and reference modes. Image-driven modes follow the source image.\n- Native synchronized audio is on by default; set `generate_audio_switch` to false for a video without it.\n- Set `generate_multi_clip_switch` to true on text-to-video and image-to-video for a multi-shot cut.\n\n**Reference videos**\n\n- Supplying `videos` in `reference` mode switches the model into omni reference. Output length is taken from the longest reference video, so `duration` is ignored.\n- Name a reference with `reference_names` or `video_reference_names` and address it in the prompt as `@name` followed by a space.\n\n**Billing**\n\n- Billed per second of generated video at the rate for the output resolution, with a higher rate when audio is on.\n- A reference request that carries a reference video bills at the video-reference rate, which is roughly double the standard rate.\n\n**Input limits**\n\n- Images: PNG, JPEG or WebP, up to 20MB and 10000px on the long edge.\n- Videos for extend: MP4, MOV or WebM, up to 30 seconds and 50MB.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=pixverse-v6","api_url":"https://docs.empiriolabs.ai/models/pixverse-v6","logo":"https://media.empiriolabs.ai/model-logos/pixverse-v6.png","status":"available"},{"id":"pixverse-c1","object":"model","created":1775520000,"owned_by":"pixverse","display_name":"Pixverse C1","author":"pixverse","provider":"pixverse","description":"Cinema-grade video model for action and effects work, from text, images, first and last frames, or references, with native synchronized audio.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image"],"output_modalities":["video"],"features":["text_to_video","image_to_video","reference_to_video","audio_sync","character_consistency","camera_control"],"aliases":["pixverse/c1"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-04-07","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description, up to 2048 characters. In reference mode you can address a named reference inline as @name followed by a space.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"How your inputs are used. auto detects it from what you attach. t2v is text to video. i2v animates one image. transition interpolates between a first and last frame. reference combines up to 7 reference images, including multi-panel storyboard frames.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v","transition","reference"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution. Higher resolutions bill at a higher per-second rate.","required":false,"metadata":{},"default":"720p","options":["360p","540p","720p","1080p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio. Used by text-to-video and reference modes. Image-driven modes follow the source image instead.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"16:9","options":["16:9","4:3","1:1","3:4","9:16","2:3","3:2","21:9"]},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds.","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":5,"min":1,"max":15},{"name":"generate_audio_switch","label":"Generate Audio","type":"boolean","description":"Generate native synchronized audio with the video. Bills at the higher with-audio rate for the chosen resolution.","required":false,"metadata":{},"default":true},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed. The same seed with the same inputs returns a similar result.","required":false,"metadata":{},"min":0,"max":2147483647},{"name":"reference_names","label":"Reference Names","type":"string","description":"Comma-separated names for the attached reference images, in order, so the prompt can address them as @name.","required":false,"metadata":{}},{"name":"image","label":"Image","type":"string","description":"Source or first-frame image URL.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"image_end","label":"Image End","type":"string","description":"Last-frame image URL for transition mode.","required":false,"metadata":{"ui":{"hide_in_playground":true}}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"Standard 360p no audio","value":"$0.030667"},{"spec":"per second","label":"Standard 360p with audio","value":"$0.040889"},{"spec":"per second","label":"Standard 540p no audio","value":"$0.040889"},{"spec":"per second","label":"Standard 540p with audio","value":"$0.051111"},{"spec":"per second","label":"Standard 720p no audio","value":"$0.051111"},{"spec":"per second","label":"Standard 720p with audio","value":"$0.066444"},{"spec":"per second","label":"Standard 1080p no audio","value":"$0.097111"},{"spec":"per second","label":"Standard 1080p with audio","value":"$0.122667"}],"unit_pricing":[{"unit":"second","usd":"0.030667","label":"Standard 360p no audio"},{"unit":"second","usd":"0.040889","label":"Standard 360p with audio"},{"unit":"second","usd":"0.040889","label":"Standard 540p no audio"},{"unit":"second","usd":"0.051111","label":"Standard 540p with audio"},{"unit":"second","usd":"0.051111","label":"Standard 720p no audio"},{"unit":"second","usd":"0.066444","label":"Standard 720p with audio"},{"unit":"second","usd":"0.097111","label":"Standard 1080p no audio"},{"unit":"second","usd":"0.122667","label":"Standard 1080p with audio"}],"limits":{"note":"PixVerse C1 is the cinematic tier, tuned for physically grounded character motion, action choreography and effects work, with automatic storyboarding from the prompt.\n\n**Modes**\n\n- `t2v`: text to video.\n- `i2v`: animate a single image.\n- `transition`: interpolate between a first-frame and a last-frame image.\n- `reference`: combine up to 7 reference images, including multi-panel storyboard frames.\n\n**Output**\n\n- 360p, 540p, 720p and 1080p, 1 to 15 seconds.\n- Aspect ratios 16:9, 4:3, 1:1, 3:4, 9:16, 2:3, 3:2 and 21:9 on text-to-video and reference modes. Image-driven modes follow the source image.\n- Native synchronized audio is on by default; set `generate_audio_switch` to false for a video without it.\n\n**Billing**\n\n- Billed per second of generated video at the rate for the output resolution, with a higher rate when audio is on.\n\n**Input limits**\n\n- Images: PNG, JPEG or WebP, up to 20MB and 10000px on the long edge.\n\nC1 does not support clip extension. Use PixVerse V6 for that."},"notes":"PixVerse C1 is the cinematic tier, tuned for physically grounded character motion, action choreography and effects work, with automatic storyboarding from the prompt.\n\n**Modes**\n\n- `t2v`: text to video.\n- `i2v`: animate a single image.\n- `transition`: interpolate between a first-frame and a last-frame image.\n- `reference`: combine up to 7 reference images, including multi-panel storyboard frames.\n\n**Output**\n\n- 360p, 540p, 720p and 1080p, 1 to 15 seconds.\n- Aspect ratios 16:9, 4:3, 1:1, 3:4, 9:16, 2:3, 3:2 and 21:9 on text-to-video and reference modes. Image-driven modes follow the source image.\n- Native synchronized audio is on by default; set `generate_audio_switch` to false for a video without it.\n\n**Billing**\n\n- Billed per second of generated video at the rate for the output resolution, with a higher rate when audio is on.\n\n**Input limits**\n\n- Images: PNG, JPEG or WebP, up to 20MB and 10000px on the long edge.\n\nC1 does not support clip extension. Use PixVerse V6 for that.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=pixverse-c1","api_url":"https://docs.empiriolabs.ai/models/pixverse-c1","logo":"https://media.empiriolabs.ai/model-logos/pixverse-c1.png","status":"available"},{"id":"pixverse-lipsync","object":"model","created":1752451200,"owned_by":"pixverse","display_name":"Pixverse Lip Sync","author":"pixverse","provider":"pixverse","description":"Aligns mouth movement in an existing video to an uploaded audio track or to text spoken by one of fourteen built-in voices.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","audio"],"input_modalities":["text","video","audio"],"output_modalities":["video"],"features":["lipsync","audio_in","video_editing"],"aliases":["pixverse/lipsync"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-07-14","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"lip_sync_tts_content","label":"Text To Speak","type":"string","description":"The line to speak. Used when no audio file is attached. Billed in 15-character blocks.","required":false,"metadata":{}},{"name":"lip_sync_tts_speaker_id","label":"Voice","type":"enum","description":"Voice used for the spoken line. Auto picks one to suit the clip. Ignored when an audio file is attached.","required":false,"metadata":{},"default":"Auto","options":["Auto","Emily","James","Isabella","Liam","Chloe","Adrian","Harper","Ava","Sophia","Julia","Mason","Jack","Oliver","Ethan"]},{"name":"video","label":"Video","type":"string","description":"Source video URL. Required.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"audio","label":"Audio","type":"string","description":"Audio URL to lip sync to. Takes precedence over the spoken text.","required":false,"metadata":{"ui":{"hide_in_playground":true}}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"Speech","value":"$0.020444"}],"unit_pricing":[{"unit":"second","usd":"0.020444","label":"Speech"}],"limits":{"note":"Aligns mouth movement in an existing video to speech, either from an audio file you supply or from text spoken by a built-in voice.\n\n**Inputs**\n\n- `video`: the source clip, up to 300 seconds and 250MB.\n- `audio`: the speech to match, up to 300 seconds and 250MB.\n- Or `lip_sync_tts_content` with `lip_sync_tts_speaker_id` to have the model speak your text. Fourteen named voices are available plus `Auto`, which picks one to suit the clip.\n\n**Billing**\n\n- Billed per second of speech. Text-to-speech input is metered in 15-character blocks at the same rate, so the charge tracks the length of the script rather than the length of the source video.\n\n**Input limits**\n\n- Video: MP4, MOV or WebM, up to 1920px on the long edge.\n- Audio: MP3, WAV, M4A or AAC."},"notes":"Aligns mouth movement in an existing video to speech, either from an audio file you supply or from text spoken by a built-in voice.\n\n**Inputs**\n\n- `video`: the source clip, up to 300 seconds and 250MB.\n- `audio`: the speech to match, up to 300 seconds and 250MB.\n- Or `lip_sync_tts_content` with `lip_sync_tts_speaker_id` to have the model speak your text. Fourteen named voices are available plus `Auto`, which picks one to suit the clip.\n\n**Billing**\n\n- Billed per second of speech. Text-to-speech input is metered in 15-character blocks at the same rate, so the charge tracks the length of the script rather than the length of the source video.\n\n**Input limits**\n\n- Video: MP4, MOV or WebM, up to 1920px on the long edge.\n- Audio: MP3, WAV, M4A or AAC.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=pixverse-lipsync","api_url":"https://docs.empiriolabs.ai/models/pixverse-lipsync","logo":"https://media.empiriolabs.ai/model-logos/pixverse-lipsync.png","status":"available"},{"id":"pixverse-avatar","object":"model","created":1735689600,"owned_by":"pixverse","display_name":"Pixverse Avatar","author":"pixverse","provider":"pixverse","description":"Turns a single portrait into a talking avatar video, driven by an uploaded audio track or by text spoken with a built-in voice.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image","audio"],"input_modalities":["text","image","audio"],"output_modalities":["video"],"features":["lipsync","image_to_video","audio_in","audio_sync"],"aliases":["pixverse/avatar"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"lip_sync_tts_content","label":"Text To Speak","type":"string","description":"The line for the avatar to speak. Used when no audio file is attached. Billed in 15-character blocks.","required":false,"metadata":{}},{"name":"lip_sync_tts_speaker_id","label":"Voice","type":"enum","description":"Voice used for the spoken line. Auto picks one to suit the portrait. Ignored when an audio file is attached.","required":false,"metadata":{},"default":"Auto","options":["Auto","Emily","James","Isabella","Liam","Chloe","Adrian","Harper","Ava","Sophia","Julia","Mason","Jack","Oliver","Ethan"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution. Higher resolutions bill at a higher per-second rate.","required":false,"metadata":{},"default":"720p","options":["360p","540p","720p","1080p"]},{"name":"prompt","label":"Prompt","type":"string","description":"Optional direction for delivery or framing.","required":false,"metadata":{}},{"name":"image","label":"Image","type":"string","description":"Portrait image URL. Required.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"audio","label":"Audio","type":"string","description":"Audio URL for the avatar to perform. Takes precedence over the spoken text.","required":false,"metadata":{"ui":{"hide_in_playground":true}}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"360p","value":"$0.025556"},{"spec":"per second","label":"540p","value":"$0.051111"},{"spec":"per second","label":"720p","value":"$0.076667"},{"spec":"per second","label":"1080p","value":"$0.102222"}],"unit_pricing":[{"unit":"second","usd":"0.025556","label":"360p"},{"unit":"second","usd":"0.051111","label":"540p"},{"unit":"second","usd":"0.076667","label":"720p"},{"unit":"second","usd":"0.102222","label":"1080p"}],"limits":{"note":"Turns a single portrait image into a talking avatar video, driven either by an audio file you supply or by text spoken with a built-in voice.\n\n**Inputs**\n\n- `image`: the portrait to animate. Use a clear, front-facing subject.\n- `audio`: the speech to perform, or `lip_sync_tts_content` with `lip_sync_tts_speaker_id` to have the model speak your text. Fourteen named voices are available plus `Auto`.\n- `prompt` is optional and can describe delivery or framing.\n\n**Output**\n\n- 360p, 540p, 720p and 1080p.\n\n**Billing**\n\n- Billed per second of speech at the rate for the output resolution. Text-to-speech input is metered in 15-character blocks at the same rate, so the charge tracks the length of the script.\n\n**Input limits**\n\n- Image: PNG, JPEG or WebP, up to 20MB and 10000px on the long edge.\n- Audio: MP3, WAV, M4A or AAC."},"notes":"Turns a single portrait image into a talking avatar video, driven either by an audio file you supply or by text spoken with a built-in voice.\n\n**Inputs**\n\n- `image`: the portrait to animate. Use a clear, front-facing subject.\n- `audio`: the speech to perform, or `lip_sync_tts_content` with `lip_sync_tts_speaker_id` to have the model speak your text. Fourteen named voices are available plus `Auto`.\n- `prompt` is optional and can describe delivery or framing.\n\n**Output**\n\n- 360p, 540p, 720p and 1080p.\n\n**Billing**\n\n- Billed per second of speech at the rate for the output resolution. Text-to-speech input is metered in 15-character blocks at the same rate, so the charge tracks the length of the script.\n\n**Input limits**\n\n- Image: PNG, JPEG or WebP, up to 20MB and 10000px on the long edge.\n- Audio: MP3, WAV, M4A or AAC.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=pixverse-avatar","api_url":"https://docs.empiriolabs.ai/models/pixverse-avatar","logo":"https://media.empiriolabs.ai/model-logos/pixverse-avatar.png","status":"available"},{"id":"pixverse-edit","object":"model","created":1735689600,"owned_by":"pixverse","display_name":"Pixverse Edit","author":"pixverse","provider":"pixverse","description":"Six video transformations in one model: prompt editing, restyling, subject swap, motion transfer, upscaling, and generated sound effects.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","video","image"],"output_modalities":["video"],"features":["video_editing","editing","styles","motion_control","audio_out"],"aliases":["pixverse/edit"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"mode","label":"Mode","type":"enum","description":"Which transformation to run. modify edits content from a prompt. restyle changes the visual style. swap replaces a subject with an uploaded image. mimic transfers the motion onto a subject image. upscale raises the resolution. sound_effect generates a synchronized sound bed.","required":false,"metadata":{},"default":"modify","options":["modify","restyle","swap","mimic","upscale","sound_effect"]},{"name":"prompt","label":"Prompt","type":"string","description":"Used by modify as the edit to make, by restyle as the target style, and by sound_effect as the sound to generate. Leave it empty on sound_effect to derive the sound from the video.","required":false,"metadata":{}},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution for modify, mimic and swap. Restyle, upscale and sound_effect follow the source clip.","required":false,"metadata":{},"default":"540p","options":["360p","540p","720p"]},{"name":"restyle_id","label":"Restyle Preset","type":"number","description":"Optional preset id for restyle, as an alternative to a style prompt.","required":false,"metadata":{}},{"name":"swap_target","label":"Swap Target","type":"string","description":"Name of the detected subject to replace in swap mode, for example person or dog. Defaults to the first subject found in the keyframe.","required":false,"metadata":{}},{"name":"keyframe_id","label":"Keyframe","type":"number","description":"Which frame of the source video swap mode reads its subjects from. Defaults to the first frame.","required":false,"metadata":{},"default":1,"min":1},{"name":"original_sound_switch","label":"Keep Original Sound","type":"boolean","description":"Keep the source clip audio underneath a generated sound effect.","required":false,"metadata":{},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed for restyle.","required":false,"metadata":{},"min":0,"max":2147483647},{"name":"video","label":"Video","type":"string","description":"Source video URL. Required for every mode.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"image","label":"Image","type":"string","description":"Replacement image for swap, subject image for mimic, or up to 3 guidance images for modify.","required":false,"metadata":{"ui":{"hide_in_playground":true}}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"Modify 360p","value":"$0.040889"},{"spec":"per second","label":"Modify 540p","value":"$0.051111"},{"spec":"per second","label":"Modify 720p","value":"$0.061333"},{"spec":"per second","label":"Restyle","value":"$0.051111"},{"spec":"per second","label":"Motion control 360p","value":"$0.046"},{"spec":"per second","label":"Motion control 540p","value":"$0.051111"},{"spec":"per second","label":"Motion control 720p","value":"$0.061333"},{"spec":"per second","label":"Swap 360p","value":"$0.046"},{"spec":"per second","label":"Swap 540p","value":"$0.046"},{"spec":"per second","label":"Swap 720p","value":"$0.061333"},{"spec":"per second","label":"Upscale","value":"$0.025556"},{"spec":"per second","label":"Sound effects","value":"$0.010222"}],"unit_pricing":[{"unit":"second","usd":"0.040889","label":"Modify 360p"},{"unit":"second","usd":"0.051111","label":"Modify 540p"},{"unit":"second","usd":"0.061333","label":"Modify 720p"},{"unit":"second","usd":"0.051111","label":"Restyle"},{"unit":"second","usd":"0.046","label":"Motion control 360p"},{"unit":"second","usd":"0.051111","label":"Motion control 540p"},{"unit":"second","usd":"0.061333","label":"Motion control 720p"},{"unit":"second","usd":"0.046","label":"Swap 360p"},{"unit":"second","usd":"0.046","label":"Swap 540p"},{"unit":"second","usd":"0.061333","label":"Swap 720p"},{"unit":"second","usd":"0.025556","label":"Upscale"},{"unit":"second","usd":"0.010222","label":"Sound effects"}],"limits":{"note":"Six transformations that take an existing video and return a new one, selected with `mode`.\n\n**Modes**\n\n- `modify`: edit the content of a clip from a text prompt, optionally guided by up to 3 reference images.\n- `restyle`: change the visual style while preserving motion and composition. Pass a `restyle_prompt` or a `restyle_id`.\n- `swap`: replace a subject in the clip with an uploaded image. The model detects the subjects in the chosen keyframe; use `swap_target` to name which one, otherwise the first detected subject is used.\n- `mimic`: transfer the motion of the source video onto a subject image.\n- `upscale`: raise the resolution of the clip.\n- `sound_effect`: generate a synchronized sound bed. Leave the prompt empty to have it derived from the video, and set `original_sound_switch` to keep the existing audio.\n\n**Output**\n\n- `modify`, `mimic` and `swap` output 360p, 540p or 720p. `restyle`, `upscale` and `sound_effect` follow the source clip.\n\n**Billing**\n\n- Billed per second of the source video at the rate for the mode and resolution. `swap` also includes a small one-off subject-detection charge, which is folded into the billed seconds for that request.\n\n**Input limits**\n\n- Video: MP4, MOV or WebM, up to 1920px on the long edge and 30 seconds. Up to 100MB for modify, mimic, swap and upscale, and 50MB for restyle and sound effects. Swap requires H.264 or H.265.\n- Images: PNG, JPEG or WebP, up to 20MB and 10000px on the long edge."},"notes":"Six transformations that take an existing video and return a new one, selected with `mode`.\n\n**Modes**\n\n- `modify`: edit the content of a clip from a text prompt, optionally guided by up to 3 reference images.\n- `restyle`: change the visual style while preserving motion and composition. Pass a `restyle_prompt` or a `restyle_id`.\n- `swap`: replace a subject in the clip with an uploaded image. The model detects the subjects in the chosen keyframe; use `swap_target` to name which one, otherwise the first detected subject is used.\n- `mimic`: transfer the motion of the source video onto a subject image.\n- `upscale`: raise the resolution of the clip.\n- `sound_effect`: generate a synchronized sound bed. Leave the prompt empty to have it derived from the video, and set `original_sound_switch` to keep the existing audio.\n\n**Output**\n\n- `modify`, `mimic` and `swap` output 360p, 540p or 720p. `restyle`, `upscale` and `sound_effect` follow the source clip.\n\n**Billing**\n\n- Billed per second of the source video at the rate for the mode and resolution. `swap` also includes a small one-off subject-detection charge, which is folded into the billed seconds for that request.\n\n**Input limits**\n\n- Video: MP4, MOV or WebM, up to 1920px on the long edge and 30 seconds. Up to 100MB for modify, mimic, swap and upscale, and 50MB for restyle and sound effects. Swap requires H.264 or H.265.\n- Images: PNG, JPEG or WebP, up to 20MB and 10000px on the long edge.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=pixverse-edit","api_url":"https://docs.empiriolabs.ai/models/pixverse-edit","logo":"https://media.empiriolabs.ai/model-logos/pixverse-edit.png","status":"available"},{"id":"seedream-4-5","object":"model","created":1764720000,"owned_by":"bytedance","display_name":"Seedream 4.5","author":"bytedance","provider":"bytedance","description":"High-fidelity image generation and editing with up to 14 reference images, strong text rendering, and 2K or 4K output at one flat price.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text","image"],"output_modalities":["image"],"features":["editing","text_rendering","batch_generation"],"aliases":["bytedance/seedream-4.5","seedream-4.5","seedream-4-5-251128"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-12-03","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Text prompt. With image attached, becomes an editing instruction. For batch mode, describe each image sequentially.","required":true,"metadata":{}},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Auto lets the model choose dimensions within the selected resolution tier. Explicit ratios use the preset size for that tier.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"auto","options":["auto","1:1","16:9","9:16","4:3","3:4","3:2","2:3","21:9"]},{"name":"quality","label":"Quality","type":"enum","description":"Output resolution tier. Every tier bills at the same flat per-image rate.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Settings"}},"default":"2K","options":["2K","4K"]},{"name":"use_custom_size","label":"Use Custom Size","type":"boolean","description":"Use custom_width and custom_height instead of preset aspect_ratio and quality. Applies when aspect_ratio is auto.","required":false,"metadata":{"visible_when":{"op":"eq","field":"aspect_ratio","value":"auto"},"clear_when_hidden":true},"default":false},{"name":"custom_width","label":"Custom Width","type":"number","description":"Pixels. Total area must be in [3.69MP, 16.78MP]; aspect must be in [1:16, 16:1]. Only when use_custom_size=true.","required":false,"metadata":{"ui":{"step":1,"control":"text_field"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":1440,"max":16384},{"name":"custom_height","label":"Custom Height","type":"number","description":"Pixels. Total area must be in [3.69MP, 16.78MP]; aspect must be in [1:16, 16:1]. Only when use_custom_size=true.","required":false,"metadata":{"ui":{"step":1,"control":"text_field"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":1440,"max":16384},{"name":"image","label":"Image","type":"string","description":"Up to 14 reference image URLs for editing. Triggers image-edit mode.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"images","label":"Images","type":"string","description":"Alias for image. Use this for multiple uploaded image references.","required":false,"metadata":{"ui":{"hidden":true}}},{"name":"batch_enabled","label":"Batch Enabled","type":"boolean","description":"Generate a cohesive set of related images from a single prompt. A max_images above 1 also generates a set.","required":false,"metadata":{},"default":false},{"name":"max_images","label":"Max Images","type":"number","description":"Batch mode only. Maximum images in the set; the model decides actual count. You are billed only for images returned.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"visible_when":{"op":"eq","field":"batch_enabled","value":true},"clear_when_hidden":true},"default":4,"min":1,"max":15},{"name":"watermark","label":"Watermark","type":"boolean","description":"When enabled, the generated image includes an AI-generated provenance watermark. EmpirioLabs does not add a separate watermark.","required":false,"metadata":{},"default":false},{"name":"response_format","label":"Response Format","type":"enum","description":"Return signed image URLs by default, or include base64 image data when b64_json is requested.","required":false,"metadata":{},"default":"url","options":["url","b64_json"]}],"supported_endpoints":["POST /v1/images/generations"],"pricing":{"prompt":"0","completion":"0","image":"0.08","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Standard","value":"$0.080"}],"unit_pricing":[{"unit":"image","usd":"0.08","label":"Standard"}],"limits":{"note":"Text-to-image, single-reference editing, and multi-reference generation from up to 14 input images, plus batch sets of up to 15 related images. Every size bills at the same flat per-image rate, and input reference images are free.\n\n**Output**\n\n- 2K or 4K tiers, or an explicit size between 3.69MP and 16.78MP total pixels. JPEG output.\n\n**Batch mode**\n\n- sequential_image_generation auto generates a cohesive set; you are billed only for images actually returned.\n\n**Content safety**\n\n- Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed."},"notes":"Text-to-image, single-reference editing, and multi-reference generation from up to 14 input images, plus batch sets of up to 15 related images. Every size bills at the same flat per-image rate, and input reference images are free.\n\n**Output**\n\n- 2K or 4K tiers, or an explicit size between 3.69MP and 16.78MP total pixels. JPEG output.\n\n**Batch mode**\n\n- sequential_image_generation auto generates a cohesive set; you are billed only for images actually returned.\n\n**Content safety**\n\n- Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=seedream-4-5","api_url":"https://docs.empiriolabs.ai/models/seedream-4-5","logo":"https://media.empiriolabs.ai/model-logos/seedream-4-5.png","status":"available"},{"id":"seedream-4-0","object":"model","created":1757376000,"owned_by":"bytedance","display_name":"Seedream 4.0","author":"bytedance","provider":"bytedance","description":"Unified image generation and editing with up to 14 reference images, batch sets of up to 15, and 1K to 4K output at one flat per-image price.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text","image"],"output_modalities":["image"],"features":["editing","batch_generation"],"aliases":["bytedance/seedream-4.0","seedream-4.0","seedream-4","seedream-4-0-250828"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-09-09","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Text prompt. With image attached, becomes an editing instruction. For batch mode, describe each image sequentially.","required":true,"metadata":{}},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Auto lets the model choose dimensions within the selected resolution tier. Explicit ratios use the preset size for that tier.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"auto","options":["auto","1:1","16:9","9:16","4:3","3:4","3:2","2:3","21:9"]},{"name":"quality","label":"Quality","type":"enum","description":"Output resolution tier. Every tier bills at the same flat per-image rate.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Settings"}},"default":"2K","options":["1K","2K","4K"]},{"name":"prompt_optimization_mode","label":"Prompt Optimization","type":"enum","description":"Standard prioritizes prompt adherence and image quality. Fast reduces generation latency with slightly lower image quality.","required":false,"metadata":{},"default":"standard","options":["standard","fast"]},{"name":"use_custom_size","label":"Use Custom Size","type":"boolean","description":"Use custom_width and custom_height instead of preset aspect_ratio and quality. Applies when aspect_ratio is auto.","required":false,"metadata":{"visible_when":{"op":"eq","field":"aspect_ratio","value":"auto"},"clear_when_hidden":true},"default":false},{"name":"custom_width","label":"Custom Width","type":"number","description":"Pixels. Total area must be in [0.92MP, 16.78MP]; aspect must be in [1:16, 16:1]. Only when use_custom_size=true.","required":false,"metadata":{"ui":{"step":1,"control":"text_field"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":720,"max":16384},{"name":"custom_height","label":"Custom Height","type":"number","description":"Pixels. Total area must be in [0.92MP, 16.78MP]; aspect must be in [1:16, 16:1]. Only when use_custom_size=true.","required":false,"metadata":{"ui":{"step":1,"control":"text_field"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":720,"max":16384},{"name":"image","label":"Image","type":"string","description":"Up to 14 reference image URLs for editing. Triggers image-edit mode.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"images","label":"Images","type":"string","description":"Alias for image. Use this for multiple uploaded image references.","required":false,"metadata":{"ui":{"hidden":true}}},{"name":"batch_enabled","label":"Batch Enabled","type":"boolean","description":"Generate a cohesive set of related images from a single prompt. A max_images above 1 also generates a set.","required":false,"metadata":{},"default":false},{"name":"max_images","label":"Max Images","type":"number","description":"Batch mode only. Maximum images in the set; the model decides actual count. You are billed only for images returned.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"visible_when":{"op":"eq","field":"batch_enabled","value":true},"clear_when_hidden":true},"default":4,"min":1,"max":15},{"name":"watermark","label":"Watermark","type":"boolean","description":"When enabled, the generated image includes an AI-generated provenance watermark. EmpirioLabs does not add a separate watermark.","required":false,"metadata":{},"default":false},{"name":"response_format","label":"Response Format","type":"enum","description":"Return signed image URLs by default, or include base64 image data when b64_json is requested.","required":false,"metadata":{},"default":"url","options":["url","b64_json"]}],"supported_endpoints":["POST /v1/images/generations"],"pricing":{"prompt":"0","completion":"0","image":"0.06","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Standard","value":"$0.060"}],"unit_pricing":[{"unit":"image","usd":"0.06","label":"Standard"}],"limits":{"note":"Text-to-image, single-reference editing, and multi-reference generation from up to 14 input images, plus batch sets of up to 15 related images. Every size bills at the same flat per-image rate, and input reference images are free.\n\n**Output**\n\n- 1K, 2K, or 4K tiers, or an explicit size between 0.92MP and 16.78MP total pixels. JPEG output.\n- A fast prompt-optimization mode trades a little quality for lower latency.\n\n**Batch mode**\n\n- sequential_image_generation auto generates a cohesive set; you are billed only for images actually returned.\n\n**Content safety**\n\n- Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed."},"notes":"Text-to-image, single-reference editing, and multi-reference generation from up to 14 input images, plus batch sets of up to 15 related images. Every size bills at the same flat per-image rate, and input reference images are free.\n\n**Output**\n\n- 1K, 2K, or 4K tiers, or an explicit size between 0.92MP and 16.78MP total pixels. JPEG output.\n- A fast prompt-optimization mode trades a little quality for lower latency.\n\n**Batch mode**\n\n- sequential_image_generation auto generates a cohesive set; you are billed only for images actually returned.\n\n**Content safety**\n\n- Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=seedream-4-0","api_url":"https://docs.empiriolabs.ai/models/seedream-4-0","logo":"https://media.empiriolabs.ai/model-logos/seedream-4-0.png","status":"available"},{"id":"hyper3d-gen2","object":"model","created":1759276800,"owned_by":"deemos","display_name":"Hyper3D Gen2","author":"deemos","provider":"deemos","description":"Rodin Gen-2 engine that turns a text prompt or up to five reference images into production 3D assets with PBR materials and quad or raw meshes.","modality":"3D","type":"generation","category":"3d","category_label":"3D","modality_label":"3D","modalities":["3D","text","image"],"input_modalities":["text","image"],"output_modalities":["3D"],"features":["image_to_3d","text_to_3d","pbr_materials","quad_mesh","seed_control"],"aliases":["deemos/hyper3d-gen2","hyper3d-gen2-260112","rodin-gen2"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-10-01","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":true,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Text description of the object, in English, up to 400 characters. Optional when input images are provided.","required":false,"metadata":{}},{"name":"image","label":"Image","type":"string","description":"Up to five input images of the object. Multiple images act as multi-view references.","required":false,"metadata":{"ui":{"accept":"image/*","control":"file","section":"Input","hide_in_playground":true}}},{"name":"material","label":"Material","type":"enum","description":"Texture output: PBR maps, Shaded baked lighting, All for both, or None for an untextured white mesh.","required":false,"metadata":{"ui":{"control":"segmented","section":"Generation"}},"default":"PBR","options":["PBR","Shaded","All","None"]},{"name":"mesh_mode","label":"Mesh Mode","type":"enum","description":"Quad outputs a quad mesh; Raw outputs a triangle mesh with higher face-count ceilings.","required":false,"metadata":{"ui":{"control":"segmented","section":"Generation"}},"default":"Quad","options":["Quad","Raw"]},{"name":"subdivision_level","label":"Subdivision Level","type":"enum","description":"Preset face-count level for the chosen mesh mode. Ignored when quality_override is set.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Generation"}},"options":["high","medium","low"]},{"name":"quality_override","label":"Face Count Override","type":"number","description":"Custom face count. Raw meshes accept 500 to 1,000,000; Quad meshes 1,000 to 200,000.","required":false,"metadata":{"ui":{"control":"number","section":"Generation"}},"min":500,"max":1000000},{"name":"file_format","label":"File Format","type":"enum","description":"3D file format of the generated model.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Export"}},"default":"glb","options":["glb","obj","usdz","fbx","stl"]},{"name":"hd_texture","label":"HD Texture","type":"boolean","description":"Generate HD textures.","required":false,"metadata":{"ui":{"control":"toggle","section":"Export"}},"default":false},{"name":"high_pack","label":"4K Textures","type":"boolean","description":"Upgrade texture maps to 4K (2K without it).","required":false,"metadata":{"ui":{"control":"toggle","section":"Export"}},"default":false},{"name":"use_original_alpha","label":"Use Original Alpha","type":"boolean","description":"Preserve transparent regions of the input image.","required":false,"metadata":{"ui":{"control":"toggle","section":"Input"}},"default":false},{"name":"ta_pose","label":"T/A Pose","type":"boolean","description":"Force humanoid subjects into a standard T or A binding pose.","required":false,"metadata":{"ui":{"control":"toggle","section":"Generation"}},"default":false},{"name":"seed","label":"Seed","type":"number","description":"Seed in [0, 65535]. Same seed gives similar, not identical, results.","required":false,"metadata":{"ui":{"control":"number","section":"Generation"}},"min":0,"max":65535}],"supported_endpoints":["POST /v1/3d/generations"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0.8","input_cache_read":"0"},"pricing_rows":[{"spec":"per request","label":"Per generation","value":"$0.80"}],"unit_pricing":[{"unit":"request","usd":"0.8","label":"Per generation"}],"limits":{"note":"Generates one 3D asset per request from a text prompt (English, up to 400 characters), one to five reference images, or both. Billing is a flat rate per generated model.\n\n**Controls**\n\n- Materials: PBR, Shaded, both, or an untextured white mesh.\n- Quad or raw triangle meshes with preset subdivision levels or an exact face count (up to 1,000,000 raw or 200,000 quad).\n- glb, obj, usdz, fbx, or stl output, optional HD and 4K textures, transparent-alpha preservation, T/A pose for humanoids, and a seed control.\n\n**Input limits**\n\n- Images: jpg, jpeg, or png, under 4096x4096 px and 30 MB each.\n\n**Output**\n\n- The generated file is stored and returned as a signed download URL."},"notes":"Generates one 3D asset per request from a text prompt (English, up to 400 characters), one to five reference images, or both. Billing is a flat rate per generated model.\n\n**Controls**\n\n- Materials: PBR, Shaded, both, or an untextured white mesh.\n- Quad or raw triangle meshes with preset subdivision levels or an exact face count (up to 1,000,000 raw or 200,000 quad).\n- glb, obj, usdz, fbx, or stl output, optional HD and 4K textures, transparent-alpha preservation, T/A pose for humanoids, and a seed control.\n\n**Input limits**\n\n- Images: jpg, jpeg, or png, under 4096x4096 px and 30 MB each.\n\n**Output**\n\n- The generated file is stored and returned as a signed download URL.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=hyper3d-gen2","api_url":"https://docs.empiriolabs.ai/models/hyper3d-gen2","logo":"https://media.empiriolabs.ai/model-logos/hyper3d-gen2.png","status":"available"},{"id":"hitem3d-2-0","object":"model","created":1735689600,"owned_by":"hitem3d","display_name":"Hitem3D 2.0","author":"hitem3d","provider":"hitem3d","description":"Production-focused image-to-3D with structure-aware textures, 1536 and 1536 Pro precision tiers, meshes up to two million faces, and five export formats.","modality":"3D","type":"generation","category":"3d","category_label":"3D","modality_label":"3D","modalities":["3D","image"],"input_modalities":["image"],"output_modalities":["3D"],"features":["image_to_3d","multi_view","high_poly","texture_generation"],"aliases":["hitem3d-2.0","hitem3d-2-0-251223"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":true,"reasoning":false},"supported_parameters":[{"name":"image","label":"Image","type":"string","description":"One to four input images of the object. With multiple views, use multi_images_bit to declare the view order.","required":true,"metadata":{"ui":{"accept":"image/*","control":"file","section":"Input","hide_in_playground":true}}},{"name":"prompt","label":"Prompt","type":"string","description":"Optional guidance text for the generation.","required":false,"metadata":{}},{"name":"resolution","label":"Resolution","type":"enum","description":"Geometry resolution. 1536pro is the high-precision tier and bills at a higher per-generation rate.","required":false,"metadata":{"ui":{"control":"segmented","section":"Generation"}},"default":"1536","options":["1536","1536pro"]},{"name":"texture","label":"Texture","type":"boolean","description":"Generate textures with the geometry. Off returns a white model at a lower per-generation rate.","required":false,"metadata":{"ui":{"control":"toggle","section":"Generation"}},"default":true},{"name":"face_count","label":"Face Count","type":"number","description":"Target polygon count of the output mesh.","required":false,"metadata":{"ui":{"control":"number","section":"Generation"}},"min":100000,"max":2000000},{"name":"file_format","label":"File Format","type":"enum","description":"3D file format of the generated model.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Export"}},"default":"glb","options":["glb","obj","stl","fbx","usdz"]},{"name":"multi_images_bit","label":"View Layout","type":"string","description":"Four 0/1 digits declaring which views the input images are, in front, back, left, right order. Example: 1010 for front plus left.","required":false,"metadata":{"ui":{"hide_in_playground":true}}}],"supported_endpoints":["POST /v1/3d/generations"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"2.8","input_cache_read":"0"},"pricing_rows":[{"spec":"per request","when":[{"op":"eq","field":"resolution","value":"1536"},{"op":"eq","field":"texture","value":true}],"label":"1536 textured","value":"$2.80"},{"spec":"per request","when":[{"op":"eq","field":"resolution","value":"1536pro"},{"op":"eq","field":"texture","value":true}],"label":"1536 Pro textured","value":"$3.60"},{"spec":"per request","when":[{"op":"eq","field":"resolution","value":"1536"},{"op":"eq","field":"texture","value":false}],"label":"1536 white model","value":"$1.60"},{"spec":"per request","when":[{"op":"eq","field":"resolution","value":"1536pro"},{"op":"eq","field":"texture","value":false}],"label":"1536 Pro white model","value":"$2.40"}],"unit_pricing":[{"unit":"request","usd":"2.8","label":"1536 textured"},{"unit":"request","usd":"3.6","label":"1536 Pro textured"},{"unit":"request","usd":"1.6","label":"1536 white model"},{"unit":"request","usd":"2.4","label":"1536 Pro white model"}],"limits":{"note":"Image-to-3D only: one to four views of the object (declare the view order with multi_images_bit in front, back, left, right order). Billing is per generated model at the tier for the chosen resolution and texture setting.\n\n**Controls**\n\n- 1536 standard or 1536 Pro high-precision geometry.\n- texture on generates geometry and textures together in one pass; off returns a white model at a lower rate.\n- Target face count from 100,000 to 2,000,000, and glb, obj, stl, fbx, or usdz output.\n\n**Input limits**\n\n- Images: jpg, jpeg, png, or webp, under 4096x4096 px and 10 MB each, provided as URLs.\n\n**Output**\n\n- The generated file is stored and returned as a signed download URL."},"notes":"Image-to-3D only: one to four views of the object (declare the view order with multi_images_bit in front, back, left, right order). Billing is per generated model at the tier for the chosen resolution and texture setting.\n\n**Controls**\n\n- 1536 standard or 1536 Pro high-precision geometry.\n- texture on generates geometry and textures together in one pass; off returns a white model at a lower rate.\n- Target face count from 100,000 to 2,000,000, and glb, obj, stl, fbx, or usdz output.\n\n**Input limits**\n\n- Images: jpg, jpeg, png, or webp, under 4096x4096 px and 10 MB each, provided as URLs.\n\n**Output**\n\n- The generated file is stored and returned as a signed download URL.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=hitem3d-2-0","api_url":"https://docs.empiriolabs.ai/models/hitem3d-2-0","logo":"https://media.empiriolabs.ai/model-logos/hitem3d-2-0.png","status":"available"},{"id":"skylark-embedding-vision","object":"model","created":1751068800,"owned_by":"bytedance","display_name":"Skylark Embedding Vision","author":"bytedance","provider":"bytedance","description":"Multimodal embedding that fuses text, images, and video into one 1024 or 2048 dimension vector for cross-modal search and retrieval.","modality":null,"type":null,"category":"embedding","category_label":null,"modality_label":null,"modalities":["text","image","video","embedding"],"input_modalities":["text","image","video"],"output_modalities":["embedding"],"features":["multimodal","fused vectors"],"aliases":["byteplus/skylark-embedding-vision","skylark-embedding-vision-250615","doubao-embedding-vision"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":8000,"context_length":8000,"max_output_tokens":null,"model_released_at":"2025-06-28","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Text to embed, an array of up to 2,048 strings (one embedding each), or an array of text, image_url, and video_url parts fused into one embedding.","required":true,"metadata":{}},{"name":"dimensions","label":"Dimensions","type":"enum","description":"Output vector dimensionality.","required":false,"metadata":{},"default":"2048","options":["1024","2048"]},{"name":"encoding_format","label":"Encoding Format","type":"enum","description":"Embedding encoding of the response.","required":false,"metadata":{},"default":"float","options":["float","base64"]},{"name":"instructions","label":"Instructions","type":"string","description":"Optional retrieval instruction that conditions the embedding, such as a query-side or corpus-side template.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/embeddings"],"pricing":{"prompt":"0.00000025","completion":"0","image":"0","request":"0","input_cache_read":"0.00000025"},"pricing_rows":[{"spec":"per 1M tokens","label":"Text input","value":"$0.25"},{"spec":"per 1M tokens","label":"Image / video input","value":"$0.65"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.25","label":"Text input"},{"unit":"1m_tokens","usd":"0.65","label":"Image / video input"}],"limits":{"note":"**Output**\n\n- One fused vector per request across all input items (text, image, and video combine into a single embedding). Choose 1024 or 2048 dimensions.\n- An array of plain strings returns one embedding per string, up to 2,048 per request.\n\n**Per-input limits**\n\n- Text: up to 8,000 tokens per item.\n- Image: JPEG, PNG, WEBP, BMP, or TIFF, sides over 14 px, up to 36MP.\n- Video: MP4, AVI, or MOV, up to 50 MB; audio tracks are ignored.\n\n**Retrieval**\n\n- An optional instructions field conditions the embedding for the query or corpus side. Apply L2 normalization before cosine or dot-product comparison."},"notes":null,"chat_url":null,"api_url":null,"logo":"https://media.empiriolabs.ai/model-logos/skylark-embedding-vision.png","status":"available"},{"id":"wan-3-0","object":"model","created":1785974400,"owned_by":"alibaba","display_name":"Wan 3.0","author":"alibaba","provider":"alibaba","description":"All-in-one video generation up to 30 seconds with native audio, omni-modal references (images, video, audio, files, web links), and a fast Prime tier.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image","audio"],"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"features":["text_to_video","image_to_video","reference_to_video","audio_sync","character_consistency"],"aliases":["alibaba/wan-3.0","wan-3.0","wan3.0","wan3.0-video","wan3.0-video-prime"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-08-06","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description, up to 20,000 characters. In reference mode, address inputs in your prompt as Image 1, Video 1, Audio 1.","required":true,"metadata":{}},{"name":"model_tier","label":"Model Tier","type":"enum","description":"standard: full quality at the base rate. prime: significantly faster end-to-end generation at a higher per-second rate. Each tier is billed at its own rate.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"standard","options":["standard","prime"]},{"name":"mode","label":"Mode","type":"enum","description":"Auto detects from attachments. t2v: text-to-video. i2v: animate one image, or interpolate between two (first and last frame). r2v: omni reference from images, videos, audio, a document, or a web link.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v","r2v"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution. Each resolution bills at its own per-second rate.","required":false,"metadata":{},"default":"1080p","options":["480p","720p","1080p"]},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds. Pass -1 via the API to let the model choose the length. With video references, input plus output stays within 30 seconds.","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":5,"min":2,"max":30},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"adaptive recommends an aspect ratio from your inputs and prompt.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"adaptive","options":["adaptive","16:9","9:16","1:1","4:3","3:4"]},{"name":"image","label":"Image","type":"string","description":"Image URL. i2v uses one or two images (first and last frame); r2v accepts up to 10 references.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"video","label":"Video","type":"string","description":"Reference video URL (r2v). Up to 5 clips, 15 seconds combined.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed.","required":false,"metadata":{},"min":0,"max":2147483647},{"name":"audio","label":"Audio","type":"boolean","description":"Generate the soundtrack with the video. Turning it off does not change the price.","required":false,"metadata":{},"default":true},{"name":"watermark","label":"Watermark","type":"boolean","description":"Add a provenance watermark to the output.","required":false,"metadata":{},"default":false},{"name":"prompt_extend","label":"Prompt Extend","type":"boolean","description":"Let the service rewrite the prompt for better results.","required":false,"metadata":{},"default":true},{"name":"link","label":"Web Link","type":"string","description":"Public web page URL used as a reference (r2v). Provide either a link or a file_url, not both.","required":false,"metadata":{}},{"name":"file_url","label":"File URL","type":"string","description":"Document URL used as a reference (r2v): PDF, Office, or text files up to 100 MB and 50 pages. Provide either a file_url or a link, not both.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"Standard 480P","value":"$0.07"},{"spec":"per second","label":"Standard 720P","value":"$0.14"},{"spec":"per second","label":"Standard 1080P","value":"$0.28"},{"spec":"per second","label":"Prime 480P","value":"$0.136"},{"spec":"per second","label":"Prime 720P","value":"$0.28"},{"spec":"per second","label":"Prime 1080P","value":"$0.56"}],"unit_pricing":[{"unit":"second","usd":"0.07","label":"Standard 480P"},{"unit":"second","usd":"0.14","label":"Standard 720P"},{"unit":"second","usd":"0.28","label":"Standard 1080P"},{"unit":"second","usd":"0.136","label":"Prime 480P"},{"unit":"second","usd":"0.28","label":"Prime 720P"},{"unit":"second","usd":"0.56","label":"Prime 1080P"}],"limits":{"note":"Generation can take several minutes on the standard tier; the prime tier is significantly faster end to end. Modes are auto-detected from attachments, or override with the `mode` parameter. The `model_tier` parameter picks standard or prime; each tier bills at its own per-second rate.\n\n**Modes**\n\n- T2V: no attachments\n- I2V: 1 image (first frame), or exactly 2 images (first + last frame)\n- R2V (omni reference): up to 10 images, 5 videos (15s combined), and 5 audio clips (15s combined), plus 1 document file or 1 public web link; address them in your prompt as `Image 1`, `Video 1`, `Audio 1`\n- I2V frames and R2V references cannot be combined in one request\n\n**Inputs**\n\n- Images: JPEG, PNG, BMP, or WEBP, 240 to 8,000 px per side, up to 20 MB\n- Videos: MP4 or MOV, 1-15s per clip, up to 100 MB\n- Audio: WAV or MP3, 1-15s per clip, up to 15 MB\n\n**Duration and billing**\n\n- Clips run 2-30 seconds; pass `duration: -1` to let the model choose the length\n- With video references, input plus output share the 30-second budget, and billed seconds cover input + output combined\n- Output is MP4 at 30 fps with native audio; `audio: false` disables sound without changing the price\n\n**Uploaded media preprocessing**\n\n- Reference videos are normalized to provider-compatible MP4 when needed."},"notes":"Generation can take several minutes on the standard tier; the prime tier is significantly faster end to end. Modes are auto-detected from attachments, or override with the `mode` parameter. The `model_tier` parameter picks standard or prime; each tier bills at its own per-second rate.\n\n**Modes**\n\n- T2V: no attachments\n- I2V: 1 image (first frame), or exactly 2 images (first + last frame)\n- R2V (omni reference): up to 10 images, 5 videos (15s combined), and 5 audio clips (15s combined), plus 1 document file or 1 public web link; address them in your prompt as `Image 1`, `Video 1`, `Audio 1`\n- I2V frames and R2V references cannot be combined in one request\n\n**Inputs**\n\n- Images: JPEG, PNG, BMP, or WEBP, 240 to 8,000 px per side, up to 20 MB\n- Videos: MP4 or MOV, 1-15s per clip, up to 100 MB\n- Audio: WAV or MP3, 1-15s per clip, up to 15 MB\n\n**Duration and billing**\n\n- Clips run 2-30 seconds; pass `duration: -1` to let the model choose the length\n- With video references, input plus output share the 30-second budget, and billed seconds cover input + output combined\n- Output is MP4 at 30 fps with native audio; `audio: false` disables sound without changing the price\n\n**Uploaded media preprocessing**\n\n- Reference videos are normalized to provider-compatible MP4 when needed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=wan-3-0","api_url":"https://docs.empiriolabs.ai/models/wan-3-0","logo":"https://media.empiriolabs.ai/model-logos/wan.png","status":"available"},{"id":"fugu-max","object":"model","created":1788998400,"owned_by":"sakana","display_name":"Fugu Max","author":"sakana","provider":"sakana","description":"Cost-efficient multi-agent conductor that assembles a right-sized expert team per task, with 1M context, image input, and web search.","modality":"multimodal","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image"],"input_modalities":["text","image"],"output_modalities":["text"],"features":["reasoning","multimodal","web_search","function_calling","agentic_coding","structured_output","cache"],"aliases":["fugu-max-v1.0","sakana/fugu-max","sakana/fugu-max-v1.0"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":131072,"model_released_at":"2026-09-10","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum number of output tokens for the final answer. Must be at least 32. Very small values can truncate or empty the answer. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"slider","section":"Generation"}},"min":32,"max":131072},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"How hard the model reasons. Reasoning is always on. The default is high; xhigh and max are aliases of the same maximum effort.","required":false,"metadata":{"ui":{"control":"segmented","section":"Reasoning"}},"default":"high","options":["high","xhigh","max"]},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable built-in web search. Adds $0.007 to the request cost for each invoked call, and a single request can run more than one call. Page fetches are billed at the same rate.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function calling tool definitions.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}},"default":[]},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible tool choice control.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Return structured JSON output. JSON mode returns any valid JSON object; JSON Schema mode enforces the exact schema you provide.","required":false,"metadata":{"ui":{"control":"json","section":"Structured Output","hide_in_playground":true},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/fugu-max:generateContent"],"pricing":{"prompt":"0.000002","completion":"0.000006","image":"0","request":"0","input_cache_read":"0.00000025"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$2.00"},{"spec":"per 1M generated tokens","label":"Output","value":"$6.00"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.25"},{"spec":"per call when invoked","label":"Web search","value":"$0.007"},{"spec":"per call when invoked","label":"Web extractor","value":"$0.007"}],"unit_pricing":[{"unit":"1m_tokens","usd":"2","label":"Input"},{"unit":"1m_tokens","usd":"6","label":"Output"},{"unit":"1m_tokens","usd":"0.25","label":"Implicit cache read"},{"unit":"call","usd":"0.007","label":"Web search"},{"unit":"call","usd":"0.007","label":"Web extractor"}],"limits":{"note":"Fugu Max is the cost-efficient multi-agent conductor: each request assembles a right-sized team of expert models for the task and composes their work into a single answer.\n\n**Latency and streaming**\n- Simple prompts usually return in a few seconds, and heavier prompts take longer while the conductor works.\n- The full answer is returned all at once when the model finishes, not token by token. Streaming is accepted, but it delivers the complete response at the end rather than streaming tokens as they generate.\n- max_tokens must be at least 16. Leave generous headroom, since very small limits can truncate or empty the answer.\n\n**Capabilities**\n- Text and image input, with a 1M token context.\n- Always-on reasoning. high is the default, xhigh raises the effort, and max is accepted as an alias of xhigh.\n- Function calling, strict JSON Schema structured output, and built-in web search that cites its sources when available.\n\n**Billing**\n- Billed on full token usage, including the orchestration tokens the model uses internally, so even short prompts carry some cost.\n- One flat token rate at every context length, with no higher rate for long prompts.\n- Built-in web search and page fetch are billed per executed call at the rates shown, and a single request can run more than one call.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes tools (web search, code interpreter, etc.) inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape, exact field names, units, and which tools appear can vary slightly per provider:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nThe tool counts are already factored into `cost_usd`, they are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=fugu-max","api_url":"https://docs.empiriolabs.ai/models/fugu-max","logo":"https://media.empiriolabs.ai/model-logos/fugu-max.png","status":"available"},{"id":"fugu-ultra-v2-0","object":"model","created":1788998400,"owned_by":"sakana","display_name":"Fugu Ultra v2.0","author":"sakana","provider":"sakana","description":"Flagship multi-agent conductor for the hardest reasoning, coding, and research work, with 1M context, image input, and web search.","modality":"multimodal","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image"],"input_modalities":["text","image"],"output_modalities":["text"],"features":["reasoning","multimodal","web_search","function_calling","agentic_coding","structured_output","cache"],"aliases":["fugu-ultra-v2.0","sakana/fugu-ultra-v2-0","sakana/fugu-ultra-v2.0"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":131072,"model_released_at":"2026-09-10","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum number of output tokens for the final answer. Must be at least 16. Very small values can truncate or empty the answer. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"slider","section":"Generation"}},"min":16,"max":131072},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"How hard the model reasons. Reasoning is always on. The default is high; xhigh and max are aliases of the same maximum effort.","required":false,"metadata":{"ui":{"control":"segmented","section":"Reasoning"}},"default":"high","options":["high","xhigh","max"]},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable built-in web search. There is no separate fee; the search cost is reflected in the orchestration tokens billed for the request.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":false},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function calling tool definitions.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}},"default":[]},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible tool choice control.","required":false,"metadata":{"ui":{"control":"json","section":"Tools","hide_in_playground":true}}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to a JSON schema you supply. JSON mode (any JSON object) is not available on this model.","required":false,"metadata":{"ui":{"control":"json","section":"Structured Output","hide_in_playground":true},"control":"structured-output","so_tier":"json_schema"}}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/fugu-ultra-v2-0:generateContent"],"pricing":[{"prompt":"0.000005","completion":"0.00003","image":"0","request":"0","input_cache_read":"0.0000005"},{"prompt":"0.00001","completion":"0.000045","image":"0","request":"0","input_cache_read":"0.000001","min_context":272000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=272K $5.00; >272K $10.00"},{"spec":"per 1M generated tokens","label":"Output","value":"<=272K $30.00; >272K $45.00"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"<=272K $0.50; >272K $1.00"}],"unit_pricing":[],"limits":{"note":"Fugu Ultra v2.0 is the flagship multi-agent conductor: each request coordinates a pool of expert models and composes their work into a single answer.\n\n**Latency and streaming**\n- Responses can take from a few seconds to a few minutes on complex prompts.\n- The full answer is returned all at once when the model finishes, not token by token. Streaming is accepted, but it delivers the complete response at the end rather than streaming tokens as they generate.\n- max_tokens must be at least 16. Leave generous headroom, since very small limits can truncate or empty the answer.\n\n**Capabilities**\n- Text and image input, with a 1M token context.\n- Always-on reasoning. high is the default, xhigh raises the effort, and max is accepted as an alias of xhigh.\n- Function calling, strict JSON Schema structured output, and built-in web search that cites its sources when available (no separate fee).\n\n**Versioning**\n- Use fugu-ultra-v2-0 for v2.0. The legacy fugu-ultra id remains pinned to v1.0 for backward compatibility, and fugu-ultra-v1-1 continues to serve v1.1.\n\n**Billing**\n- Billed on full token usage, including the orchestration tokens the model uses internally, so even short prompts carry some cost.\n- Context-tiered: requests above 272K total input tokens use the higher rate shown."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=fugu-ultra-v2-0","api_url":"https://docs.empiriolabs.ai/models/fugu-ultra-v2-0","logo":"https://media.empiriolabs.ai/model-logos/fugu-ultra-v2-0.png","status":"available"},{"id":"stepaudio-3-tts","object":"model","created":1788912000,"owned_by":"stepfun","display_name":"StepAudio 3 TTS","author":"stepfun","provider":"stepfun","description":"Human-level speech synthesis across six languages, with 12 system voices, natural-language delivery direction, and streaming playback.","modality":"audio","type":"tts","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["text_to_speech","contextual_tts","voice_control","multilingual"],"aliases":["stepfun/stepaudio-3-tts"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-09-09","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Text to synthesize. Maximum 1,000 characters. Content in parentheses is treated as delivery direction and is not spoken.","required":true,"metadata":{"ui":{"control":"textarea","section":"Input"}},"max":1000},{"name":"voice","label":"Voice","type":"enum","description":"Voice for the generated speech.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Voice"}},"default":"lively-girl","options":["lively-girl","vibrant-youth","soft-spoken-gentleman","magnetic-voiced-male","elegantgentle-female","livelybreezy-female","zixinnansheng","Alfie","Ethan","Matthew","qingshunvsheng","tianrunnvsheng"]},{"name":"instruction","label":"Instruction","type":"string","description":"Global emotion or style guidance for the whole passage, in natural language. Maximum 500 characters.","required":false,"metadata":{"ui":{"control":"textarea","section":"Voice"}},"max":500},{"name":"speed","label":"Speed","type":"number","description":"Speech speed.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Voice"}},"default":1,"min":0.5,"max":2},{"name":"volume","label":"Volume","type":"number","description":"Output volume.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Voice"}},"default":1,"min":0.1,"max":2},{"name":"language","label":"Language","type":"enum","description":"Target language. Japanese, Korean, French, and Spanish are in preview.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Voice"}},"default":"en","options":["en","zh","ja","ko","fr","es"]},{"name":"response_format","label":"Response Format","type":"enum","description":"Output audio format.","required":false,"metadata":{"ui":{"control":"segmented","section":"Output"}},"default":"mp3","options":["mp3","wav","flac","opus","pcm"]},{"name":"sample_rate","label":"Sample Rate","type":"enum","description":"Output sample rate in Hz.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Output"}},"default":24000,"options":["8000","16000","22050","24000"]},{"name":"markdown_filter","label":"Markdown Filter","type":"boolean","description":"Strip Markdown syntax from the input before it is spoken.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"default":false},{"name":"pronunciation_map","label":"Pronunciation Map","type":"string","description":"Optional pronunciation overrides, as an object with a tone array of \"written/spoken\" rules.","required":false,"metadata":{"ui":{"control":"json","section":"Output"}}}],"supported_endpoints":["POST /v1/audio/speech","POST /v1/audio/speech:stream"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per 10,000 characters","label":"Synthesis","value":"$0.14"}],"unit_pricing":[{"unit":"10k_characters","usd":"0.14","label":"Synthesis"}],"limits":{"note":"Maximum input is 1,000 characters. Content in parentheses is treated as delivery direction and is not spoken. Use instruction for global emotion or style guidance, up to 500 characters. Twelve system voices are available. Recognized languages are Chinese, English, Japanese, Korean, French, and Spanish, with languages other than Chinese and English in preview. Output formats are mp3, wav, flac, opus, and pcm at 8000, 16000, 22050, or 24000 Hz. Wav is returned as a complete file rather than streamed. This model does not support voice_label."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=stepaudio-3-tts","api_url":"https://docs.empiriolabs.ai/models/stepaudio-3-tts","logo":"https://media.empiriolabs.ai/model-logos/stepaudio-3-tts.png","status":"available"},{"id":"stepaudio-3-asr-max","object":"model","created":1788134400,"owned_by":"stepfun","display_name":"StepAudio 3 ASR Max","author":"stepfun","provider":"stepfun","description":"Context-aware transcription for proper nouns, technical terms, dialects, and difficult audio including whispers, fast speech, and singing.","modality":"audio","type":"stt","category":"transcription","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio"],"output_modalities":["text"],"features":["transcription","speech_to_text","multilingual"],"aliases":["stepfun/stepaudio-3-asr-max"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-08-31","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"file","label":"File","type":"string","description":"Audio file upload for transcription.","required":false,"metadata":{"ui":{"accept":"audio/*","control":"file","section":"Input"}}},{"name":"file_url","label":"File URL","type":"string","description":"Public URL to an audio file.","required":false,"metadata":{"ui":{"control":"text_field","section":"Input"}}},{"name":"audio_base64","label":"Audio Base64","type":"string","description":"Base64 audio payload for JSON requests.","required":false,"metadata":{"ui":{"hidden":true}}},{"name":"enable_itn","label":"Enable ITN","type":"boolean","description":"Enable inverse text normalization, which writes numbers, dates, and currency in their written form.","required":false,"metadata":{"ui":{"control":"toggle","section":"Recognition"}},"default":true},{"name":"format","label":"Format","type":"enum","description":"Audio container format. When omitted, it is detected from the uploaded file.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Format"}},"options":["wav","mp3","ogg","m4a","pcm"]},{"name":"codec","label":"Codec","type":"string","description":"PCM codec such as pcm_s16le.","required":false,"metadata":{"ui":{"control":"text_field","section":"Format"}}},{"name":"rate","label":"Sample Rate","type":"number","description":"PCM sample rate in Hz.","required":false,"metadata":{"ui":{"control":"text_field","section":"Format"}}},{"name":"bits","label":"Bit Depth","type":"number","description":"PCM bit depth.","required":false,"metadata":{"ui":{"control":"text_field","section":"Format"}}},{"name":"channel","label":"Channels","type":"number","description":"PCM channel count.","required":false,"metadata":{"ui":{"control":"text_field","section":"Format"}}}],"supported_endpoints":["POST /v1/audio/transcriptions"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per hour of audio","label":"Transcription","value":"$0.60"}],"unit_pricing":[{"unit":"hour","usd":"0.6","label":"Transcription"}],"limits":{"note":"Supports wav, mp3, ogg, m4a, and pcm input. PCM requests should include codec, sample rate, bit depth, and channel count. The language is detected automatically and cannot be set; Chinese, English, Japanese, Korean, French, and Spanish are recognized, with languages other than Chinese and English in preview. Inverse text normalization is on by default and can be turned off with enable_itn. Hotwords and word timestamps are not available on this model. Audio is billed by its measured duration, with a one second minimum."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=stepaudio-3-asr-max","api_url":"https://docs.empiriolabs.ai/models/stepaudio-3-asr-max","logo":"https://media.empiriolabs.ai/model-logos/stepaudio-3-asr-max.png","status":"available"},{"id":"stepaudio-3-chat","object":"model","created":1788912000,"owned_by":"stepfun","display_name":"StepAudio 3 Chat","author":"stepfun","provider":"stepfun","description":"Audio and text conversation model that reasons before answering, with function calling and JSON output.","modality":"multimodal","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","audio"],"input_modalities":["text","audio"],"output_modalities":["text"],"features":["reasoning","audio_in","function_calling","structured_output","multimodal"],"aliases":["stepaudio-3-chat-preview","stepfun/stepaudio-3-chat"],"structured_output":"json_object","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":262144,"context_length":262144,"max_output_tokens":131072,"model_released_at":"2026-09-09","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0.5,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0.9,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. Reasoning tokens count toward this limit, so a small budget can be spent entirely on thinking and return an empty answer. Leave unset for a sensible default, or allow at least a few thousand tokens.","required":false,"metadata":{"ui":{"control":"number","section":"Output"}},"default":4096,"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Stop sequences.","required":false,"metadata":{"ui":{"control":"stop-sequences","section":"Output"}}},{"name":"frequency_penalty","label":"Frequency Penalty","type":"number","description":"Penalty for repeated tokens.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0,"min":-2,"max":2},{"name":"modalities","label":"Modalities","type":"string","description":"Response modalities. Text output is currently exposed.","required":false,"metadata":{"ui":{"control":"json","section":"Audio chat"}},"default":["text"]},{"name":"response_format","label":"Response Format","type":"string","description":"OpenAI-compatible response format. Use {\"type\":\"json_object\"} for JSON object mode.","required":false,"metadata":{"ui":{"control":"json","section":"Output"}}},{"name":"reasoning_format","label":"Reasoning Format","type":"enum","description":"Format of the reasoning trace returned alongside the answer.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Reasoning"}},"default":"general","options":["general","deepseek-style"]},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function tools.","required":false,"metadata":{"ui":{"control":"json","section":"Tools"}}},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible tool choice.","required":false,"metadata":{"ui":{"control":"text_field","section":"Tools"}}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions"],"pricing":{"prompt":"0.0000015","completion":"0.0000035","image":"0","request":"0","input_cache_read":"0.0000003"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.50"},{"spec":"per 1M generated tokens","label":"Output","value":"$3.50"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.30"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.5","label":"Input"},{"unit":"1m_tokens","usd":"3.5","label":"Output"},{"unit":"1m_tokens","usd":"0.3","label":"Implicit cache read"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Accepts text and audio input and replies with text. The model reasons before answering and returns its reasoning alongside the answer, and those reasoning tokens bill as output tokens. Because reasoning consumes the output budget, a small max_tokens can be spent entirely on thinking and return an empty answer; leave max_tokens unset for a sensible default, or allow at least a few thousand tokens. Function calling and JSON object output are supported. Linkup web search is available for text prompts. This model is in preview and its capabilities may change."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=stepaudio-3-chat","api_url":"https://docs.empiriolabs.ai/models/stepaudio-3-chat","logo":"https://media.empiriolabs.ai/model-logos/stepaudio-3-chat.png","status":"available"},{"id":"stepaudio-3-gen","object":"model","created":1788912000,"owned_by":"stepfun","display_name":"StepAudio 3 Gen","author":"stepfun","provider":"stepfun","description":"Generates dialogue, sound effects, ambience, and background music together in one clip from a written scene.","modality":"audio","type":"audio","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["audio_generation","text_to_speech","sound_effects","voice_control"],"aliases":["stepaudio-3-gen-preview","stepfun/stepaudio-3-gen"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-09-09","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Text to speak, read as written. Wrap a sound effect or music cue in square brackets and a delivery direction in parentheses, and describe the setting and background music in instruction.","required":false,"metadata":{"ui":{"control":"textarea","section":"Input"}}},{"name":"instruction","label":"Instruction","type":"string","description":"Global guidance for the setting, background music, and emotional tone. Maximum 500 characters.","required":false,"metadata":{"ui":{"control":"textarea","section":"Input"}},"max":500},{"name":"roles","label":"Roles","type":"string","description":"Optional speakers, as objects with a name and a voice description. All names and descriptions together are capped at 500 characters.","required":false,"metadata":{"ui":{"control":"json","section":"Input"}}},{"name":"scripts","label":"Scripts","type":"string","description":"Optional ordered lines, as objects with a speaker and text. Capped at 1,000 characters in total. Use this instead of prompt for multi-speaker scenes.","required":false,"metadata":{"ui":{"control":"json","section":"Input"}}},{"name":"response_format","label":"Response Format","type":"enum","description":"Output audio format.","required":false,"metadata":{"ui":{"control":"segmented","section":"Output"}},"default":"mp3","options":["mp3","wav","flac","opus","pcm"]},{"name":"sample_rate","label":"Sample Rate","type":"enum","description":"Output sample rate in Hz.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Output"}},"default":24000,"options":["8000","16000","22050","24000","48000"]},{"name":"speed","label":"Speed","type":"number","description":"Speech speed.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Output"}},"default":1,"min":0.5,"max":2},{"name":"volume","label":"Volume","type":"number","description":"Output volume.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Output"}},"default":1,"min":0.1,"max":2},{"name":"text_normalization","label":"Text Normalization","type":"enum","description":"How numbers, dates, and symbols are read aloud.","required":false,"metadata":{"ui":{"control":"segmented","section":"Output"}},"default":"standard","options":["standard","enhanced"]}],"supported_endpoints":["POST /v1/audio/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per 10,000 characters","label":"Generation","value":"$0.14"}],"unit_pricing":[{"unit":"10k_characters","usd":"0.14","label":"Generation"}],"limits":{"note":"One finished clip with spoken lines, sound effects, ambience, and background music together. Text in prompt and scripts is spoken as written: describe the setting and background music in instruction, wrap a sound effect or music cue in square brackets, and put a delivery direction in parentheses. Send a prompt, or use roles and scripts for multi-speaker control. Roles and instruction are capped at 500 characters each and scripts at 1,000. Output formats are mp3, wav, flac, opus, and pcm. Reference voices and voice cloning are not available on this model. This model is in preview and its capabilities may change."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=stepaudio-3-gen","api_url":"https://docs.empiriolabs.ai/models/stepaudio-3-gen","logo":"https://media.empiriolabs.ai/model-logos/stepaudio-3-gen.png","status":"available"},{"id":"stepaudio-3-music","object":"model","created":1788825600,"owned_by":"stepfun","display_name":"StepAudio 3 Music","author":"stepfun","provider":"stepfun","description":"Writes complete songs from a style description, with vocals, arrangement, and mixing, or instrumentals and covers.","modality":"audio","type":"audio","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text","audio"],"output_modalities":["audio"],"features":["music_generation","audio_generation","audio_in","multilingual"],"aliases":["stepaudio-3-music-preview","stepfun/stepaudio-3-music"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-09-08","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Style description: genre, vocals, mood, instruments, and key.","required":true,"metadata":{"ui":{"control":"textarea","section":"Input"}}},{"name":"lyrics","label":"Lyrics","type":"string","description":"Optional lyrics. Section tags such as [Verse], [Chorus], and [Outro] shape the structure. Left empty, the model writes them. Required for a cover or a vocal arrangement.","required":false,"metadata":{"ui":{"control":"textarea","section":"Input"}}},{"name":"task","label":"Task","type":"enum","description":"Write a new song, cover a reference song, or build an arrangement around a dry vocal.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Input"}},"default":"text_to_music","options":["text_to_music","music_cover","vocal_to_music"]},{"name":"instrumental","label":"Instrumental","type":"boolean","description":"Generate a track with no vocals. Cannot be combined with lyrics.","required":false,"metadata":{"ui":{"control":"toggle","section":"Input"}},"default":false},{"name":"song_audio","label":"Reference Song","type":"string","description":"Base64 reference song. Required for a cover.","required":false,"metadata":{"ui":{"accept":"audio/*","control":"file","section":"Input"}}},{"name":"vocal_audio","label":"Dry Vocal","type":"string","description":"Base64 dry vocal with no accompaniment. Required for a vocal arrangement.","required":false,"metadata":{"ui":{"accept":"audio/*","control":"file","section":"Input"}}},{"name":"response_format","label":"Response Format","type":"enum","description":"Output audio format.","required":false,"metadata":{"ui":{"control":"segmented","section":"Output"}},"default":"mp3","options":["mp3","wav","flac","opus","pcm"]},{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. Higher is more varied.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0.85,"min":0.01,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0.92,"min":0,"max":1},{"name":"lyrics_rewrite","label":"Rewrite Lyrics","type":"boolean","description":"Let the model rewrite the lyrics you supplied.","required":false,"metadata":{"ui":{"control":"toggle","section":"Sampling"}},"default":false}],"supported_endpoints":["POST /v1/audio/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per generated second","label":"Text to music","value":"$0.000667"},{"spec":"per generated second","label":"Audio to music","value":"$0.001334"}],"unit_pricing":[{"unit":"second","usd":"0.000667","label":"Text to music"},{"unit":"second","usd":"0.001334","label":"Audio to music"}],"limits":{"note":"Describe the style and the model writes and performs a complete song. Supply lyrics or let the model write them, set instrumental for a track with no vocals, or attach a reference song for a cover or a dry vocal to build an arrangement around. Section tags such as [Verse], [Chorus], and [Outro] shape the structure. Output length is chosen by the model and is typically one to three minutes, so it is not set by a parameter and two runs of the same prompt can differ. Billing follows the generated length. Instrumental and lyrics cannot be combined. This model is in preview and its capabilities may change."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=stepaudio-3-music","api_url":"https://docs.empiriolabs.ai/models/stepaudio-3-music","logo":"https://media.empiriolabs.ai/model-logos/stepaudio-3-music.png","status":"available"},{"id":"stepaudio-3-realtime","object":"model","created":1785974400,"owned_by":"stepfun","display_name":"StepAudio 3 Realtime","author":"stepfun","provider":"stepfun","description":"Speech in, speech out, over one socket. Interruptible mid-reply, with voice activity detection deciding when to answer.","modality":"audio","type":"realtime","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio","text"],"output_modalities":["audio","text"],"features":["realtime","speech_to_speech","audio_in","audio_out","function_calling","voice_control"],"aliases":["stepaudio-3-realtime-preview","stepfun/stepaudio-3-realtime"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":262144,"context_length":262144,"max_output_tokens":131072,"model_released_at":"2026-08-06","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"voice","label":"Voice","type":"enum","description":"Session voice, set with session.update before the model produces audio. It cannot be changed once the model has spoken, and any other value is rejected.","required":false,"metadata":{"ui":{},"option_labels":{"lively-girl":"Lively Girl","vibrant-youth":"Vibrant Youth","zixinnansheng":"Confident Male","livelybreezy-female":"Breezy Female","elegantgentle-female":"Gentle Female","magnetic-voiced-male":"Magnetic Male","soft-spoken-gentleman":"Gentleman"}},"default":"soft-spoken-gentleman","options":["soft-spoken-gentleman","magnetic-voiced-male","vibrant-youth","lively-girl","livelybreezy-female","elegantgentle-female","zixinnansheng"]},{"name":"instructions","label":"Instructions","type":"string","description":"System instructions for the session: persona, speaking style, and boundaries.","required":false,"metadata":{"ui":{}}},{"name":"modalities","label":"Modalities","type":"string","description":"Response modalities for the session.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":["text","audio"]},{"name":"volume_ratio","label":"Volume","type":"number","description":"Loudness of the spoken reply, relative to the default. Accepted range is 0.1 to 2.0.","required":false,"metadata":{},"default":1,"min":0.1,"max":2},{"name":"input_audio_format","label":"Input Audio Format","type":"enum","description":"Encoding of the audio you send. 16-bit PCM.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"pcm16","options":["pcm16"]},{"name":"output_audio_format","label":"Output Audio Format","type":"enum","description":"Encoding of the audio the model returns. 16-bit PCM.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"pcm16","options":["pcm16"]},{"name":"turn_detection","label":"Turn Detection","type":"string","description":"Server-side voice activity detection. Decides when you have stopped speaking and the model should reply. Without it the model listens but never answers, so leave it on unless you are driving turns yourself with input_audio_buffer.commit and response.create. With server_vad you can also set three whole numbers: prefix_padding_ms, the audio in milliseconds kept from before your speech starts (default 500); silence_duration_ms, the silence in milliseconds that ends your turn (default 100); and energy_awakeness_threshold, the audio level above which speech is detected, from 0 to 5000 (default 2500).","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":{"type":"server_vad"}}],"supported_endpoints":["WEBSOCKET /v1/realtime"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per minute","label":"Session","value":"$0.125"}],"unit_pricing":[{"unit":"minute","usd":"0.125","label":"Session"}],"limits":{"note":"Full-duplex voice over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=stepaudio-3-realtime, authenticated with the ordinary Authorization Bearer header. Audio is pcm16 in and out. The model listens while it speaks, so it can be interrupted mid-reply, and server-side voice activity detection decides when to answer. Set voice with session.update before the first audio; it cannot be changed once the model has spoken, and only the seven listed voices are accepted. Conversation is Chinese and English only. A session is billed by its length, from when it opens until it closes, in whole seconds, with a partial second counted as a full second. This model is in preview and its capabilities may change."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=stepaudio-3-realtime","api_url":"https://docs.empiriolabs.ai/models/stepaudio-3-realtime","logo":"https://media.empiriolabs.ai/model-logos/stepaudio-3-realtime.png","status":"available"},{"id":"stepaudio-2-5-realtime","object":"model","created":1784160000,"owned_by":"stepfun","display_name":"StepAudio 2.5 Realtime","author":"stepfun","provider":"stepfun","description":"Speech in, speech out, over one socket, with paralinguistic understanding of tone and pacing.","modality":"audio","type":"realtime","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio","text"],"output_modalities":["audio","text"],"features":["realtime","speech_to_speech","audio_in","audio_out","function_calling","voice_control"],"aliases":["stepaudio-2.5-realtime","stepfun/stepaudio-2-5-realtime"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":262144,"context_length":262144,"max_output_tokens":131072,"model_released_at":"2026-07-16","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"voice","label":"Voice","type":"enum","description":"Session voice, set with session.update before the model produces audio. It cannot be changed once the model has spoken, and any other value is rejected.","required":false,"metadata":{"ui":{},"option_labels":{"lively-girl":"Lively Girl","vibrant-youth":"Vibrant Youth","zixinnansheng":"Confident Male","livelybreezy-female":"Breezy Female","elegantgentle-female":"Gentle Female","magnetic-voiced-male":"Magnetic Male","soft-spoken-gentleman":"Gentleman"}},"default":"soft-spoken-gentleman","options":["soft-spoken-gentleman","magnetic-voiced-male","vibrant-youth","lively-girl","livelybreezy-female","elegantgentle-female","zixinnansheng"]},{"name":"instructions","label":"Instructions","type":"string","description":"System instructions for the session: persona, speaking style, and boundaries.","required":false,"metadata":{"ui":{}}},{"name":"modalities","label":"Modalities","type":"string","description":"Response modalities for the session.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":["text","audio"]},{"name":"volume_ratio","label":"Volume","type":"number","description":"Loudness of the spoken reply, relative to the default. Accepted range is 0.1 to 2.0.","required":false,"metadata":{},"default":1,"min":0.1,"max":2},{"name":"input_audio_format","label":"Input Audio Format","type":"enum","description":"Encoding of the audio you send. 16-bit PCM.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"pcm16","options":["pcm16"]},{"name":"output_audio_format","label":"Output Audio Format","type":"enum","description":"Encoding of the audio the model returns. 16-bit PCM.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"pcm16","options":["pcm16"]},{"name":"turn_detection","label":"Turn Detection","type":"string","description":"Server-side voice activity detection. Decides when you have stopped speaking and the model should reply. Without it the model listens but never answers, so leave it on unless you are driving turns yourself with input_audio_buffer.commit and response.create. With server_vad you can also set three whole numbers: prefix_padding_ms, the audio in milliseconds kept from before your speech starts (default 500); silence_duration_ms, the silence in milliseconds that ends your turn (default 100); and energy_awakeness_threshold, the audio level above which speech is detected, from 0 to 5000 (default 2500).","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":{"type":"server_vad"}}],"supported_endpoints":["WEBSOCKET /v1/realtime"],"pricing":{"prompt":"0.0000015","completion":"0.00001","image":"0","request":"0","input_cache_read":"0.0000003"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.50"},{"spec":"per 1M generated tokens","label":"Output","value":"$10.00"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.30"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.5","label":"Input"},{"unit":"1m_tokens","usd":"10","label":"Output"},{"unit":"1m_tokens","usd":"0.3","label":"Implicit cache read"}],"limits":{"note":"Full-duplex voice over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=stepaudio-2-5-realtime, authenticated with the ordinary Authorization Bearer header. Audio is pcm16 in and out. The model listens while it speaks, so it can be interrupted mid-reply, and server-side voice activity detection decides when to answer. Set voice with session.update before the first audio; it cannot be changed once the model has spoken, and only the seven listed voices are accepted. Conversation is Chinese and English only. Each completed turn is billed on its own from the usage the model reports."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=stepaudio-2-5-realtime","api_url":"https://docs.empiriolabs.ai/models/stepaudio-2-5-realtime","logo":"https://media.empiriolabs.ai/model-logos/stepaudio-2-5-realtime.png","status":"available"},{"id":"stepaudio-2-5-asr-stream","object":"model","created":1784160000,"owned_by":"stepfun","display_name":"StepAudio 2.5 ASR Stream","author":"stepfun","provider":"stepfun","description":"Live transcription over a socket, returning partial results as the speaker talks, with voice activity detection marking each sentence.","modality":"audio","type":"realtime","category":"transcription","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio"],"output_modalities":["text"],"features":["transcription","speech_to_text","realtime","streaming_asr"],"aliases":["stepaudio-2.5-asr-stream","stepfun/stepaudio-2-5-asr-stream"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-07-16","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input_audio_format","label":"Input audio format","type":"enum","description":"Encoding of the audio you append to the input buffer: base64 16-bit PCM.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"pcm16","options":["pcm16"]},{"name":"language","label":"Language","type":"enum","description":"Recognition language.","required":false,"metadata":{"ui":{"control":"segmented","section":"Recognition"},"option_labels":{"en":"English","es":"Spanish","fr":"French","zh":"Chinese"}},"default":"zh","options":["en","zh","fr","es"]}],"supported_endpoints":["WEBSOCKET /v1/realtime"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per hour of audio","label":"Transcription","value":"$0.40"}],"unit_pricing":[{"unit":"hour","usd":"0.4","label":"Transcription"}],"limits":{"note":"Live transcription over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=stepaudio-2-5-asr-stream, authenticated with the ordinary Authorization Bearer header. Stream 16 kHz pcm16 audio up with input_audio_buffer.append and read partial results back as the speaker is still talking, with server-side voice activity detection marking where each sentence ends. Use this for live captions and voice input; for a finished recording, StepAudio 2.5 ASR returns the whole transcript in one call. Billing follows the duration of audio you stream, settled when the session closes."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=stepaudio-2-5-asr-stream","api_url":"https://docs.empiriolabs.ai/models/stepaudio-2-5-asr-stream","logo":"https://media.empiriolabs.ai/model-logos/stepaudio-2-5-asr-stream.png","status":"available"},{"id":"qwen3-5-omni-flash-realtime","object":"model","created":1735689600,"owned_by":"alibaba","display_name":"Qwen3.5 Omni Flash Realtime","author":"alibaba","provider":"alibaba","description":"Speech in, speech out, over one socket, with separate text and audio token rates and per-turn billing.","modality":"audio","type":"realtime","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text","image","video"],"input_modalities":["audio","text","image","video"],"output_modalities":["audio","text"],"features":["realtime","speech_to_speech","audio_in","audio_out","video","function_calling","multilingual"],"aliases":["qwen3.5-omni-flash-realtime","alibaba/qwen3-5-omni-flash-realtime"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":196608,"context_length":196608,"max_output_tokens":65536,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"voice","label":"Voice","type":"enum","description":"Speaking voice for the session. Set it with session.update before the model produces any audio.","required":false,"metadata":{},"default":"Tina","options":["Tina","Serena","Ethan","Dylan","Sunny","Peter","Kiki","Eric"]},{"name":"instructions","label":"Instructions","type":"string","description":"System guidance for how the model should behave and speak during the conversation.","required":false,"metadata":{}},{"name":"modalities","label":"Modalities","type":"string","description":"Which output types the model returns for a turn. Drop \"audio\" for a text-only reply.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":["text","audio"]},{"name":"input_audio_format","label":"Input audio format","type":"enum","description":"Encoding of the audio you append to the input buffer: base64 16-bit PCM at 16 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"pcm","options":["pcm"]},{"name":"output_audio_format","label":"Output audio format","type":"enum","description":"Encoding of the audio the model streams back: base64 16-bit PCM at 24 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":24000},"default":"pcm","options":["pcm"]},{"name":"turn_detection","label":"Turn detection","type":"string","description":"Voice activity detection: decides when you have finished speaking and the model should reply. It is on by default as server_vad, which ends your turn after a pause. semantic_vad also judges whether you have finished speaking, so filler sounds and background noise do not end your turn. threshold is a number from -1 to 1, 0.5 by default; a higher value needs clearer, louder speech to count. silence_duration_ms, from 200 to 6000 and 800 by default, is how long a pause must last to end your turn. idle_timeout_ms, from 5000 to 30000 with server_vad, makes the model speak again when you stay silent that long after its reply. Set turn_detection to null to end each turn yourself with input_audio_buffer.commit and response.create.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":{"type":"server_vad"}},{"name":"max_response_output_tokens","label":"Max output tokens","type":"number","description":"Largest number of output tokens one reply may use: from 1 to 65536, where a larger number runs at 65536, or \"inf\" for the model's own limit. Also accepted as max_output_tokens. When omitted, the model's own default applies.","required":false,"metadata":{"aliases":["max_output_tokens"]},"min":1,"max":65536},{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness. When omitted, the model's own default applies.","required":false,"metadata":{},"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused. When omitted, the model's own default applies.","required":false,"metadata":{},"min":0.01,"max":1},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":0.1,"max":2},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647}],"supported_endpoints":["WEBSOCKET /v1/realtime"],"pricing":{"prompt":"0.0000011","completion":"0.0000066","image":"0","request":"0","input_cache_read":"0.0000011"},"pricing_rows":[{"spec":"per 1M audio input tokens","label":"Input: audio","value":"$9.00"},{"spec":"per 1M prompt tokens","label":"Input","value":"$1.10"},{"spec":"per 1M generated tokens, text-only replies","label":"Output","value":"$6.60"},{"spec":"per 1M generated audio tokens","label":"Output: audio","value":"$35.40"}],"unit_pricing":[{"unit":"1m_tokens","usd":"9","label":"Input: audio"},{"unit":"1m_tokens","usd":"1.1","label":"Input"},{"unit":"1m_tokens","usd":"35.4","label":"Output: audio"}],"limits":{"note":"Full-duplex voice over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=qwen3-5-omni-flash-realtime, authenticated with the ordinary Authorization Bearer header. Configure the session with session.update over the socket: voice, instructions, modalities, turn detection, sampling and the reply length limit, max_response_output_tokens. Send camera or video frames as JPEG images with input_image_buffer.append, after the first audio. This model's voices differ from the earlier Omni generation, so set one it accepts or leave the default; an unknown voice ends the session rather than returning an error. Text and audio tokens are priced separately, a spoken reply is billed for its audio output tokens only, and each completed turn is billed on its own from the usage the model reports."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-5-omni-flash-realtime","api_url":"https://docs.empiriolabs.ai/models/qwen3-5-omni-flash-realtime","logo":"https://media.empiriolabs.ai/model-logos/qwen3-5-omni-flash-realtime.png","status":"available"},{"id":"qwen3-5-omni-plus-realtime","object":"model","created":1735689600,"owned_by":"alibaba","display_name":"Qwen3.5 Omni Plus Realtime","author":"alibaba","provider":"alibaba","description":"Speech in, speech out, over one socket, on the larger Omni tier, with separate text and audio token rates and per-turn billing.","modality":"audio","type":"realtime","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text","image","video"],"input_modalities":["audio","text","image","video"],"output_modalities":["audio","text"],"features":["realtime","speech_to_speech","audio_in","audio_out","video","function_calling","multilingual"],"aliases":["qwen3.5-omni-plus-realtime","alibaba/qwen3-5-omni-plus-realtime"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":196608,"context_length":196608,"max_output_tokens":65536,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"voice","label":"Voice","type":"enum","description":"Speaking voice for the session. Set it with session.update before the model produces any audio.","required":false,"metadata":{},"default":"Tina","options":["Tina","Serena","Ethan","Dylan","Sunny","Peter","Kiki","Eric"]},{"name":"instructions","label":"Instructions","type":"string","description":"System guidance for how the model should behave and speak during the conversation.","required":false,"metadata":{}},{"name":"modalities","label":"Modalities","type":"string","description":"Which output types the model returns for a turn. Drop \"audio\" for a text-only reply.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":["text","audio"]},{"name":"input_audio_format","label":"Input audio format","type":"enum","description":"Encoding of the audio you append to the input buffer: base64 16-bit PCM at 16 kHz. With the beta version of the protocol, set session.audio.input.format before the first audio for type pcm or wav and sample_rate 8000, 16000, 24000 or 48000.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"pcm","options":["pcm"]},{"name":"output_audio_format","label":"Output audio format","type":"enum","description":"Encoding of the audio the model streams back: base64 16-bit PCM at 24 kHz. With the beta version of the protocol, set session.audio.output.format before the first audio for type pcm or wav and sample_rate 8000, 16000, 24000 or 48000.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":24000},"default":"pcm","options":["pcm"]},{"name":"turn_detection","label":"Turn detection","type":"string","description":"Voice activity detection: decides when you have finished speaking and the model should reply. It is on by default as server_vad, which ends your turn after a pause. semantic_vad also judges whether you have finished speaking, so filler sounds and background noise do not end your turn. threshold is a number from -1 to 1, 0.5 by default; a higher value needs clearer, louder speech to count. silence_duration_ms, from 200 to 6000 and 800 by default, is how long a pause must last to end your turn. idle_timeout_ms, from 5000 to 30000 with server_vad, makes the model speak again when you stay silent that long after its reply. Set turn_detection to null to end each turn yourself with input_audio_buffer.commit and response.create.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":{"type":"server_vad"}},{"name":"max_response_output_tokens","label":"Max output tokens","type":"number","description":"Largest number of output tokens one reply may use: from 1 to 65536, where a larger number runs at 65536, or \"inf\" for the model's own limit. Also accepted as max_output_tokens. When omitted, the model's own default applies.","required":false,"metadata":{"aliases":["max_output_tokens"]},"min":1,"max":65536},{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness. When omitted, the model's own default applies.","required":false,"metadata":{},"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused. When omitted, the model's own default applies.","required":false,"metadata":{},"min":0.01,"max":1},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":0.1,"max":2},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647}],"supported_endpoints":["WEBSOCKET /v1/realtime"],"pricing":{"prompt":"0.0000042","completion":"0.0000248","image":"0","request":"0","input_cache_read":"0.0000042"},"pricing_rows":[{"spec":"per 1M audio input tokens","label":"Input: audio","value":"$33.00"},{"spec":"per 1M prompt tokens","label":"Input","value":"$4.20"},{"spec":"per 1M generated tokens, text-only replies","label":"Output","value":"$24.80"},{"spec":"per 1M generated audio tokens","label":"Output: audio","value":"$124.00"}],"unit_pricing":[{"unit":"1m_tokens","usd":"33","label":"Input: audio"},{"unit":"1m_tokens","usd":"4.2","label":"Input"},{"unit":"1m_tokens","usd":"124","label":"Output: audio"}],"limits":{"note":"Full-duplex voice over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=qwen3-5-omni-plus-realtime, authenticated with the ordinary Authorization Bearer header. Configure the session with session.update over the socket: voice, instructions, modalities, turn detection, sampling and the reply length limit, max_response_output_tokens. Send camera or video frames as JPEG images with input_image_buffer.append, after the first audio. For WAV or another sample rate with the beta version of the protocol, set session.audio.input.format and session.audio.output.format before the first audio. This model's voices differ from the earlier Omni generation, so set one it accepts or leave the default; an unknown voice ends the session rather than returning an error. Text and audio tokens are priced separately, a spoken reply is billed for its audio output tokens only, and each completed turn is billed on its own from the usage the model reports."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-5-omni-plus-realtime","api_url":"https://docs.empiriolabs.ai/models/qwen3-5-omni-plus-realtime","logo":"https://media.empiriolabs.ai/model-logos/qwen3-5-omni-plus-realtime.png","status":"available"},{"id":"deepgram-nova-3-stream","object":"model","created":1735689600,"owned_by":"deepgram","display_name":"Deepgram Nova-3 Stream","author":"deepgram","provider":"deepgram","description":"Live transcription over a socket, returning interim results while the speaker is still talking and a settled transcript once each phrase ends.","modality":"audio","type":"realtime","category":"transcription","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio"],"output_modalities":["text"],"features":["transcription","speech_to_text","realtime","streaming_asr","multilingual"],"aliases":["nova-3-stream","deepgram/deepgram-nova-3-stream"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input_audio_format","label":"Input audio format","type":"enum","description":"Encoding of the audio you send: 16 kHz mono 16-bit PCM, or 24 kHz in the current OpenAI Realtime protocol.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"linear16","options":["linear16"]},{"name":"language","label":"Language","type":"string","description":"Language code such as en, es or fr, or multi for speech that switches between languages. Set it with language= on the connection URL or in the session's transcription settings.","required":false,"metadata":{},"default":"en"}],"supported_endpoints":["WEBSOCKET /v1/realtime"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per minute of audio","label":"Transcription","value":"$0.025"}],"unit_pricing":[{"unit":"minute","usd":"0.025","label":"Transcription"}],"limits":{"note":"Live transcription over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=deepgram-nova-3-stream, with your API key in the Authorization header. Use the OpenAI Realtime protocol, including the OpenAI SDKs, or Deepgram's streaming protocol with 16 kHz mono 16-bit PCM sent as binary frames. Add language= to the connection URL to transcribe a specific language. Billing is per minute of audio sent."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=deepgram-nova-3-stream","api_url":"https://docs.empiriolabs.ai/models/deepgram-nova-3-stream","logo":"https://media.empiriolabs.ai/model-logos/deepgram-nova-3-stream.png","status":"available"},{"id":"qwen3-8-livetranslate-flash-realtime","object":"model","created":1789603200,"owned_by":"alibaba","display_name":"Qwen3.8 LiveTranslate Flash Realtime","author":"alibaba","provider":"alibaba","description":"Simultaneous spoken translation over a WebSocket. Set the target language, then speak; the model replies in that language with text and audio.","modality":"audio","type":"realtime","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio","text"],"output_modalities":["audio","text"],"features":["realtime","speech_to_speech","audio_in","audio_out","multilingual","voice_cloning"],"aliases":["qwen3.8-livetranslate-flash-realtime","alibaba/qwen3-8-livetranslate-flash-realtime"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":49152,"context_length":49152,"max_output_tokens":4096,"model_released_at":"2026-09-17","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"voice","label":"Voice","type":"enum","description":"Speaking voice for the translated audio. Set it with session.update before the model produces any audio. Not used while voice_clone is once or always.","required":false,"metadata":{"hidden_when":{"op":"in","field":"voice_clone","values":["once","always"]},"value_when_hidden":"default"},"default":"Tina","options":["Tina","Serena","Ethan","Cindy"]},{"name":"target_language","label":"Target language","type":"enum","description":"Language the model translates into. Defaults to en. These languages translate to speech and text. With text output only (modalities [\"text\"]), 31 more translate to text: yue, el, af, ast, be, bg, bn, bs, ca, ceb, et, gl, gu, hr, hu, jv, kk, kn, ky, lv, mk, ml, mr, pa, ro, sk, sl, sw, tg, az and uk. Set it with session.update before you send audio.","required":false,"metadata":{"variants":[{"when":{"op":"eq","field":"modalities","value":"text"},"allowed_values":["zh","en","ar","de","fr","es","pt","id","it","ko","ru","th","vi","ja","tr","hi","ms","nl","ur","nb","sv","da","he","fi","pl","is","cs","fil","fa","yue","el","af","ast","be","bg","bn","bs","ca","ceb","et","gl","gu","hr","hu","jv","kk","kn","ky","lv","mk","ml","mr","pa","ro","sk","sl","sw","tg","az","uk"]}],"option_labels":{"af":"Afrikaans","ar":"Arabic","az":"Azerbaijani","be":"Belarusian","bg":"Bulgarian","bn":"Bengali","bs":"Bosnian","ca":"Catalan","cs":"Czech","da":"Danish","de":"German","el":"Greek","en":"English","es":"Spanish","et":"Estonian","fa":"Persian","fi":"Finnish","fr":"French","gl":"Galician","gu":"Gujarati","he":"Hebrew","hi":"Hindi","hr":"Croatian","hu":"Hungarian","id":"Indonesian","is":"Icelandic","it":"Italian","ja":"Japanese","jv":"Javanese","kk":"Kazakh","kn":"Kannada","ko":"Korean","ky":"Kyrgyz","lv":"Latvian","mk":"Macedonian","ml":"Malayalam","mr":"Marathi","ms":"Malay","nb":"Norwegian","nl":"Dutch","pa":"Punjabi","pl":"Polish","pt":"Portuguese","ro":"Romanian","ru":"Russian","sk":"Slovak","sl":"Slovenian","sv":"Swedish","sw":"Swahili","tg":"Tajik","th":"Thai","tr":"Turkish","uk":"Ukrainian","ur":"Urdu","vi":"Vietnamese","zh":"Chinese","ast":"Asturian","ceb":"Cebuano","fil":"Filipino","yue":"Cantonese"}},"default":"en","options":["zh","en","ar","de","fr","es","pt","id","it","ko","ru","th","vi","ja","tr","hi","ms","nl","ur","nb","sv","da","he","fi","pl","is","cs","fil","fa"]},{"name":"modalities","label":"Modalities","type":"string","description":"Which output types the model returns: [\"text\", \"audio\"] by default, or [\"text\"] for a text-only translation, which the text-only target languages need.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":["text","audio"]},{"name":"input_audio_format","label":"Input audio format","type":"enum","description":"Encoding of the audio you append to the input buffer: base64 16-bit PCM.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"pcm","options":["pcm"]},{"name":"output_audio_format","label":"Output audio format","type":"enum","description":"Encoding of the audio the model streams back: base64 16-bit PCM.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":"pcm","options":["pcm"]},{"name":"voice_clone","label":"Voice cloning","type":"enum","description":"Speaks the translation in the speaker's own voice. once keeps the voice heard at the start of the session for every reply; always matches the voice again before each reply, so the translation follows whoever is speaking. While this is on, voice is not used. Set it with session.update before you send audio.","required":false,"metadata":{"option_labels":{"off":"Off","once":"Once per session","always":"Follow each speaker"}},"default":"off","options":["off","once","always"]},{"name":"glossary","label":"Glossary","type":"string","description":"Preferred translations for specific terms, as an object of source term to translation, for example {\"machine learning\": \"aprendizaje automático\"}. Up to 1,000 terms, each at most 200 characters. Also accepted as translation.corpus.phrases. Set it with session.update before you send audio.","required":false,"metadata":{"ui":{"control":"json","section":"Advanced"}}}],"supported_endpoints":["WEBSOCKET /v1/realtime"],"pricing":{"prompt":"0.0000011","completion":"0.00004","image":"0","request":"0","input_cache_read":"0.0000011"},"pricing_rows":[{"spec":"per 1M audio input tokens","label":"Input: audio","value":"$15.00"},{"spec":"per 1M prompt tokens","label":"Input","value":"$1.10"},{"spec":"per 1M generated tokens","label":"Output","value":"$40.00"},{"spec":"per 1M generated audio tokens","label":"Output: audio","value":"$60.00"}],"unit_pricing":[{"unit":"1m_tokens","usd":"15","label":"Input: audio"},{"unit":"1m_tokens","usd":"1.1","label":"Input"},{"unit":"1m_tokens","usd":"40","label":"Output"},{"unit":"1m_tokens","usd":"60","label":"Output: audio"}],"limits":{"note":"Spoken translation over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=qwen3-8-livetranslate-flash-realtime, authenticated with the ordinary Authorization Bearer header. Set the target language with session.update before you send audio. With modalities set to [\"text\"], 31 more target languages translate to text only. Add glossary to set how specific terms are translated. Use a voice this model accepts, or leave the default Tina. To speak the translation in the speaker's own voice, set voice_clone to once (the voice heard at the start of the session) or always (the voice of whoever is speaking, matched before each reply); cloning adds no charge. Audio and text tokens are priced separately, and each completed turn is billed on its own from the usage the model reports."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-8-livetranslate-flash-realtime","api_url":"https://docs.empiriolabs.ai/models/qwen3-8-livetranslate-flash-realtime","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"step-5-preview","object":"model","created":1789430400,"owned_by":"stepfun","display_name":"Step 5 Preview","author":"stepfun","provider":"stepfun","description":"Frontier multimodal reasoning with a 1M token context, image and video input, parallel tool calling, and strict JSON schema output.","modality":"multimodal","type":"reasoning","category":"text","category_label":null,"modality_label":null,"modalities":["multimodal","text","image","video"],"input_modalities":["text","image","video"],"output_modalities":["text"],"features":["reasoning","function_calling","structured_output","vision","video","prompt_cache","agentic_coding"],"aliases":["stepfun/step-5-preview"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1024000,"context_length":1024000,"max_output_tokens":131072,"model_released_at":"2026-09-15","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0.5,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0.9,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens. Reasoning tokens count toward this limit.","required":false,"metadata":{"ui":{"control":"number","section":"Output"}},"default":4096,"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Stop sequences.","required":false,"metadata":{"ui":{"control":"stop-sequences","section":"Output"}}},{"name":"frequency_penalty","label":"Frequency Penalty","type":"number","description":"Penalty for repeated tokens.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Sampling"}},"default":0,"min":-2,"max":2},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Controls how much the model reasons before it answers. Higher effort spends more tokens on reasoning.","required":false,"metadata":{"ui":{"control":"segmented","section":"Reasoning"}},"default":"low","options":["low","medium","high"]},{"name":"reasoning_format","label":"Reasoning Format","type":"enum","description":"Format of the reasoning trace returned alongside the answer.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Reasoning"}},"default":"general","options":["general","deepseek-style"]},{"name":"tools","label":"Tools","type":"string","description":"OpenAI-compatible function tools.","required":false,"metadata":{"ui":{"control":"json","section":"Tools"}}},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"OpenAI-compatible tool choice.","required":false,"metadata":{"ui":{"control":"text_field","section":"Tools"}}},{"name":"response_format","label":"Structured Output","type":"string","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"ui":{"control":"json","section":"Output"},"control":"structured-output","so_tier":"json_schema"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/step-5-preview:generateContent"],"pricing":{"prompt":"0.000001","completion":"0.0000027","image":"0","request":"0","input_cache_read":"0.0000001"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.00"},{"spec":"per 1M generated tokens","label":"Output","value":"$2.70"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.10"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1","label":"Input"},{"unit":"1m_tokens","usd":"2.7","label":"Output"},{"unit":"1m_tokens","usd":"0.1","label":"Implicit cache read"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Supports text, image, and video input with a 1M token context, parallel function tools, strict JSON schema output, and reasoning_effort low, medium, or high. Prompt-cache hits are billed at the cache-read rate. Video input supports MP4 under 128 MB, with clips under 5 minutes recommended. This is a preview release, so its behavior and identifier may change."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=step-5-preview","api_url":"https://docs.empiriolabs.ai/models/step-5-preview","logo":"https://media.empiriolabs.ai/model-logos/step-5-preview.png","status":"available"},{"id":"sonilo-v1-1","object":"model","created":1781740800,"owned_by":"sonilo","display_name":"Sonilo v1.1","author":"sonilo","provider":"sonilo","description":"Frame-synced soundtracks generated straight from video, or music from a text prompt, with per-segment direction and stem separation.","modality":"audio","type":"generation","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text","video"],"input_modalities":["text","video"],"output_modalities":["audio"],"features":["music_generation","text_to_music","video_to_music","stems","commercial_ready"],"aliases":["sonilo-v1.1","sonilo/v1.1","sonilo-music","sonilo/sonilo-v1-1"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-06-18","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Style or creative direction for the music. Required when generating from text alone. Optional when scoring a video, where the footage leads.","required":false,"metadata":{"required_when":{"op":"neq","field":"mode","value":"video"}}},{"name":"mode","label":"Mode","type":"enum","description":"auto scores an attached video and falls back to text to music when there is no video. Set text or video to pin the behaviour.","required":false,"metadata":{},"default":"auto","options":["auto","text","video"]},{"name":"duration","label":"Duration","type":"number","description":"Track length in seconds. Text mode only. In video mode the track follows the length of the source video. Leave empty to let the prompt decide.","required":false,"metadata":{"visible_when":{"op":"neq","field":"mode","value":"video"},"clear_when_hidden":true},"min":5,"max":360},{"name":"output_format","label":"Output Format","type":"enum","description":"Delivered audio format. m4a is AAC, wav is 16-bit PCM, mp3 is 320 kbps.","required":false,"metadata":{},"default":"m4a","options":["m4a","wav","mp3"]},{"name":"variants_num","label":"Variants","type":"number","description":"How many distinct musical directions to generate in one request. Each variant is billed separately at the per-second rate, and the 10 second minimum applies to each one.","required":false,"metadata":{},"default":1,"min":1,"max":10},{"name":"prompt_influence","label":"Prompt Influence","type":"number","description":"Video mode only. How strongly the music follows the prompt rather than the footage. Lower lets the video lead, higher follows the prompt more literally. Adds no charge.","required":false,"metadata":{"visible_when":{"op":"neq","field":"mode","value":"text"},"clear_when_hidden":true},"default":0.5,"min":0,"max":1},{"name":"segments","label":"Segments","type":"string","description":"JSON array of timed segment prompts for scene by scene direction. Each entry takes start, end and prompt in seconds.","required":false,"metadata":{}},{"name":"video_url","label":"Video URL","type":"string","description":"Source video to score, as a publicly reachable URL. Up to 300MB and 6 minutes. Uploading a video in the playground sets this for you.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/audio/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per generated second","label":"Text to music","value":"$0.0045"},{"spec":"per generated second","label":"Video to music","value":"$0.018"}],"unit_pricing":[{"unit":"second","usd":"0.0045","label":"Text to music"},{"unit":"second","usd":"0.018","label":"Video to music"}],"limits":{"note":"**Modes**\n\n- auto scores the attached video, and falls back to text to music when there is no video\n- Video mode follows the cuts and pacing of the source footage\n- Text mode generates from a prompt alone\n\n**Controls**\n\nSupports prompt, mode, source video, 5 to 360 second duration in text mode, m4a, wav or mp3 output, 1 to 10 variants, stem separation, ducking, speech preservation, prompt influence, and JSON segment prompts.\n\n**Limits**\n\n- Source video up to 300MB and 6 minutes\n- Duration 5 to 360 seconds in text mode. Video mode follows the length of the source\n- Ducking, speech preservation and prompt influence apply to video mode only\n\n**Billing**\n\n- Charged per generated second at the catalog rate, with a 10 second minimum per track. A 4 second track bills 10 seconds.\n- Each variant is billed separately and the 10 second minimum applies to each one.\n- Stem separation, ducking and prompt influence add no charge.\n- A request rejected before generation is not billed."},"notes":"**Modes**\n\n- auto scores the attached video, and falls back to text to music when there is no video\n- Video mode follows the cuts and pacing of the source footage\n- Text mode generates from a prompt alone\n\n**Controls**\n\nSupports prompt, mode, source video, 5 to 360 second duration in text mode, m4a, wav or mp3 output, 1 to 10 variants, stem separation, ducking, speech preservation, prompt influence, and JSON segment prompts.\n\n**Limits**\n\n- Source video up to 300MB and 6 minutes\n- Duration 5 to 360 seconds in text mode. Video mode follows the length of the source\n- Ducking, speech preservation and prompt influence apply to video mode only\n\n**Billing**\n\n- Charged per generated second at the catalog rate, with a 10 second minimum per track. A 4 second track bills 10 seconds.\n- Each variant is billed separately and the 10 second minimum applies to each one.\n- Stem separation, ducking and prompt influence add no charge.\n- A request rejected before generation is not billed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=sonilo-v1-1","api_url":"https://docs.empiriolabs.ai/models/sonilo-v1-1","logo":"https://media.empiriolabs.ai/model-logos/sonilo-v1-1.png","status":"available"},{"id":"sonilo-sound-effects-1-0","object":"model","created":1784937600,"owned_by":"sonilo","display_name":"Sonilo Sound Effects 1.0","author":"sonilo","provider":"sonilo","description":"Frame-accurate sound effects placed on the action in a video, or generated from a text description, with per-segment direction.","modality":"audio","type":"generation","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text","video"],"input_modalities":["text","video"],"output_modalities":["audio"],"features":["sound_effects","text_to_audio","video_to_audio","audio_generation","music_generation","commercial_ready"],"aliases":["sonilo-sound-effects-1.0","sonilo-sfx","sonilo/sonilo-sound-effects-1-0"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-07-25","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Description of the sound to generate. Required when generating from text alone. Optional when working from a video, where the footage leads.","required":false,"metadata":{"required_when":{"in":["auto","text"],"op":"in","field":"mode"}}},{"name":"mode","label":"Mode","type":"enum","description":"auto places effects on an attached video and falls back to text to sound effect when there is no video. music_and_effects scores the video with music AND effects as one finished track.","required":false,"metadata":{},"default":"auto","options":["auto","text","video","music_and_effects"]},{"name":"duration","label":"Duration","type":"number","description":"Effect length in seconds. Text mode only. Leave empty to let the prompt decide. Video and sound modes follow the timing of the source video.","required":false,"metadata":{"visible_when":{"in":["auto","text"],"op":"in","field":"mode"},"clear_when_hidden":true},"min":0.5,"max":180},{"name":"music_prompt","label":"Music Prompt","type":"string","description":"Direction for the music bed that sits under the effects.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"music_and_effects"},"clear_when_hidden":true}},{"name":"sfx_prompt","label":"Effects Prompt","type":"string","description":"Direction for the sound effects placed on the action.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"music_and_effects"},"clear_when_hidden":true}},{"name":"output_format","label":"Output Format","type":"enum","description":"music_and_effects mode only: format of the combined track. wav is 16-bit PCM, m4a is AAC, mp3 is 320 kbps.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"music_and_effects"},"clear_when_hidden":true},"default":"wav","options":["wav","m4a","mp3"]},{"name":"preserve_speech","label":"Preserve Speech","type":"boolean","description":"music_and_effects mode only. Keep the speech from the source video and carry it into the finished mix.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"music_and_effects"},"clear_when_hidden":true},"default":false},{"name":"ducking","label":"Ducking","type":"boolean","description":"music_and_effects mode only. Dip the generated music under the speech so dialogue stays intelligible.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"music_and_effects"},"clear_when_hidden":true},"default":false},{"name":"segments","label":"Segments","type":"string","description":"JSON array of timed segment prompts for directed beats. Each entry takes start, end and prompt in seconds.","required":false,"metadata":{}},{"name":"video_url","label":"Video URL","type":"string","description":"Source video to sync effects to, as a publicly reachable URL. Up to 300MB and 8 minutes. Uploading a video in the playground sets this for you.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/audio/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per generated second","label":"Text to sound effect","value":"$0.0036"},{"spec":"per generated second","label":"Video to sound effect","value":"$0.018"},{"spec":"per generated second","label":"Music and effects","value":"$0.0288"}],"unit_pricing":[{"unit":"second","usd":"0.0036","label":"Text to sound effect"},{"unit":"second","usd":"0.018","label":"Video to sound effect"},{"unit":"second","usd":"0.0288","label":"Music and effects"}],"limits":{"note":"**Modes**\n\n- auto places effects on the attached video, and falls back to text to sound effect when there is no video\n- video syncs effects to the timing of the footage\n- text generates an effect from a description alone\n- music_and_effects scores the video with music AND effects as one finished track\n\n**Controls**\n\nSupports prompt, mode, source video, 0.5 to 180 second duration in text mode, separate music and effects prompts in sound mode, wav, m4a or mp3 output in sound mode, speech preservation, ducking, and JSON segment prompts.\n\n**Limits**\n\n- Source video up to 300MB and 8 minutes\n- Duration 0.5 to 180 seconds in text mode. Video and music_and_effects modes follow the source\n- Music and effects prompts, output format, speech preservation and ducking apply to sound mode only\n\n**Billing**\n\n- Charged per generated second at the catalog rate for the mode used, with a 3 second minimum for text and video modes and a 10 second minimum for sound mode\n- A request rejected before generation is not billed."},"notes":"**Modes**\n\n- auto places effects on the attached video, and falls back to text to sound effect when there is no video\n- video syncs effects to the timing of the footage\n- text generates an effect from a description alone\n- music_and_effects scores the video with music AND effects as one finished track\n\n**Controls**\n\nSupports prompt, mode, source video, 0.5 to 180 second duration in text mode, separate music and effects prompts in sound mode, wav, m4a or mp3 output in sound mode, speech preservation, ducking, and JSON segment prompts.\n\n**Limits**\n\n- Source video up to 300MB and 8 minutes\n- Duration 0.5 to 180 seconds in text mode. Video and music_and_effects modes follow the source\n- Music and effects prompts, output format, speech preservation and ducking apply to sound mode only\n\n**Billing**\n\n- Charged per generated second at the catalog rate for the mode used, with a 3 second minimum for text and video modes and a 10 second minimum for sound mode\n- A request rejected before generation is not billed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=sonilo-sound-effects-1-0","api_url":"https://docs.empiriolabs.ai/models/sonilo-sound-effects-1-0","logo":"https://media.empiriolabs.ai/model-logos/sonilo-sound-effects-1-0.png","status":"available"},{"id":"sonilo-video-to-video","object":"model","created":1735689600,"owned_by":"sonilo","display_name":"Sonilo Video to Video","author":"sonilo","provider":"sonilo","description":"Returns your own video with a generated soundtrack, frame-synced effects, or both mixed in, keeping the original picture untouched.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text"],"input_modalities":["text","video"],"output_modalities":["video"],"features":["video_generation","video_to_video","music_generation","sound_effects","commercial_ready"],"aliases":["sonilo-v2v","sonilo/sonilo-video-to-video"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"mode","label":"Mode","type":"enum","description":"What to add to the returned video: a generated soundtrack, frame-synced sound effects, or both mixed together.","required":false,"metadata":{},"default":"music","options":["music","effects","music_and_effects"]},{"name":"prompt","label":"Prompt","type":"string","description":"Creative direction for the generated audio.","required":false,"metadata":{"visible_when":{"op":"neq","field":"mode","value":"music_and_effects"},"clear_when_hidden":true}},{"name":"music_prompt","label":"Music Prompt","type":"string","description":"Direction for the music bed.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"music_and_effects"},"clear_when_hidden":true}},{"name":"sfx_prompt","label":"Effects Prompt","type":"string","description":"Direction for the sound effects.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"music_and_effects"},"clear_when_hidden":true}},{"name":"keep_original_sound","label":"Keep Original Sound","type":"boolean","description":"Keep the whole original audio track under the generated audio. Without this the source audio is removed.","required":false,"metadata":{},"default":false},{"name":"preserve_speech","label":"Preserve Speech","type":"boolean","description":"Keep only the isolated speech from the source, rather than the whole original track.","required":false,"metadata":{},"default":false},{"name":"ducking","label":"Ducking","type":"boolean","description":"Dip the kept voice under the generated audio instead of holding a static mix.","required":false,"metadata":{},"default":false},{"name":"variants_num","label":"Variants","type":"number","description":"Music mode only. How many differently scored videos to generate in one request. Each variant is billed separately.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"music"},"clear_when_hidden":true},"default":1,"min":1,"max":10},{"name":"prompt_influence","label":"Prompt Influence","type":"number","description":"Music mode only. How strongly the music follows the prompt rather than the footage. Lower lets the video lead.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"music"},"clear_when_hidden":true},"default":0.5,"min":0,"max":1},{"name":"segments","label":"Segments","type":"string","description":"JSON array of timed segment prompts for scene by scene direction. Each entry takes start, end and prompt in seconds.","required":false,"metadata":{}},{"name":"video_url","label":"Video URL","type":"string","description":"Source video, as a publicly reachable URL. Up to 300MB and 8 minutes. Uploading a video in the playground sets this for you.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"Music only","value":"$0.018"},{"spec":"per second","label":"Effects only","value":"$0.018"},{"spec":"per second","label":"Music and effects","value":"$0.0288"}],"unit_pricing":[{"unit":"second","usd":"0.018","label":"Music only"},{"unit":"second","usd":"0.018","label":"Effects only"},{"unit":"second","usd":"0.0288","label":"Music and effects"}],"limits":{"note":"**Modes**\n\n- music returns the video scored with a generated soundtrack\n- effects returns the video with frame-synced sound effects\n- music_and_effects returns the video with music and effects mixed together\n\n**Controls**\n\nSupports mode, source video, creative direction, separate music and effects prompts in sound mode, keeping the original audio, speech preservation, ducking, 1 to 10 variants in music mode, prompt influence, and JSON segment prompts.\n\n**Limits**\n\n- Source video up to 300MB and 8 minutes\n- Accepts mp4, mov, m4v or webm carrying H.264, H.265, VP9 or AV1\n- The source picture is copied through without re-encoding, so the returned video keeps its original resolution and frame rate\n- By default the source audio is removed. Keep all of it with keep original sound, or keep only the speech with preserve speech\n\n**Billing**\n\n- Charged per generated second at the catalog rate for the mode used, with a 10 second minimum for music and sound modes and a 3 second minimum for sfx mode\n- Each variant is billed separately\n- A request rejected before generation is not billed."},"notes":"**Modes**\n\n- music returns the video scored with a generated soundtrack\n- effects returns the video with frame-synced sound effects\n- music_and_effects returns the video with music and effects mixed together\n\n**Controls**\n\nSupports mode, source video, creative direction, separate music and effects prompts in sound mode, keeping the original audio, speech preservation, ducking, 1 to 10 variants in music mode, prompt influence, and JSON segment prompts.\n\n**Limits**\n\n- Source video up to 300MB and 8 minutes\n- Accepts mp4, mov, m4v or webm carrying H.264, H.265, VP9 or AV1\n- The source picture is copied through without re-encoding, so the returned video keeps its original resolution and frame rate\n- By default the source audio is removed. Keep all of it with keep original sound, or keep only the speech with preserve speech\n\n**Billing**\n\n- Charged per generated second at the catalog rate for the mode used, with a 10 second minimum for music and sound modes and a 3 second minimum for sfx mode\n- Each variant is billed separately\n- A request rejected before generation is not billed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=sonilo-video-to-video","api_url":"https://docs.empiriolabs.ai/models/sonilo-video-to-video","logo":"https://media.empiriolabs.ai/model-logos/sonilo-video-to-video.png","status":"available"},{"id":"sonilo-video-translation","object":"model","created":1735689600,"owned_by":"sonilo","display_name":"Sonilo Video Translation","author":"sonilo","provider":"sonilo","description":"Dubs a video into 24 languages with lip-sync matched voices, returning one finished video per language plus optional subtitle tracks.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video"],"input_modalities":["video"],"output_modalities":["video"],"features":["dubbing","translation","multilingual","lip_sync","video_to_video","commercial_ready"],"aliases":["sonilo-dubbing","sonilo/sonilo-video-translation"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"languages","label":"Target Languages","type":"string","description":"JSON array of target language codes. One dubbed video is returned per language, and the request is billed per language. Supported: en, zh_cn, ja, ko, pt, pt_br, es, es_419, de, fr, it, ru, th, ar, tr, vi, id, ta, ml, kn, gu, pa_in, sd_in, hi.","required":false,"metadata":{},"default":"[\"zh_cn\",\"es\",\"fr\"]"},{"name":"video_url","label":"Video URL","type":"string","description":"Source video, as a publicly reachable URL. Up to 300MB and 5 minutes, and it must carry a speech audio track.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second per language","label":"Video translation","value":"$0.11634"}],"unit_pricing":[],"limits":{"note":"**Languages**\n\nen, zh_cn, ja, ko, pt, pt_br, es, es_419, de, fr, it, ru, th, ar, tr, vi, id, ta, ml, kn, gu, pa_in, sd_in, hi\n\n**Controls**\n\nSupports source video, a list of target languages, and an option to return the re-timed subtitle track for each language.\n\n**Limits**\n\n- Source video up to 300MB and 5 minutes\n- The video must carry a speech audio track\n- One dubbed video is returned per requested language\n\n**Billing**\n\n- Charged per second of source video multiplied by the number of target languages, with a 10 second minimum. Three languages on a 30 second video bill 90 seconds.\n- A request rejected before generation is not billed."},"notes":"**Languages**\n\nen, zh_cn, ja, ko, pt, pt_br, es, es_419, de, fr, it, ru, th, ar, tr, vi, id, ta, ml, kn, gu, pa_in, sd_in, hi\n\n**Controls**\n\nSupports source video, a list of target languages, and an option to return the re-timed subtitle track for each language.\n\n**Limits**\n\n- Source video up to 300MB and 5 minutes\n- The video must carry a speech audio track\n- One dubbed video is returned per requested language\n\n**Billing**\n\n- Charged per second of source video multiplied by the number of target languages, with a 10 second minimum. Three languages on a 30 second video bill 90 seconds.\n- A request rejected before generation is not billed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=sonilo-video-translation","api_url":"https://docs.empiriolabs.ai/models/sonilo-video-translation","logo":"https://media.empiriolabs.ai/model-logos/sonilo-video-translation.png","status":"available"},{"id":"sonilo-audio-ducking","object":"model","created":1735689600,"owned_by":"sonilo","display_name":"Sonilo Audio Ducking","author":"sonilo","provider":"sonilo","description":"Mixes narration over a music bed, dipping the music under the voice automatically so dialogue stays clear without manual automation.","modality":"audio","type":"generation","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","video"],"input_modalities":["audio","video"],"output_modalities":["audio"],"features":["audio_in","audio_out","ducking","audio_generation","commercial_ready"],"aliases":["sonilo/sonilo-audio-ducking"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"voice_url","label":"Voice URL","type":"string","description":"Narration, dialogue, or a talking video to keep in front. In the playground, attach this file first.","required":false,"metadata":{}},{"name":"music_url","label":"Music URL","type":"string","description":"Music track to duck underneath the voice. In the playground, attach this file second.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/audio/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per generated second","label":"Audio ducking","value":"$0.0012"}],"unit_pricing":[{"unit":"second","usd":"0.0012","label":"Audio ducking"}],"limits":{"note":"**Inputs**\n\n- A voice track: narration, dialogue, or a talking video\n- A music track to sit underneath it\n\n**Controls**\n\nSupports a voice URL and a music URL. In the playground, attach the voice first and the music second.\n\n**Limits**\n\n- Each input up to 300MB\n- The voice track up to 10 minutes\n- A talking video as the voice input returns that video with the mixed audio; an audio voice input returns audio\n\n**Billing**\n\n- Charged per generated second at the catalog rate, with a 10 second minimum\n- A request rejected before generation is not billed."},"notes":"**Inputs**\n\n- A voice track: narration, dialogue, or a talking video\n- A music track to sit underneath it\n\n**Controls**\n\nSupports a voice URL and a music URL. In the playground, attach the voice first and the music second.\n\n**Limits**\n\n- Each input up to 300MB\n- The voice track up to 10 minutes\n- A talking video as the voice input returns that video with the mixed audio; an audio voice input returns audio\n\n**Billing**\n\n- Charged per generated second at the catalog rate, with a 10 second minimum\n- A request rejected before generation is not billed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=sonilo-audio-ducking","api_url":"https://docs.empiriolabs.ai/models/sonilo-audio-ducking","logo":"https://media.empiriolabs.ai/model-logos/sonilo-audio-ducking.png","status":"available"},{"id":"sonilo-proofread","object":"model","created":1735689600,"owned_by":"sonilo","display_name":"Sonilo Proofread","author":"sonilo","provider":"sonilo","description":"Transcribes a video and translates the script into 24 languages, returning editable subtitle tracks you can correct before dubbing.","modality":"text","type":"transcription","category":"transcription","category_label":null,"modality_label":null,"modalities":["text","video"],"input_modalities":["video"],"output_modalities":["text"],"features":["transcription","translation","multilingual","srt_vtt","timestamps"],"aliases":["sonilo/sonilo-proofread"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"languages","label":"Target Languages","type":"string","description":"JSON array of language codes to translate the transcript into. Billed per language. Omit it for the source transcript only. Supported: en, zh_cn, ja, ko, pt, pt_br, es, es_419, de, fr, it, ru, th, ar, tr, vi, id, ta, ml, kn, gu, pa_in, sd_in, hi.","required":false,"metadata":{}},{"name":"source_language","label":"Source Language","type":"string","description":"The language actually spoken in the video, which helps on short, noisy or mixed-language audio. Omit it to detect the language. Supported: en, zh_cn, ja, ko, pt, pt_br, es, es_419, de, fr, it, ru, th, ar, tr, vi, id, ta, ml, kn, gu, pa_in, sd_in, hi.","required":false,"metadata":{}},{"name":"video_url","label":"Video URL","type":"string","description":"Source video, as a publicly reachable URL. Up to 300MB and 5 minutes, and it must carry an audio track.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/audio/transcriptions"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second per language","label":"Proofread","value":"$0.002"}],"unit_pricing":[],"limits":{"note":"**Languages**\n\nen, zh_cn, ja, ko, pt, pt_br, es, es_419, de, fr, it, ru, th, ar, tr, vi, id, ta, ml, kn, gu, pa_in, sd_in, hi\n\n**Controls**\n\nSupports source video, a list of target languages to translate the transcript into, and an optional expected source language for short or noisy audio.\n\n**Limits**\n\n- Source video up to 300MB and 5 minutes\n- The video must carry an audio track\n- Subtitle tracks are returned inline as text, one per language, always including the source language\n\n**Billing**\n\n- Charged per second of source video multiplied by the number of target languages, with a 10 second minimum. A transcript-only request counts as one.\n- A request rejected before generation is not billed."},"notes":"**Languages**\n\nen, zh_cn, ja, ko, pt, pt_br, es, es_419, de, fr, it, ru, th, ar, tr, vi, id, ta, ml, kn, gu, pa_in, sd_in, hi\n\n**Controls**\n\nSupports source video, a list of target languages to translate the transcript into, and an optional expected source language for short or noisy audio.\n\n**Limits**\n\n- Source video up to 300MB and 5 minutes\n- The video must carry an audio track\n- Subtitle tracks are returned inline as text, one per language, always including the source language\n\n**Billing**\n\n- Charged per second of source video multiplied by the number of target languages, with a 10 second minimum. A transcript-only request counts as one.\n- A request rejected before generation is not billed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=sonilo-proofread","api_url":"https://docs.empiriolabs.ai/models/sonilo-proofread","logo":"https://media.empiriolabs.ai/model-logos/sonilo-proofread.png","status":"available"},{"id":"sonilo-video-analysis","object":"model","created":1735689600,"owned_by":"sonilo","display_name":"Sonilo Video Analysis","author":"sonilo","provider":"sonilo","description":"Reads a video and writes a timed creative brief, with a prompt per scene for music and sound design, ready to drive a later generation.","modality":"text","type":"chat","category":"video","category_label":null,"modality_label":null,"modalities":["text","video"],"input_modalities":["text","video"],"output_modalities":["text"],"features":["video","multimodal","scene_analysis"],"aliases":["sonilo/sonilo-video-analysis"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":false,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"mode","label":"Brief","type":"enum","description":"Which brief to write: a music direction, a sound design direction, or both. All three cost the same.","required":false,"metadata":{},"default":"both","options":["both","music","sfx"]},{"name":"prompt","label":"Prompt","type":"string","description":"Creative direction for the brief. Steers the music plan; the sound design plan follows the footage.","required":false,"metadata":{}},{"name":"variants_num","label":"Variants","type":"number","description":"How many alternative creative briefs to write. Each variant is billed separately.","required":false,"metadata":{},"default":1,"min":1,"max":5},{"name":"video_url","label":"Video URL","type":"string","description":"Source video to analyse, as a publicly reachable URL. Up to 300MB and 8 minutes.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/chat/completions"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"Video analysis","value":"$0.0004"}],"unit_pricing":[{"unit":"second","usd":"0.0004","label":"Video analysis"}],"limits":{"note":"**Output**\n\nReturns a written creative brief as JSON, not generated media: a time-aligned segment plan with a prompt per segment, plus one overall prompt per requested variant. Use it to direct a later music or sound effects generation.\n\n**Controls**\n\nSupports source video, creative direction, a mode selecting the music brief, the sound design brief, or both, and 1 to 5 variants.\n\n**Limits**\n\n- Source video up to 300MB and 8 minutes\n- In both mode the sound design prompt is authored once regardless of the variant count\n\n**Billing**\n\n- Charged per second of source video at the catalog rate, with a 10 second minimum\n- Each variant is billed separately\n- A request rejected before generation is not billed."},"notes":"**Output**\n\nReturns a written creative brief as JSON, not generated media: a time-aligned segment plan with a prompt per segment, plus one overall prompt per requested variant. Use it to direct a later music or sound effects generation.\n\n**Controls**\n\nSupports source video, creative direction, a mode selecting the music brief, the sound design brief, or both, and 1 to 5 variants.\n\n**Limits**\n\n- Source video up to 300MB and 8 minutes\n- In both mode the sound design prompt is authored once regardless of the variant count\n\n**Billing**\n\n- Charged per second of source video at the catalog rate, with a 10 second minimum\n- Each variant is billed separately\n- A request rejected before generation is not billed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=sonilo-video-analysis","api_url":"https://docs.empiriolabs.ai/models/sonilo-video-analysis","logo":"https://media.empiriolabs.ai/model-logos/sonilo-video-analysis.png","status":"available"},{"id":"mimo-v2-6-pro","object":"model","created":1790035200,"owned_by":"xiaomi","display_name":"MiMo V2.6 Pro","author":"xiaomi","provider":"xiaomi","description":"Trillion-parameter flagship for agentic work, with native image, video, and audio understanding and reasoning across a 1M context.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video","audio"],"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"features":["reasoning","agentic","vision","audio_in","function_calling","structured_output","web_search"],"aliases":["mimo-v2.6-pro","mimo/v2.6-pro","xiaomi/mimo-v2.6-pro"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1048576,"context_length":1048576,"max_output_tokens":131072,"model_released_at":"2026-09-22","is_new":false,"is_featured":true,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable extended thinking mode. Slower but improves reasoning-heavy tasks.","required":false,"metadata":{},"default":true},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"min":0.1,"max":10},{"name":"media_resolution","label":"Media Resolution","type":"enum","description":"Resolution at which video inputs are read. max reads finer detail and uses more input tokens.","required":false,"metadata":{"ui":{"control":"segmented","section":"Video"}},"default":"default","options":["default","max"]},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.015 to the request cost for each invoked call.","required":false,"metadata":{},"default":false},{"name":"web_search_force","label":"Web Search Force","type":"boolean","description":"Force the model to always run a web search before answering.","required":false,"metadata":{"visible_when":{"op":"eq","field":"tool_web_search","value":true},"clear_when_hidden":true},"default":false},{"name":"web_search_max_keyword","label":"Web Search Max Keyword","type":"number","description":"Max number of search queries the model can run in one request. Each query is a separate web search call.","required":false,"metadata":{"visible_when":{"op":"eq","field":"tool_web_search","value":true},"clear_when_hidden":true},"default":3,"min":1,"max":5},{"name":"web_search_limit","label":"Web Search Limit","type":"number","description":"Max number of web pages returned for each search query.","required":false,"metadata":{"visible_when":{"op":"eq","field":"tool_web_search","value":true},"clear_when_hidden":true},"default":5,"min":1,"max":10},{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 1.5 = maximum randomness.","required":false,"metadata":{},"default":1,"min":0,"max":1.5},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.95,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum tokens in the response.","required":false,"metadata":{},"default":8192,"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/mimo-v2-6-pro:generateContent"],"pricing":{"prompt":"0.000000435","completion":"0.00000087","image":"0","request":"0","input_cache_read":"0.000000435"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.435"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.87"},{"spec":"per call when invoked","label":"Web search","value":"$0.015"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.435","label":"Input"},{"unit":"1m_tokens","usd":"0.87","label":"Output"},{"unit":"call","usd":"0.015","label":"Web search"}],"limits":{"note":"Web search ($0.015/call) is charged only when invoked. Accepts text, image, video, and audio input and returns text. Thinking is on by default and can be turned off. Sustains complex autonomous workflows with 1000+ tool calls on a 1M context.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes tools (web search, code interpreter, etc.) inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape, exact field names, units, and which tools appear can vary slightly per provider:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nThe tool counts are already factored into `cost_usd`, they are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=mimo-v2-6-pro","api_url":"https://docs.empiriolabs.ai/models/mimo-v2-6-pro","logo":"https://media.empiriolabs.ai/model-logos/mimo-v2-6-pro.png","status":"available"},{"id":"mimo-v2-6-flash","object":"model","created":1790035200,"owned_by":"xiaomi","display_name":"MiMo V2.6 Flash","author":"xiaomi","provider":"xiaomi","description":"Low-cost full-modality reasoner with native image, video, and audio understanding on a 1M context, built for high-frequency production workloads.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video","audio"],"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"features":["reasoning","vision","audio_in","function_calling","structured_output","web_search"],"aliases":["mimo-v2.6-flash","mimo/v2.6-flash","xiaomi/mimo-v2.6-flash"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1048576,"context_length":1048576,"max_output_tokens":131072,"model_released_at":"2026-09-22","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable extended thinking mode. Slower but improves reasoning-heavy tasks. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"min":0.1,"max":10},{"name":"media_resolution","label":"Media Resolution","type":"enum","description":"Resolution at which video inputs are read. max reads finer detail and uses more input tokens.","required":false,"metadata":{"ui":{"control":"segmented","section":"Video"}},"default":"default","options":["default","max"]},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information. Adds $0.015 to the request cost for each invoked call.","required":false,"metadata":{},"default":false},{"name":"web_search_force","label":"Web Search Force","type":"boolean","description":"Force the model to always run a web search before answering.","required":false,"metadata":{"visible_when":{"op":"eq","field":"tool_web_search","value":true},"clear_when_hidden":true},"default":false},{"name":"web_search_max_keyword","label":"Web Search Max Keyword","type":"number","description":"Max number of search queries the model can run in one request. Each query is a separate web search call.","required":false,"metadata":{"visible_when":{"op":"eq","field":"tool_web_search","value":true},"clear_when_hidden":true},"default":3,"min":1,"max":5},{"name":"web_search_limit","label":"Web Search Limit","type":"number","description":"Max number of web pages returned for each search query.","required":false,"metadata":{"visible_when":{"op":"eq","field":"tool_web_search","value":true},"clear_when_hidden":true},"default":5,"min":1,"max":10},{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 1.5 = maximum randomness.","required":false,"metadata":{},"default":1,"min":0,"max":1.5},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.95,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum tokens in the response.","required":false,"metadata":{},"default":8192,"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without EmpirioLabs formatting: citations stay as plain [N] markers and no References block is added.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/mimo-v2-6-flash:generateContent"],"pricing":{"prompt":"0.00000014","completion":"0.00000028","image":"0","request":"0","input_cache_read":"0.00000014"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.14"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.28"},{"spec":"per call when invoked","label":"Web search","value":"$0.015"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.14","label":"Input"},{"unit":"1m_tokens","usd":"0.28","label":"Output"},{"unit":"call","usd":"0.015","label":"Web search"}],"limits":{"note":"Web search ($0.015/call) is charged only when invoked. Accepts text, image, video, and audio input and returns text. Thinking is on by default and can be turned off.","tool_usage_note":"**Per-tool billing (`usage.tool_usage`)**\n\nWhen this model invokes tools (web search, code interpreter, etc.) inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. The example below shows the shape, exact field names, units, and which tools appear can vary slightly per provider:\n\n```json\n\"usage\": {\n  \"prompt_tokens\": 123,\n  \"completion_tokens\": 456,\n  \"cost_usd\": 0.0042,\n  \"tool_usage\": {\"web_search\": 3, \"code_interpreter\": 1}\n}\n```\n\nThe tool counts are already factored into `cost_usd`, they are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=mimo-v2-6-flash","api_url":"https://docs.empiriolabs.ai/models/mimo-v2-6-flash","logo":"https://media.empiriolabs.ai/model-logos/mimo-v2-6-flash.png","status":"available"},{"id":"mimo-v2-6-pro-ultraspeed","object":"model","created":1790035200,"owned_by":"xiaomi","display_name":"MiMo V2.6 Pro UltraSpeed","author":"xiaomi","provider":"xiaomi","description":"High-throughput build of the trillion-parameter flagship, matching its full-modality reasoning while generating output substantially faster.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image","video","audio"],"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"features":["reasoning","agentic","vision","audio_in","function_calling","structured_output"],"aliases":["mimo-v2.6-pro-ultraspeed","mimo/v2.6-pro-ultraspeed","xiaomi/mimo-v2.6-pro-ultraspeed"],"structured_output":"json_schema","native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":1048576,"context_length":1048576,"max_output_tokens":131072,"model_released_at":"2026-09-22","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable extended thinking mode. Slower but improves reasoning-heavy tasks. A request that forces a tool call runs without reasoning unless it sets enable_thinking.","required":false,"metadata":{"forced_tool_choice_turns_thinking_off":true},"default":true},{"name":"video_fps","label":"Video FPS","type":"number","description":"Frames per second to sample from video inputs. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Video"}},"min":0.1,"max":10},{"name":"media_resolution","label":"Media Resolution","type":"enum","description":"Resolution at which video inputs are read. max reads finer detail and uses more input tokens.","required":false,"metadata":{"ui":{"control":"segmented","section":"Video"}},"default":"default","options":["default","max"]},{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 1.5 = maximum randomness.","required":false,"metadata":{},"default":1,"min":0,"max":1.5},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.95,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum tokens in the response.","required":false,"metadata":{},"default":8192,"min":1,"max":131072},{"name":"stop","label":"Stop","type":"string","description":"Up to 4 strings where the model will stop generating further tokens.","required":false,"metadata":{"control":"stop-sequences"}},{"name":"response_format","label":"Structured Output","type":"enum","description":"Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.","required":false,"metadata":{"control":"structured-output","so_tier":"json_schema"}},{"name":"web_search_linkup","label":"Web Search (Linkup)","type":"boolean","description":"Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.","required":false,"metadata":{"group":"tools","powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return the answer without the Sources list that web search adds.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/mimo-v2-6-pro-ultraspeed:generateContent"],"pricing":{"prompt":"0.00000435","completion":"0.0000087","image":"0","request":"0","input_cache_read":"0.00000435"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$4.35"},{"spec":"per 1M generated tokens","label":"Output","value":"$8.70"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"unit_pricing":[{"unit":"1m_tokens","usd":"4.35","label":"Input"},{"unit":"1m_tokens","usd":"8.7","label":"Output"},{"unit":"call","usd":"0.013","label":"Web Search (Linkup)"}],"limits":{"note":"Accepts text, image, video, and audio input and returns text. Thinking is on by default and can be turned off. Optional Linkup web search is billed only when invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=mimo-v2-6-pro-ultraspeed","api_url":"https://docs.empiriolabs.ai/models/mimo-v2-6-pro-ultraspeed","logo":"https://media.empiriolabs.ai/model-logos/mimo-v2-6-pro-ultraspeed.png","status":"available"},{"id":"qwen3-8-omni-flash-realtime","object":"model","created":1789948800,"owned_by":"alibaba","display_name":"Qwen3.8 Omni Flash Realtime","author":"alibaba","provider":"alibaba","description":"Speech and live video frames in, speech out over one socket, with 56 voices, tool calling during the conversation, and separate text and audio token rates.","modality":"audio","type":"realtime","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text","image","video"],"input_modalities":["audio","text","image","video"],"output_modalities":["audio","text"],"features":["realtime","speech_to_speech","audio_in","audio_out","video","function_calling","multilingual"],"aliases":["qwen3.8-omni-flash-realtime","alibaba/qwen3-8-omni-flash-realtime"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":196608,"context_length":196608,"max_output_tokens":65536,"model_released_at":"2026-09-21","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"voice","label":"Voice","type":"enum","description":"Speaking voice for the session. Set it with session.update before the model produces any audio. These voices are specific to this model.","required":false,"metadata":{},"default":"Tina","options":["Tina","Cindy","Liora Mira","Raymond","Zane","Katerina","Ryan","Mia","Cici","Theo Calm","Serena","Maia","Evan","Qiao","Momo","Wil","Angel","Li Cassian","Joyner","Gold","Jennifer","Aiden","Mione","Sunny","Dylan","Eric","Peter","Joseph Chen","Marcus","Li","Rocky","Kiki","Sohee","Eliška","Alek","Arda","Dolce","Lenn","Ono Anna","Sonrisa","Bodega","Andre","Radio Gol","Rizky","Roya","Hana","Jakub","Griet","Marina","Siiri","Ingrid","Sigga","Bea","Chloe","Emilien","longanlingxin"]},{"name":"instructions","label":"Instructions","type":"string","description":"System guidance for how the model should behave and speak during the conversation.","required":false,"metadata":{}},{"name":"modalities","label":"Modalities","type":"string","description":"Which output types the model returns for a turn. Drop audio for a text-only reply.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":["text","audio"]},{"name":"input_audio_format","label":"Input audio format","type":"enum","description":"Encoding of the audio you append to the input buffer: base64 16-bit PCM at 16 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"pcm16","options":["pcm16"]},{"name":"output_audio_format","label":"Output audio format","type":"enum","description":"Encoding of the audio the model streams back: 16-bit PCM at 24 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":24000},"default":"pcm24","options":["pcm24"]},{"name":"turn_detection","label":"Turn detection","type":"string","description":"Voice activity detection: decides when you have finished speaking and the model should reply. It is on by default as server_vad, which ends your turn after a pause. semantic_vad also judges whether you have finished speaking, so filler sounds and background noise do not end your turn, and semantic_vad_ec does the same and lets you interrupt a reply more readily. threshold is a number from -1 to 1, 0.5 by default; a higher value needs clearer, louder speech to count. silence_duration_ms, from 200 to 6000 and 800 by default, is how long a pause must last to end your turn. idle_timeout_ms, from 5000 to 30000 with server_vad, makes the model speak again when you stay silent that long after its reply. Set turn_detection to null to end each turn yourself with input_audio_buffer.commit and response.create.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":{"type":"server_vad"}},{"name":"max_response_output_tokens","label":"Max output tokens","type":"number","description":"Largest number of output tokens one reply may use: from 1 to 65536, where a larger number runs at 65536, or \"inf\" for the model's own limit. Also accepted as max_output_tokens. When omitted, the model's own default applies.","required":false,"metadata":{"aliases":["max_output_tokens"]},"min":1,"max":65536},{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 is deterministic and 1.99 is maximum randomness. When omitted, the model's own default applies.","required":false,"metadata":{},"min":0,"max":1.99},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower values make outputs more focused. When omitted, the model's own default applies.","required":false,"metadata":{},"min":0.01,"max":1},{"name":"top_k","label":"Top K","type":"number","description":"Sample only from the K most likely tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":1,"max":100},{"name":"repetition_penalty","label":"Repetition Penalty","type":"number","description":"Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":0.1,"max":2},{"name":"presence_penalty","label":"Presence Penalty","type":"number","description":"Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"min":-2,"max":2},{"name":"seed","label":"Seed","type":"number","description":"Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced sampling"}},"min":0,"max":2147483647},{"name":"video_representation_compact","label":"Compact video","type":"enum","description":"How the model reads the video frames you send: none keeps full detail, and normal reads the same frames for a quarter of the input tokens when fine detail is not needed. When omitted, frames keep full detail. Set it before the first audio; it cannot change after that.","required":false,"metadata":{"ui":{"hide_in_playground":true},"option_labels":{"none":"Full detail","normal":"Compact"}},"options":["none","normal"]}],"supported_endpoints":["WEBSOCKET /v1/realtime"],"pricing":{"prompt":"0.00000046","completion":"0.0000014","image":"0","request":"0","input_cache_read":"0.00000046"},"pricing_rows":[{"spec":"per 1M audio input tokens","label":"Input: audio","value":"$1.86"},{"spec":"per 1M prompt tokens","label":"Input","value":"$0.46"},{"spec":"per 1M generated tokens","label":"Output","value":"$1.40"},{"spec":"per 1M generated audio tokens","label":"Output: audio","value":"$3.74"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.86","label":"Input: audio"},{"unit":"1m_tokens","usd":"0.46","label":"Input"},{"unit":"1m_tokens","usd":"1.4","label":"Output"},{"unit":"1m_tokens","usd":"3.74","label":"Output: audio"}],"limits":{"note":"**Connecting**\n\nFull-duplex voice over a WebSocket at `wss://api.empiriolabs.ai/v1/realtime?model=qwen3-8-omni-flash-realtime`, authenticated with the ordinary Authorization Bearer header. Configure the session with `session.update` over the socket: voice, instructions, modalities, turn detection, sampling and the reply length limit, `max_response_output_tokens`.\n\n**Sending audio and video**\n\n- Append microphone audio as `input_audio_buffer.append` events.\n- Append live video frames as `input_image_buffer.append` events. Frames are not message content, so an image inside a conversation item is rejected.\n- Set `video_representation_compact` to `normal` before the first audio to read the same frames for a quarter of the input tokens.\n- Voice activity detection decides when you have stopped speaking, so keep streaming for about a second after the speech ends.\n\n**Voices**\n\nThe voices on this model are not the same set as the Qwen3.5 Omni realtime models. Pick one from the voice list rather than carrying a voice across, or leave it unset and the default is supplied for you.\n\n**Billing**\n\nAudio and text tokens are priced separately in both directions, and each completed turn is billed on its own from the usage the model reports."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-8-omni-flash-realtime","api_url":"https://docs.empiriolabs.ai/models/qwen3-8-omni-flash-realtime","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen-audio-3-1-realtime-plus","object":"model","created":1789862400,"owned_by":"alibaba","display_name":"Qwen Audio 3.1 Realtime Plus","author":"alibaba","provider":"alibaba","description":"Duplex speech conversation over one socket, with 88 voices, tool calling, and separate text and audio token rates.","modality":"audio","type":"realtime","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio","text"],"output_modalities":["audio","text"],"features":["realtime","speech_to_speech","audio_in","audio_out","function_calling","multilingual"],"aliases":["qwen-audio-3.1-realtime-plus","alibaba/qwen-audio-3-1-realtime-plus"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":245760,"context_length":245760,"max_output_tokens":16384,"model_released_at":"2026-09-20","is_new":false,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"voice","label":"Voice","type":"enum","description":"Speaking voice for the session. Set it with session.update before the model produces any audio. These voices are specific to this model.","required":false,"metadata":{},"default":"longanqian_v3.1","options":["longanqian_v3.1","longanhuan_v3.1","longanlingxin_v3.1","longanfengyue_v3.1","xunanchuan_v3.1","beth_v3.1","betty_v3.1","cally_v3.1","longanqian","longanlingxin","longanlufeng","longanlingxi","longanxiaoxin","longanfengyue","longanyuanfei","longanhuan_v3.6","longjielidou_v3.6","longpaopao_v3.6","longhuohuo_v3.6","longchuanshu_v3.6","loongmary","loongeva_v3.6","loongjohn","daniel","echo","hannah","sherry","yuxiaoyun_v3.1","qiaoxiaojiao_v3.1","xiaxiaochen_v3.1","anmingyuan_v3.1","wenhuaiqing_v3.1","anxiaolan_v3.1","xieshurou_v3.1","baiqinglan_v3.1","xuyuyuan_v3.1","anruorou_v3.1","wenhuaizhi_v3.1","xiaoxingzhi_v3.1","guyunshu_v3.1","huozhuoshi_v3.1","yeqinghe_v3.1","yunhuanhuan_v3.1","xuxiaoqiao_v3.1","baianran_v3.1","xuyanchu_v3.1","yezhiqing_v3.1","andi_v3.1","anyuqing_v3.1","emily_v3.1","luna_v3.1","eric_v3.1","luca_v3.1","abby_v3.1","annie_v3.1","ava_v3.1","cindy_v3.1","donna_v3.1","andy_v3.1","brian_v3.1","david_v3.1","longanyuanfei_v3.1","longjielidou_v3.1","longanlingxi_v3.1","longhuohuo_v3.1","longyingtao_v3.1","longanya_v3.1","longwan_v3.1","longxing_v3.1","longhua_v3.1","longhan_v3.1","longanzhi_v3.1","longzhe_v3.1","longanyang_v3.1","libai_v3.1","longling_v3.1","longniuniu_v3.1","longshanshan_v3.1","longpaopao_v3.1","loongstella_v3.1","longyuan_v3.1","longmiao_v3.1","longsanshu_v3.1","longanli_v3.1","longanwen_v3.1","longanlang_v3.1","longxiaoxia_v3.1","longanchong_v3.1"]},{"name":"instructions","label":"Instructions","type":"string","description":"System guidance for how the model should behave and speak during the conversation.","required":false,"metadata":{}},{"name":"input_language","label":"Input language","type":"enum","description":"Language you speak. The transcript of your speech is written in it; auto detects it. Also accepted as input_audio_transcription.language.","required":false,"metadata":{"option_labels":{"ar":"Arabic","de":"German","en":"English","es":"Spanish","fr":"French","id":"Indonesian","it":"Italian","ja":"Japanese","ko":"Korean","pt":"Portuguese","ru":"Russian","th":"Thai","vi":"Vietnamese","zh":"Chinese","auto":"Auto-detect"}},"default":"auto","options":["auto","zh","en","ja","ko","vi","th","id","ar","fr","de","es","pt","ru","it"]},{"name":"output_language","label":"Output language","type":"enum","description":"Language the spoken reply is read in, for example Japanese or Chinese for the same characters. It does not translate the reply: ask for its language in your instructions. auto lets the model choose. Also accepted as output_audio.language.","required":false,"metadata":{"option_labels":{"ar":"Arabic","de":"German","en":"English","es":"Spanish","fr":"French","id":"Indonesian","it":"Italian","ja":"Japanese","ko":"Korean","pt":"Portuguese","ru":"Russian","th":"Thai","vi":"Vietnamese","zh":"Chinese","auto":"Automatic"}},"default":"auto","options":["auto","zh","en","ja","ko","vi","th","id","ar","fr","de","es","pt","ru","it"]},{"name":"speed","label":"Speed","type":"number","description":"Speaking rate of the reply, from 0.5 to 2. Lower values slow the speech and higher values speed it up. Also accepted as speech_rate. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider"}},"min":0.5,"max":2},{"name":"enable_speech_emotion","label":"Expressive delivery","type":"boolean","description":"More pronounced emotion in the spoken reply. Turn it off for a more even delivery.","required":false,"metadata":{},"default":true},{"name":"max_history_turns","label":"History turns","type":"number","description":"How many earlier exchanges the model reads for each reply, from 1 to 50. Fewer exchanges use fewer input tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number"}},"min":1,"max":50},{"name":"modalities","label":"Modalities","type":"string","description":"Which output types the model returns for a turn. Drop audio for a text-only reply.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":["text","audio"]},{"name":"input_audio_format","label":"Input audio format","type":"enum","description":"Encoding of the audio you append to the input buffer: base64 16-bit PCM at 16 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"pcm16","options":["pcm16"]},{"name":"output_audio_format","label":"Output audio format","type":"enum","description":"Encoding of the audio the model streams back: 16-bit PCM at 24 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":24000},"default":"pcm24","options":["pcm24"]},{"name":"turn_detection","label":"Turn detection","type":"string","description":"Voice activity detection: decides when you have finished speaking and the model should reply. It is on by default as server_vad, which ends your turn after a pause. smart_turn also weighs what you said, so filler sounds such as um do not end your turn or interrupt the reply, and smart_turn_v2 also answers bystanders and side remarks less often. threshold is a number from -1 to 1, 0.5 by default; a higher value needs clearer, louder speech to count. With server_vad, silence_duration_ms, from 200 to 6000 and 800 by default, is how long a pause must last to end your turn. Set turn_detection to null to end each turn yourself with input_audio_buffer.commit and response.create.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":{"type":"server_vad"}}],"supported_endpoints":["WEBSOCKET /v1/realtime"],"pricing":{"prompt":"0.0000016","completion":"0.0000128","image":"0","request":"0","input_cache_read":"0.0000016"},"pricing_rows":[{"spec":"per 1M audio input tokens","label":"Input: audio","value":"$12.80"},{"spec":"per 1M prompt tokens","label":"Input","value":"$1.60"},{"spec":"per 1M generated tokens, text-only replies","label":"Output","value":"$12.80"},{"spec":"per 1M generated audio tokens","label":"Output: audio","value":"$48.00"}],"unit_pricing":[{"unit":"1m_tokens","usd":"12.8","label":"Input: audio"},{"unit":"1m_tokens","usd":"1.6","label":"Input"},{"unit":"1m_tokens","usd":"48","label":"Output: audio"}],"limits":{"note":"**Connecting**\n\nFull-duplex voice over a WebSocket at `wss://api.empiriolabs.ai/v1/realtime?model=qwen-audio-3-1-realtime-plus`, authenticated with the ordinary Authorization Bearer header. Configure the session with `session.update` over the socket: voice, instructions, modalities, turn detection, languages and delivery.\n\n**Sending audio**\n\n- Append microphone audio as `input_audio_buffer.append` events.\n- Voice activity detection decides when you have stopped speaking, so keep streaming for about a second after the speech ends.\n\n**Language and delivery**\n\nSet `input_language` to the language you speak, which the transcript of your speech is written in, and `output_language` to the language the spoken reply is read in. Each takes auto or one of zh, en, ja, ko, vi, th, id, ar, fr, de, es, pt, ru and it. The output language does not translate the reply, so ask for its language in your instructions too. `speed` (0.5 to 2) sets the speaking rate, `enable_speech_emotion` the expressive delivery, and `max_history_turns` (1 to 50) how many earlier exchanges the model reads.\n\n**Voices**\n\nThe voices on this model are its own set. Pick one from the voice list rather than carrying a voice across from another model, or leave it unset and the default is supplied for you.\n\n**Billing**\n\nAudio and text tokens are priced separately in both directions. A spoken reply is billed for its audio output tokens only, and the text output rate applies to replies with no audio. Each completed turn is billed on its own from the usage the model reports."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen-audio-3-1-realtime-plus","api_url":"https://docs.empiriolabs.ai/models/qwen-audio-3-1-realtime-plus","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"gemini-3-8-flash-tts","object":"model","created":1790035200,"owned_by":"google","display_name":"Gemini 3.8 Flash TTS","author":"google","provider":"google","description":"Expressive speech with inline vocal tags, style direction, and two-speaker dialogue, across 130 languages and a library of more than 2,000 voices.","modality":"audio","type":"tts","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["text_to_speech","multi_speaker","multilingual","voice_tags","voice_control","streaming","voice_cloning"],"aliases":["gemini-3.8-flash-tts","google/gemini-3.8-flash-tts"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-09-22","is_new":true,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Text to convert to speech. For multi-speaker mode, prefix lines with Speaker1: / Speaker2:. Up to 5,000 characters. Put delivery direction in style_prompt, and place these vocal tags inline where the sound should happen: <argh>, <breath>, <heavy breath>, <exhales>, <cackle>, <cheer>, <chuckle>, <chuckles>, <cough>, <cry>, <gasp>, <giggle>, <groan>, <growl>, <grunt>, <grr>, <hiss>, <laugh>, <laughter>, <moan>, <pant>, <pff>, <phew>, <scream>, <shout>, <shriek>, <sigh>, <sighs>, <sneeze>, <snicker>, <snort>, <sob>, <throat-clearing>, <tsk>, <whimper>, <whispers>, <whispering>, <yawn>, <short pause>, <long pause>. Capitalize a word to stress it, and wrap a listener reaction in pipes, for example |mm-hmm|.","required":true,"metadata":{},"max":5000},{"name":"mode","label":"Mode","type":"enum","description":"single = one voice, multi = two-voice dialogue (uses voice + voice2 + speaker names).","required":false,"metadata":{},"default":"single","options":["single","multi"]},{"name":"language","label":"Language","type":"string","description":"Optional BCP-47 language tag (en-US, es-ES, etc.). The language of the text is detected automatically. The 30 listed voices speak every supported language; a library voice must be used with its own language.","required":false,"metadata":{}},{"name":"voice","label":"Voice","type":"enum","description":"Primary voice name (e.g. Kore, Puck, Aoede). Leave blank for the default. These 30 voices speak every supported language. GET /v1/voices lists the full library of more than 2,000 voices, and any voice id it returns is also accepted here. custom clones a voice from voice_audio_url and voice_consent_audio_url, and the response's voice_id then works here or in voice2 for 7 days, for the account that created it.","required":false,"metadata":{"saved_voices":"session","option_labels":{"custom":"Custom"}},"default":"Charon","options":["Zephyr","Puck","Charon","Kore","Fenrir","Leda","Orus","Aoede","Callirrhoe","Autonoe","Enceladus","Iapetus","Umbriel","Algieba","Despina","Erinome","Algenib","Rasalgethi","Laomedeia","Achernar","Alnilam","Schedar","Gacrux","Pulcherrima","Achird","Zubenelgenubi","Vindemiatrix","Sadachbia","Sadaltager","Sulafat","custom"]},{"name":"voice_audio_url","label":"Reference audio URL","type":"string","description":"voice=custom only: an https URL to a 10 to 30 second recording of clean, natural speech from the voice to clone (WAV, MP3, M4A, OGG, WEBM or FLAC). Record it in a quiet room, on the same microphone as the consent recording.","required":false,"metadata":{"control":"audio-clip","max_seconds":30,"min_seconds":10,"visible_when":{"op":"eq","field":"voice","value":"custom"},"required_when":{"op":"eq","field":"voice","value":"custom"},"clear_when_hidden":true}},{"name":"voice_consent_audio_url","label":"Consent audio URL","type":"string","description":"voice=custom only: an https URL to the same speaker reading this statement aloud: \"I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model.\" The same statement in any of 30 languages is accepted; consent_statements in this parameter's metadata lists each one.","required":false,"metadata":{"control":"audio-clip","max_seconds":30,"visible_when":{"op":"eq","field":"voice","value":"custom"},"required_when":{"op":"eq","field":"voice","value":"custom"},"clear_when_hidden":true,"consent_statements":{"ar-XA":"أنا مالك هذا الصوت وأوافق على أن تستخدم Google هذا الصوت لإنشاء نموذج صوتي اصطناعي.","bn-IN":"আমি এই ভয়েসের মালিক এবং আমি একটি সিন্থেটিক ভয়েস মডেল তৈরি করতে এই ভয়েস ব্যবহার করে Google-এর সাথে সম্মতি দিচ্ছি।","de-DE":"Ich bin der Eigentümer dieser Stimme und bin damit einverstanden, dass Google diese Stimme zur Erstellung eines synthetischen Stimmmodells verwendet.","en-AU":"I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model.","en-GB":"I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model.","en-IN":"I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model.","en-US":"I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model.","es-ES":"Soy el propietario de esta voz y doy mi consentimiento para que Google la utilice para crear un modelo de voz sintética.","es-US":"Soy el propietario de esta voz y doy mi consentimiento para que Google la utilice para crear un modelo de voz sintética.","fr-CA":"Je suis le propriétaire de cette voix et j'autorise Google à utiliser cette voix pour créer un modèle de voix synthétique.","fr-FR":"Je suis le propriétaire de cette voix et j'autorise Google à utiliser cette voix pour créer un modèle de voix synthétique.","gu-IN":"હું આ વોઈસનો માલિક છું અને સિન્થેટિક વોઈસ મોડલ બનાવવા માટે આ વોઈસનો ઉપયોગ કરીને google ને હું સંમતિ આપું છું","hi-IN":"मैं इस आवाज का मालिक हूं और मैं सिंथेटिक आवाज मॉडल बनाने के लिए Google को इस आवाज का उपयोग करने की सहमति देता हूं","id-ID":"Saya pemilik suara ini dan saya menyetujui Google menggunakan suara ini untuk membuat model suara sintetis.","it-IT":"Sono il proprietario di questa voce e acconsento che Google la utilizzi per creare un modello di voce sintetica.","ja-JP":"私はこの音声の所有者であり、Googleがこの音声を使用して音声合成モデルを作成することを承認します。","kn-IN":"ನಾನು ಈ ಧ್ವನಿಯ ಮಾಲಿಕ ಮತ್ತು ಸಂಶ್ಲೇಷಿತ ಧ್ವನಿ ಮಾದರಿಯನ್ನು ರಚಿಸಲು ಈ ಧ್ವನಿಯನ್ನು ಬಳಸಿಕೊಂಡುಗೂಗಲ್ ಗೆ ನಾನು ಸಮ್ಮತಿಸುತ್ತೇನೆ.","ko-KR":"나는 이 음성의 소유자이며 구글이 이 음성을 사용하여 음성 합성 모델을 생성할 것을 허용합니다.","ml-IN":"ഈ ശബ്ദത്തിന്റെ ഉടമ ഞാനാണ്, ഒരു സിന്തറ്റിക് വോയ്സ് മോഡൽ സൃഷ്ടിക്കാൻ ഈ ശബ്ദം ഉപയോഗിക്കുന്നതിന് ഞാൻ Google-ന് സമ്മതം നൽകുന്നു.","mr-IN":"मी या आवाजाचा मालक आहे आणि सिंथेटिक व्हॉइस मॉडेल तयार करण्यासाठी हा आवाज वापरण्यासाठी मी Google ला संमती देतो","nl-NL":"Ik ben de eigenaar van deze stem en ik geef Google toestemming om deze stem te gebruiken om een synthetisch stemmodel te maken.","pl-PL":"Jestem właścicielem tego głosu i wyrażam zgodę na wykorzystanie go przez Google w celu utworzenia syntetycznego modelu głosu.","pt-BR":"Eu sou o proprietário desta voz e autorizo o Google a usá-la para criar um modelo de voz sintética.","ru-RU":"Я являюсь владельцем этого голоса и даю согласие Google на использование этого голоса для создания модели синтетического голоса.","ta-IN":"நான் இந்த குரலின் உரிமையாளர் மற்றும் செயற்கை குரல் மாதிரியை உருவாக்க இந்த குரலை பயன்படுத்த குகல்க்கு நான் ஒப்புக்கொள்கிறேன்.","te-IN":"నేను ఈ వాయిస్ యజమానిని మరియు సింతటిక్ వాయిస్ మోడల్ ని రూపొందించడానికి ఈ వాయిస్ ని ఉపయోగించడానికి googleకి నేను సమ్మతిస్తున్నాను.","th-TH":"ฉันเป็นเจ้าของเสียงนี้ และฉันยินยอมให้ Google ใช้เสียงนี้เพื่อสร้างแบบจำลองเสียงสังเคราะห์","tr-TR":"Bu sesin sahibi benim ve Google'ın bu sesi kullanarak sentetik bir ses modeli oluşturmasına izin veriyorum.","vi-VN":"Tôi là chủ sở hữu giọng nói này và tôi đồng ý cho Google sử dụng giọng nói này để tạo mô hình giọng nói tổng hợp.","zh-CN":"我是此声音的拥有者并授权谷歌使用此声音创建语音合成模型"}}},{"name":"voice2","label":"Voice2","type":"enum","description":"Second voice name for multi-speaker mode. Library and cloned voice ids are also accepted.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"multi"},"clear_when_hidden":true},"default":"Kore","options":["Zephyr","Puck","Charon","Kore","Fenrir","Leda","Orus","Aoede","Callirrhoe","Autonoe","Enceladus","Iapetus","Umbriel","Algieba","Despina","Erinome","Algenib","Rasalgethi","Laomedeia","Achernar","Alnilam","Schedar","Gacrux","Pulcherrima","Achird","Zubenelgenubi","Vindemiatrix","Sadachbia","Sadaltager","Sulafat"]},{"name":"speaker1_name","label":"Speaker1 Name","type":"string","description":"Display name used in the input prefix for speaker 1 (default: Speaker1).","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"multi"},"clear_when_hidden":true},"default":"Speaker1"},{"name":"speaker2_name","label":"Speaker2 Name","type":"string","description":"Display name used in the input prefix for speaker 2 (default: Speaker2).","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"multi"},"clear_when_hidden":true},"default":"Speaker2"},{"name":"output_format","label":"Output Format","type":"enum","description":"Audio file format: WAV, MP3, OGG (Opus), or ALAW / MULAW for telephony.","required":false,"metadata":{},"default":"WAV","options":["WAV","MP3","OGG","ALAW","MULAW"]},{"name":"speed","label":"Speed","type":"number","description":"Playback rate. 1.0 = natural; <1 slower, >1 faster. Not available on POST /v1/audio/speech:stream.","required":false,"metadata":{},"default":1,"min":0.25,"max":2},{"name":"volume_gain","label":"Volume Gain","type":"number","description":"Output gain in dB. 0 = unchanged.","required":false,"metadata":{},"default":0,"min":-96,"max":16},{"name":"sample_rate","label":"Sample Rate","type":"enum","description":"Output sample rate in Hz (8000, 16000, 22050, 24000, 44100, or 48000). OGG output uses the nearest of 8000, 16000, 24000 or 48000.","required":false,"metadata":{},"default":"24000","options":["8000","16000","22050","24000","44100","48000"]},{"name":"style_prompt","label":"Style Prompt","type":"string","description":"Natural-language style direction (e.g. \"warm, conversational\" or \"newscaster, serious\").","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/audio/speech","POST /v1/audio/speech:stream","GET /v1/voices"],"pricing":{"prompt":"0.0000026","completion":"0.0000468","image":"0","request":"0","input_cache_read":"0.0000026"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$2.60"},{"spec":"per 1M generated tokens","label":"Output","value":"$46.80"}],"unit_pricing":[{"unit":"1m_tokens","usd":"2.6","label":"Input"},{"unit":"1m_tokens","usd":"46.8","label":"Output"}],"limits":{"note":"**Limits**\n\n- Text: up to 5,000 characters per request\n- Audio billing: 32 output tokens per second of generated audio\n- 130 languages. The language of the text is detected automatically.\n\n**Voices**\n\n- The 30 voices in the `voice` list speak every supported language.\n- `GET /v1/voices?model=gemini-3-8-flash-tts` lists the full library of more than 2,000 voices across 30 locales, with the language, accent, gender, pitch, and a description of each. Filter it with `language`, `gender`, `pitch`, or `q`. Any id it returns works as `voice` or `voice2`; when you also set `language`, use the voice's own language.\n\n**Custom voices**\n\n- Set `voice` to `custom` and pass two recordings of the same adult speaker as https URLs: `voice_audio_url`, 10 to 30 seconds of natural speech, and `voice_consent_audio_url`, the speaker reading \"I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model.\" The statement is accepted in 30 languages; `consent_statements` on that parameter lists each wording.\n- Both must be recordings of a real person, in a quiet room on the same microphone. AI-generated audio is not accepted. WAV, MP3, M4A, OGG, WEBM and FLAC are accepted, up to 15 MB each.\n- The response includes `voice_id` and `voice_id_expires_at`. Pass the `voice_id` as `voice` or `voice2` to reuse the voice for 7 days without new recordings. A `voice_id` works only for the account that created it.\n- This model keeps no list of custom voices, so keep the `voice_id` from the response. A custom voice ends when its id expires, so there is nothing to delete.\n- In the Playground, set Voice to Custom to use a voice made in the same tab again, or copy its id.\n\n**Delivery direction**\n\n- Put direction for the whole passage in `style_prompt` rather than in the text, for example \"warm, unhurried, and reassuring\".\n- Place vocal tags inline where the sound should happen. Use these English tags even when the text is in another language:\n\n```text\n<argh> <breath> <heavy breath> <exhales> <cackle> <cheer> <chuckle> <chuckles> <cough> <cry> <gasp> <giggle> <groan> <growl> <grunt> <grr> <hiss> <laugh> <laughter> <moan> <pant> <pff> <phew> <scream> <shout> <shriek> <sigh> <sighs> <sneeze> <snicker> <snort> <sob> <throat-clearing> <tsk> <whimper> <whispers> <whispering> <yawn> <short pause> <long pause>\n```\n\n- Capitalize a word to stress it. Wrap a listener reaction in pipes, for example |mm-hmm|, to add it without starting a new turn.\n\n**Multi-speaker**\n\n- Up to two speakers per request. Start each line with a speaker name and a colon, for example Speaker1: and Speaker2:. The names must match `speaker1_name` and `speaker2_name`.\n\n**Output**\n\n- WAV, MP3, OGG (Opus), ALAW, or MULAW, at 8,000 to 48,000 Hz.\n- `POST /v1/audio/speech:stream` sends 16-bit PCM chunks at 24,000 Hz while the audio is generated, then the complete file in the requested format. `speed` is available on `POST /v1/audio/speech` only."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=gemini-3-8-flash-tts","api_url":"https://docs.empiriolabs.ai/models/gemini-3-8-flash-tts","logo":"https://media.empiriolabs.ai/model-logos/gemini-3-8-flash-tts.png","status":"available"},{"id":"gemini-3-8-flash-lite-tts","object":"model","created":1790035200,"owned_by":"google","display_name":"Gemini 3.8 Flash-Lite TTS","author":"google","provider":"google","description":"Cost-efficient speech for voice agents and dubbing, with streaming, vocal tags, and two-speaker dialogue across 101 languages and 2,000+ voices.","modality":"audio","type":"tts","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["text_to_speech","multi_speaker","multilingual","voice_tags","voice_control","streaming","voice_cloning"],"aliases":["gemini-3.8-flash-lite-tts","google/gemini-3.8-flash-lite-tts"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-09-22","is_new":true,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Text to convert to speech. For multi-speaker mode, prefix lines with Speaker1: / Speaker2:. Up to 5,000 characters. Put delivery direction in style_prompt, and place these vocal tags inline where the sound should happen: <argh>, <breath>, <heavy breath>, <exhales>, <cackle>, <cheer>, <chuckle>, <chuckles>, <cough>, <cry>, <gasp>, <giggle>, <groan>, <growl>, <grunt>, <grr>, <hiss>, <laugh>, <laughter>, <moan>, <pant>, <pff>, <phew>, <scream>, <shout>, <shriek>, <sigh>, <sighs>, <sneeze>, <snicker>, <snort>, <sob>, <throat-clearing>, <tsk>, <whimper>, <whispers>, <whispering>, <yawn>, <short pause>, <long pause>. Capitalize a word to stress it, and wrap a listener reaction in pipes, for example |mm-hmm|.","required":true,"metadata":{},"max":5000},{"name":"mode","label":"Mode","type":"enum","description":"single = one voice, multi = two-voice dialogue (uses voice + voice2 + speaker names).","required":false,"metadata":{},"default":"single","options":["single","multi"]},{"name":"language","label":"Language","type":"string","description":"Optional BCP-47 language tag (en-US, es-ES, etc.). The language of the text is detected automatically. The 30 listed voices speak every supported language; a library voice must be used with its own language.","required":false,"metadata":{}},{"name":"voice","label":"Voice","type":"enum","description":"Primary voice name (e.g. Kore, Puck, Aoede). Leave blank for the default. These 30 voices speak every supported language. GET /v1/voices lists the full library of more than 2,000 voices, and any voice id it returns is also accepted here. custom clones a voice from voice_audio_url and voice_consent_audio_url, and the response's voice_id then works here or in voice2 for 7 days, for the account that created it.","required":false,"metadata":{"saved_voices":"session","option_labels":{"custom":"Custom"}},"default":"Charon","options":["Zephyr","Puck","Charon","Kore","Fenrir","Leda","Orus","Aoede","Callirrhoe","Autonoe","Enceladus","Iapetus","Umbriel","Algieba","Despina","Erinome","Algenib","Rasalgethi","Laomedeia","Achernar","Alnilam","Schedar","Gacrux","Pulcherrima","Achird","Zubenelgenubi","Vindemiatrix","Sadachbia","Sadaltager","Sulafat","custom"]},{"name":"voice_audio_url","label":"Reference audio URL","type":"string","description":"voice=custom only: an https URL to a 10 to 30 second recording of clean, natural speech from the voice to clone (WAV, MP3, M4A, OGG, WEBM or FLAC). Record it in a quiet room, on the same microphone as the consent recording.","required":false,"metadata":{"control":"audio-clip","max_seconds":30,"min_seconds":10,"visible_when":{"op":"eq","field":"voice","value":"custom"},"required_when":{"op":"eq","field":"voice","value":"custom"},"clear_when_hidden":true}},{"name":"voice_consent_audio_url","label":"Consent audio URL","type":"string","description":"voice=custom only: an https URL to the same speaker reading this statement aloud: \"I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model.\" The same statement in any of 30 languages is accepted; consent_statements in this parameter's metadata lists each one.","required":false,"metadata":{"control":"audio-clip","max_seconds":30,"visible_when":{"op":"eq","field":"voice","value":"custom"},"required_when":{"op":"eq","field":"voice","value":"custom"},"clear_when_hidden":true,"consent_statements":{"ar-XA":"أنا مالك هذا الصوت وأوافق على أن تستخدم Google هذا الصوت لإنشاء نموذج صوتي اصطناعي.","bn-IN":"আমি এই ভয়েসের মালিক এবং আমি একটি সিন্থেটিক ভয়েস মডেল তৈরি করতে এই ভয়েস ব্যবহার করে Google-এর সাথে সম্মতি দিচ্ছি।","de-DE":"Ich bin der Eigentümer dieser Stimme und bin damit einverstanden, dass Google diese Stimme zur Erstellung eines synthetischen Stimmmodells verwendet.","en-AU":"I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model.","en-GB":"I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model.","en-IN":"I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model.","en-US":"I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model.","es-ES":"Soy el propietario de esta voz y doy mi consentimiento para que Google la utilice para crear un modelo de voz sintética.","es-US":"Soy el propietario de esta voz y doy mi consentimiento para que Google la utilice para crear un modelo de voz sintética.","fr-CA":"Je suis le propriétaire de cette voix et j'autorise Google à utiliser cette voix pour créer un modèle de voix synthétique.","fr-FR":"Je suis le propriétaire de cette voix et j'autorise Google à utiliser cette voix pour créer un modèle de voix synthétique.","gu-IN":"હું આ વોઈસનો માલિક છું અને સિન્થેટિક વોઈસ મોડલ બનાવવા માટે આ વોઈસનો ઉપયોગ કરીને google ને હું સંમતિ આપું છું","hi-IN":"मैं इस आवाज का मालिक हूं और मैं सिंथेटिक आवाज मॉडल बनाने के लिए Google को इस आवाज का उपयोग करने की सहमति देता हूं","id-ID":"Saya pemilik suara ini dan saya menyetujui Google menggunakan suara ini untuk membuat model suara sintetis.","it-IT":"Sono il proprietario di questa voce e acconsento che Google la utilizzi per creare un modello di voce sintetica.","ja-JP":"私はこの音声の所有者であり、Googleがこの音声を使用して音声合成モデルを作成することを承認します。","kn-IN":"ನಾನು ಈ ಧ್ವನಿಯ ಮಾಲಿಕ ಮತ್ತು ಸಂಶ್ಲೇಷಿತ ಧ್ವನಿ ಮಾದರಿಯನ್ನು ರಚಿಸಲು ಈ ಧ್ವನಿಯನ್ನು ಬಳಸಿಕೊಂಡುಗೂಗಲ್ ಗೆ ನಾನು ಸಮ್ಮತಿಸುತ್ತೇನೆ.","ko-KR":"나는 이 음성의 소유자이며 구글이 이 음성을 사용하여 음성 합성 모델을 생성할 것을 허용합니다.","ml-IN":"ഈ ശബ്ദത്തിന്റെ ഉടമ ഞാനാണ്, ഒരു സിന്തറ്റിക് വോയ്സ് മോഡൽ സൃഷ്ടിക്കാൻ ഈ ശബ്ദം ഉപയോഗിക്കുന്നതിന് ഞാൻ Google-ന് സമ്മതം നൽകുന്നു.","mr-IN":"मी या आवाजाचा मालक आहे आणि सिंथेटिक व्हॉइस मॉडेल तयार करण्यासाठी हा आवाज वापरण्यासाठी मी Google ला संमती देतो","nl-NL":"Ik ben de eigenaar van deze stem en ik geef Google toestemming om deze stem te gebruiken om een synthetisch stemmodel te maken.","pl-PL":"Jestem właścicielem tego głosu i wyrażam zgodę na wykorzystanie go przez Google w celu utworzenia syntetycznego modelu głosu.","pt-BR":"Eu sou o proprietário desta voz e autorizo o Google a usá-la para criar um modelo de voz sintética.","ru-RU":"Я являюсь владельцем этого голоса и даю согласие Google на использование этого голоса для создания модели синтетического голоса.","ta-IN":"நான் இந்த குரலின் உரிமையாளர் மற்றும் செயற்கை குரல் மாதிரியை உருவாக்க இந்த குரலை பயன்படுத்த குகல்க்கு நான் ஒப்புக்கொள்கிறேன்.","te-IN":"నేను ఈ వాయిస్ యజమానిని మరియు సింతటిక్ వాయిస్ మోడల్ ని రూపొందించడానికి ఈ వాయిస్ ని ఉపయోగించడానికి googleకి నేను సమ్మతిస్తున్నాను.","th-TH":"ฉันเป็นเจ้าของเสียงนี้ และฉันยินยอมให้ Google ใช้เสียงนี้เพื่อสร้างแบบจำลองเสียงสังเคราะห์","tr-TR":"Bu sesin sahibi benim ve Google'ın bu sesi kullanarak sentetik bir ses modeli oluşturmasına izin veriyorum.","vi-VN":"Tôi là chủ sở hữu giọng nói này và tôi đồng ý cho Google sử dụng giọng nói này để tạo mô hình giọng nói tổng hợp.","zh-CN":"我是此声音的拥有者并授权谷歌使用此声音创建语音合成模型"}}},{"name":"voice2","label":"Voice2","type":"enum","description":"Second voice name for multi-speaker mode. Library and cloned voice ids are also accepted.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"multi"},"clear_when_hidden":true},"default":"Kore","options":["Zephyr","Puck","Charon","Kore","Fenrir","Leda","Orus","Aoede","Callirrhoe","Autonoe","Enceladus","Iapetus","Umbriel","Algieba","Despina","Erinome","Algenib","Rasalgethi","Laomedeia","Achernar","Alnilam","Schedar","Gacrux","Pulcherrima","Achird","Zubenelgenubi","Vindemiatrix","Sadachbia","Sadaltager","Sulafat"]},{"name":"speaker1_name","label":"Speaker1 Name","type":"string","description":"Display name used in the input prefix for speaker 1 (default: Speaker1).","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"multi"},"clear_when_hidden":true},"default":"Speaker1"},{"name":"speaker2_name","label":"Speaker2 Name","type":"string","description":"Display name used in the input prefix for speaker 2 (default: Speaker2).","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"multi"},"clear_when_hidden":true},"default":"Speaker2"},{"name":"output_format","label":"Output Format","type":"enum","description":"Audio file format: WAV, MP3, OGG (Opus), or ALAW / MULAW for telephony.","required":false,"metadata":{},"default":"WAV","options":["WAV","MP3","OGG","ALAW","MULAW"]},{"name":"speed","label":"Speed","type":"number","description":"Playback rate. 1.0 = natural; <1 slower, >1 faster. Not available on POST /v1/audio/speech:stream.","required":false,"metadata":{},"default":1,"min":0.25,"max":2},{"name":"volume_gain","label":"Volume Gain","type":"number","description":"Output gain in dB. 0 = unchanged.","required":false,"metadata":{},"default":0,"min":-96,"max":16},{"name":"sample_rate","label":"Sample Rate","type":"enum","description":"Output sample rate in Hz (8000, 16000, 22050, 24000, 44100, or 48000). OGG output uses the nearest of 8000, 16000, 24000 or 48000.","required":false,"metadata":{},"default":"24000","options":["8000","16000","22050","24000","44100","48000"]},{"name":"style_prompt","label":"Style Prompt","type":"string","description":"Natural-language style direction (e.g. \"warm, conversational\" or \"newscaster, serious\").","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/audio/speech","POST /v1/audio/speech:stream","GET /v1/voices"],"pricing":{"prompt":"0.0000026","completion":"0.0000312","image":"0","request":"0","input_cache_read":"0.0000026"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$2.60"},{"spec":"per 1M generated tokens","label":"Output","value":"$31.20"}],"unit_pricing":[{"unit":"1m_tokens","usd":"2.6","label":"Input"},{"unit":"1m_tokens","usd":"31.2","label":"Output"}],"limits":{"note":"**Limits**\n\n- Text: up to 5,000 characters per request\n- Audio billing: 32 output tokens per second of generated audio\n- 101 languages. The language of the text is detected automatically.\n\n**Voices**\n\n- The 30 voices in the `voice` list speak every supported language.\n- `GET /v1/voices?model=gemini-3-8-flash-lite-tts` lists the full library of more than 2,000 voices across 30 locales, with the language, accent, gender, pitch, and a description of each. Filter it with `language`, `gender`, `pitch`, or `q`. Any id it returns works as `voice` or `voice2`; when you also set `language`, use the voice's own language.\n\n**Custom voices**\n\n- Set `voice` to `custom` and pass two recordings of the same adult speaker as https URLs: `voice_audio_url`, 10 to 30 seconds of natural speech, and `voice_consent_audio_url`, the speaker reading \"I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model.\" The statement is accepted in 30 languages; `consent_statements` on that parameter lists each wording.\n- Both must be recordings of a real person, in a quiet room on the same microphone. AI-generated audio is not accepted. WAV, MP3, M4A, OGG, WEBM and FLAC are accepted, up to 15 MB each.\n- The response includes `voice_id` and `voice_id_expires_at`. Pass the `voice_id` as `voice` or `voice2` to reuse the voice for 7 days without new recordings. A `voice_id` works only for the account that created it.\n- This model keeps no list of custom voices, so keep the `voice_id` from the response. A custom voice ends when its id expires, so there is nothing to delete.\n- In the Playground, set Voice to Custom to use a voice made in the same tab again, or copy its id.\n\n**Delivery direction**\n\n- Put direction for the whole passage in `style_prompt` rather than in the text, for example \"warm, unhurried, and reassuring\".\n- Place vocal tags inline where the sound should happen. Use these English tags even when the text is in another language:\n\n```text\n<argh> <breath> <heavy breath> <exhales> <cackle> <cheer> <chuckle> <chuckles> <cough> <cry> <gasp> <giggle> <groan> <growl> <grunt> <grr> <hiss> <laugh> <laughter> <moan> <pant> <pff> <phew> <scream> <shout> <shriek> <sigh> <sighs> <sneeze> <snicker> <snort> <sob> <throat-clearing> <tsk> <whimper> <whispers> <whispering> <yawn> <short pause> <long pause>\n```\n\n- Capitalize a word to stress it. Wrap a listener reaction in pipes, for example |mm-hmm|, to add it without starting a new turn.\n\n**Multi-speaker**\n\n- Up to two speakers per request. Start each line with a speaker name and a colon, for example Speaker1: and Speaker2:. The names must match `speaker1_name` and `speaker2_name`.\n\n**Output**\n\n- WAV, MP3, OGG (Opus), ALAW, or MULAW, at 8,000 to 48,000 Hz.\n- `POST /v1/audio/speech:stream` sends 16-bit PCM chunks at 24,000 Hz while the audio is generated, then the complete file in the requested format. `speed` is available on `POST /v1/audio/speech` only."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=gemini-3-8-flash-lite-tts","api_url":"https://docs.empiriolabs.ai/models/gemini-3-8-flash-lite-tts","logo":"https://media.empiriolabs.ai/model-logos/gemini-3-8-flash-lite-tts.png","status":"available"},{"id":"gemini-3-8-live","object":"model","created":1789430400,"owned_by":"google","display_name":"Gemini 3.8 Live","author":"google","provider":"google","description":"Low-latency voice conversation over one socket, with 30 voices, live video input, tool calling, and replies you can interrupt as you speak.","modality":"audio","type":"realtime","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text","video"],"input_modalities":["audio","text","video"],"output_modalities":["audio","text"],"features":["realtime","speech_to_speech","audio_in","audio_out","video","function_calling","multilingual"],"aliases":["gemini-3.8-live","google/gemini-3.8-live"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":131072,"context_length":131072,"max_output_tokens":65536,"model_released_at":"2026-09-15","is_new":true,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"voice","label":"Voice","type":"enum","description":"Speaking voice for the session. Set it with session.update before the conversation starts; it cannot change afterwards.","required":false,"metadata":{},"default":"Puck","options":["Zephyr","Puck","Charon","Kore","Fenrir","Leda","Orus","Aoede","Callirrhoe","Autonoe","Enceladus","Iapetus","Umbriel","Algieba","Despina","Erinome","Algenib","Rasalgethi","Laomedeia","Achernar","Alnilam","Schedar","Gacrux","Pulcherrima","Achird","Zubenelgenubi","Vindemiatrix","Sadachbia","Sadaltager","Sulafat"]},{"name":"instructions","label":"Instructions","type":"string","description":"System guidance for how the model behaves and speaks. Set it with session.update before the conversation starts.","required":false,"metadata":{}},{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature from 0.2 to 2. Lower values make replies more consistent. Set it before the conversation starts.","required":false,"metadata":{},"min":0.2,"max":2},{"name":"input_audio_format","label":"Input audio format","type":"enum","description":"Encoding of the audio you append to the input buffer: pcm16 is base64 16-bit PCM at 16 kHz, and pcm24 is the same at 24 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"pcm16","options":["pcm16","pcm24"]},{"name":"output_audio_format","label":"Output audio format","type":"enum","description":"Encoding of the audio the model streams back: 16-bit PCM at 24 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":24000},"default":"pcm24","options":["pcm24"]},{"name":"turn_detection","label":"Turn detection","type":"string","description":"Voice activity detection: decides when you have finished speaking and the model should reply. It is on by default as server_vad. With server_vad, threshold is a number from 0 to 1; above 0.5, a turn needs clearer speech to start, which helps in noisy rooms. prefix_padding_ms is how long speech must last to start a turn and silence_duration_ms how long a pause must last to end it, each up to 10000. With semantic_vad, eagerness low waits longer before the model replies; medium, high and auto use the default timing. interrupt_response false lets the model finish a reply you talk over. Set turn_detection to null to end each turn yourself with input_audio_buffer.commit. Set it before the conversation starts.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":{"type":"server_vad"}},{"name":"max_response_output_tokens","label":"Max output tokens","type":"number","description":"Largest number of output tokens one reply may use: from 4096 to 65536, where a larger number runs at 65536, or \"inf\" for the model's own limit. Also accepted as max_output_tokens. When omitted, the model's own default applies. Set it before the conversation starts.","required":false,"metadata":{"aliases":["max_output_tokens"]},"min":4096,"max":65536},{"name":"input_audio_transcription","label":"Input transcription","type":"string","description":"Hints for the transcript of what you say: language is a language code such as en or fr-FR, and prompt lists up to 1,000 words and names to recognize, separated by commas, in at most 20,000 characters. The transcript always comes from this model. Set it to null for no transcript events. Set language and prompt before the conversation starts.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"media_resolution","label":"Media resolution","type":"enum","description":"Detail the model sees in each video frame you send: low uses the fewest input tokens per frame, and medium and high show more detail. When omitted, the model's own default applies. Set it before the conversation starts.","required":false,"metadata":{"ui":{"hide_in_playground":true},"option_labels":{"low":"Low","high":"High","medium":"Medium"}},"options":["low","medium","high"]}],"supported_endpoints":["WEBSOCKET /v1/realtime"],"pricing":{"prompt":"0.0000026","completion":"0.0000117","image":"0","request":"0","input_cache_read":"0.0000026"},"pricing_rows":[{"spec":"per 1M audio input tokens","label":"Input: audio","value":"$7.80"},{"spec":"per 1M prompt tokens","label":"Input","value":"$2.60"},{"spec":"per 1M generated tokens","label":"Output","value":"$11.70"},{"spec":"per 1M generated audio tokens","label":"Output: audio","value":"$31.20"}],"unit_pricing":[{"unit":"1m_tokens","usd":"7.8","label":"Input: audio"},{"unit":"1m_tokens","usd":"2.6","label":"Input"},{"unit":"1m_tokens","usd":"11.7","label":"Output"},{"unit":"1m_tokens","usd":"31.2","label":"Output: audio"}],"limits":{"note":"**Connecting**\r\n\r\nFull-duplex voice over a WebSocket at `wss://api.empiriolabs.ai/v1/realtime?model=gemini-3-8-live`, authenticated with the ordinary Authorization Bearer header. Configure the session with `session.update` before you send the first audio: voice, instructions, turn detection and tools. These settings are fixed once the conversation starts.\r\n\r\n**Sending audio and video**\r\n\r\n- Append microphone audio as `input_audio_buffer.append` events: 16-bit PCM at 16 kHz, or at 24 kHz with `input_audio_format` set to `pcm24`.\r\n- Append live video frames as `input_image_buffer.append` events, as base64 JPEG or PNG images.\r\n- Voice activity detection is on by default, so keep streaming for about a second after the speech ends. Set `turn_detection` to null to end each turn yourself with `input_audio_buffer.commit`.\r\n\r\n**Voices and language**\r\n\r\n- Use one of the 30 voices in the `voice` list, for example Puck, Kore or Charon. Any other value is refused.\r\n- The model replies in the language you speak.\r\n\r\n**Replies**\r\n\r\n- Speech streams as `response.audio.delta` events, 16-bit PCM at 24 kHz, with the words as `response.audio_transcript.delta` events. Your own speech is transcribed as well.\r\n- Speaking while the model replies interrupts it.\r\n\r\n**Tools**\r\n\r\n- Function calling with JSON Schema parameters. Return each result as a `function_call_output` item with its `call_id`.\r\n\r\n**Billing**\r\n\r\nAudio and text tokens are priced separately in both directions, video frames bill as input tokens, and reasoning tokens bill as output tokens. Each completed turn is billed on its own from the usage the model reports, including a reply you interrupt."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=gemini-3-8-live","api_url":"https://docs.empiriolabs.ai/models/gemini-3-8-live","logo":"https://media.empiriolabs.ai/model-logos/gemini.png","status":"available"},{"id":"gemini-3-8-live-extended-thinking","object":"model","created":1789430400,"owned_by":"google","display_name":"Gemini 3.8 Live Extended Thinking","author":"google","provider":"google","description":"Voice conversation that keeps talking while it reasons in the background, with 30 voices, live video input, tool calling, and adjustable reasoning effort.","modality":"audio","type":"realtime","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text","video"],"input_modalities":["audio","text","video"],"output_modalities":["audio","text"],"features":["realtime","speech_to_speech","audio_in","audio_out","video","function_calling","reasoning","multilingual"],"aliases":["gemini-3.8-live-extended-thinking","google/gemini-3.8-live-extended-thinking"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":131072,"context_length":131072,"max_output_tokens":65536,"model_released_at":"2026-09-15","is_new":true,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":true,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"voice","label":"Voice","type":"enum","description":"Speaking voice for the session. Set it with session.update before the conversation starts; it cannot change afterwards.","required":false,"metadata":{},"default":"Puck","options":["Zephyr","Puck","Charon","Kore","Fenrir","Leda","Orus","Aoede","Callirrhoe","Autonoe","Enceladus","Iapetus","Umbriel","Algieba","Despina","Erinome","Algenib","Rasalgethi","Laomedeia","Achernar","Alnilam","Schedar","Gacrux","Pulcherrima","Achird","Zubenelgenubi","Vindemiatrix","Sadachbia","Sadaltager","Sulafat"]},{"name":"instructions","label":"Instructions","type":"string","description":"System guidance for how the model behaves and speaks. Set it with session.update before the conversation starts.","required":false,"metadata":{}},{"name":"reasoning_effort","label":"Reasoning effort","type":"enum","description":"How much the model reasons in the background while it talks. Higher effort uses more output tokens. Set it before the conversation starts.","required":false,"metadata":{},"default":"medium","options":["low","medium","high"]},{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature from 0.2 to 2. Lower values make replies more consistent. Set it before the conversation starts.","required":false,"metadata":{},"min":0.2,"max":2},{"name":"input_audio_format","label":"Input audio format","type":"enum","description":"Encoding of the audio you append to the input buffer: pcm16 is base64 16-bit PCM at 16 kHz, and pcm24 is the same at 24 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"pcm16","options":["pcm16","pcm24"]},{"name":"output_audio_format","label":"Output audio format","type":"enum","description":"Encoding of the audio the model streams back: 16-bit PCM at 24 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":24000},"default":"pcm24","options":["pcm24"]},{"name":"turn_detection","label":"Turn detection","type":"string","description":"Voice activity detection: decides when you have finished speaking and the model should reply. It is on by default as server_vad. With server_vad, threshold is a number from 0 to 1; above 0.5, a turn needs clearer speech to start, which helps in noisy rooms. prefix_padding_ms is how long speech must last to start a turn and silence_duration_ms how long a pause must last to end it, each up to 10000. With semantic_vad, eagerness low waits longer before the model replies; medium, high and auto use the default timing. interrupt_response false lets the model finish a reply you talk over. Set turn_detection to null to end each turn yourself with input_audio_buffer.commit. Set it before the conversation starts.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":{"type":"server_vad"}},{"name":"max_response_output_tokens","label":"Max output tokens","type":"number","description":"Largest number of output tokens one reply may use: from 4096 to 65536, where a larger number runs at 65536, or \"inf\" for the model's own limit. Also accepted as max_output_tokens. When omitted, the model's own default applies. Set it before the conversation starts.","required":false,"metadata":{"aliases":["max_output_tokens"]},"min":4096,"max":65536},{"name":"input_audio_transcription","label":"Input transcription","type":"string","description":"Hints for the transcript of what you say: language is a language code such as en or fr-FR, and prompt lists up to 1,000 words and names to recognize, separated by commas, in at most 20,000 characters. The transcript always comes from this model. Set it to null for no transcript events. Set language and prompt before the conversation starts.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"media_resolution","label":"Media resolution","type":"enum","description":"Detail the model sees in each video frame you send: low uses the fewest input tokens per frame, and medium and high show more detail. When omitted, the model's own default applies. Set it before the conversation starts.","required":false,"metadata":{"ui":{"hide_in_playground":true},"option_labels":{"low":"Low","high":"High","medium":"Medium"}},"options":["low","medium","high"]}],"supported_endpoints":["WEBSOCKET /v1/realtime"],"pricing":{"prompt":"0.0000026","completion":"0.0000117","image":"0","request":"0","input_cache_read":"0.0000026"},"pricing_rows":[{"spec":"per 1M audio input tokens","label":"Input: audio","value":"$7.80"},{"spec":"per 1M prompt tokens","label":"Input","value":"$2.60"},{"spec":"per 1M generated tokens","label":"Output","value":"$11.70"},{"spec":"per 1M generated audio tokens","label":"Output: audio","value":"$31.20"}],"unit_pricing":[{"unit":"1m_tokens","usd":"7.8","label":"Input: audio"},{"unit":"1m_tokens","usd":"2.6","label":"Input"},{"unit":"1m_tokens","usd":"11.7","label":"Output"},{"unit":"1m_tokens","usd":"31.2","label":"Output: audio"}],"limits":{"note":"**Connecting**\r\n\r\nFull-duplex voice over a WebSocket at `wss://api.empiriolabs.ai/v1/realtime?model=gemini-3-8-live-extended-thinking`, authenticated with the ordinary Authorization Bearer header. Configure the session with `session.update` before you send the first audio: voice, instructions, turn detection and tools. These settings are fixed once the conversation starts.\r\n\r\n**Sending audio and video**\r\n\r\n- Append microphone audio as `input_audio_buffer.append` events: 16-bit PCM at 16 kHz, or at 24 kHz with `input_audio_format` set to `pcm24`.\r\n- Append live video frames as `input_image_buffer.append` events, as base64 JPEG or PNG images.\r\n- Voice activity detection is on by default, so keep streaming for about a second after the speech ends. Set `turn_detection` to null to end each turn yourself with `input_audio_buffer.commit`.\r\n\r\n**Voices and language**\r\n\r\n- Use one of the 30 voices in the `voice` list, for example Puck, Kore or Charon. Any other value is refused.\r\n- The model replies in the language you speak.\r\n\r\n**Replies**\r\n\r\n- Speech streams as `response.audio.delta` events, 16-bit PCM at 24 kHz, with the words as `response.audio_transcript.delta` events. Your own speech is transcribed as well.\r\n- Speaking while the model replies interrupts it.\r\n\r\n**Reasoning**\n\n- `reasoning_effort` sets how much the model reasons in the background while it talks: low, medium (the default) or high. Set it before the conversation starts.\n- The model often acknowledges a question first and answers in a second turn. Each turn is billed on its own.\n\n**Tools**\r\n\r\n- Function calling with JSON Schema parameters. Return each result as a `function_call_output` item with its `call_id`.\r\n\r\n**Billing**\r\n\r\nAudio and text tokens are priced separately in both directions, video frames bill as input tokens, and reasoning tokens bill as output tokens. Each completed turn is billed on its own from the usage the model reports, including a reply you interrupt."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=gemini-3-8-live-extended-thinking","api_url":"https://docs.empiriolabs.ai/models/gemini-3-8-live-extended-thinking","logo":"https://media.empiriolabs.ai/model-logos/gemini.png","status":"available"},{"id":"qwen-audio-3-1-asr","object":"model","created":1788998400,"owned_by":"alibaba","display_name":"Qwen Audio 3.1 ASR","author":"alibaba","provider":"alibaba","description":"Speech-to-text for short clips and long recordings, with sentence segments, word timestamps, and multilingual and Chinese dialect recognition.","modality":"audio","type":"stt","category":"transcription","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio"],"output_modalities":["text"],"features":["transcription","speech_to_text","multilingual"],"aliases":["qwen-audio-3.1-asr","alibaba/qwen-audio-3-1-asr"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-09-10","is_new":true,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[],"supported_endpoints":["POST /v1/audio/transcriptions"],"pricing":{"prompt":"0.0000003","completion":"0.00000094","image":"0","request":"0","input_cache_read":"0.0000003"},"pricing_rows":[{"spec":"per 1M audio input tokens","label":"Input","value":"$0.30"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.94"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.3","label":"Input"},{"unit":"1m_tokens","usd":"0.94","label":"Output"}],"limits":{"note":"**Sending audio**\n\nSend a file as multipart `file`, or JSON with `audio_url` or `audio_base64`, in common audio formats. Short clips and long recordings are both accepted.\n\n**Getting the result**\n\nThe request returns a `job_id` and a `poll_url` right away. Poll `GET /v1/jobs/<job-id>` until `status` is `completed`. Short clips finish in seconds; long recordings take longer.\n\n**What comes back**\n\nThe `result` of the completed job holds the full transcript as `text`, sentence segments with start and end times, and word timestamps. The language is detected automatically, including Chinese dialects.\n\n**Billing**\n\nInput and output tokens are priced per 1M, and each request is billed from the usage the model reports."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen-audio-3-1-asr","api_url":"https://docs.empiriolabs.ai/models/qwen-audio-3-1-asr","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen-audio-3-1-asr-stream","object":"model","created":1735689600,"owned_by":"alibaba","display_name":"Qwen Audio 3.1 ASR Stream","author":"alibaba","provider":"alibaba","description":"Live transcription over a socket, streaming partial words while the speaker talks and a settled sentence at each pause, priced per token.","modality":"audio","type":"realtime","category":"transcription","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio"],"output_modalities":["text"],"features":["transcription","speech_to_text","realtime","streaming_asr","multilingual"],"aliases":["qwen-audio-3.1-asr-stream","alibaba/qwen-audio-3-1-asr-stream"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":true,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input_audio_format","label":"Input audio format","type":"enum","description":"Encoding of the audio you append to the input buffer: base64 16-bit PCM, mono, at 16 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"pcm16","options":["pcm16"]},{"name":"language","label":"Language","type":"enum","description":"Language of the speech, or auto to detect it from the audio. Set it with the language query parameter of the connection URL, or as input_audio_transcription.language in session.update.","required":false,"metadata":{"ui":{"section":"Recognition"},"option_labels":{"ar":"Arabic","bg":"Bulgarian","cs":"Czech","da":"Danish","de":"German","el":"Greek","en":"English","es":"Spanish","fi":"Finnish","fr":"French","hi":"Hindi","hr":"Croatian","hu":"Hungarian","id":"Indonesian","it":"Italian","ja":"Japanese","ko":"Korean","ms":"Malay","nl":"Dutch","no":"Norwegian","pl":"Polish","pt":"Portuguese","ro":"Romanian","ru":"Russian","sk":"Slovak","sv":"Swedish","th":"Thai","tl":"Filipino","vi":"Vietnamese","zh":"Chinese","auto":"Detect automatically"}},"default":"auto","options":["auto","zh","en","ja","ko","vi","th","id","ms","tl","hi","ar","fr","de","es","pt","ru","it","nl","sv","da","fi","no","el","pl","cs","hu","ro","bg","hr","sk"]},{"name":"prompt","label":"Prompt","type":"string","description":"Text that guides recognition, up to 400 characters: the names and terms the speaker uses, or the text spoken just before this audio. Write the words exactly as they should appear in the transcript. Also accepted as input_audio_transcription.prompt.","required":false,"metadata":{"ui":{"section":"Recognition"}}},{"name":"silence_duration_ms","label":"Silence duration (ms)","type":"number","description":"The pause, in milliseconds, that ends a sentence, from 200 to 6000. A shorter pause settles each sentence sooner; a longer one keeps a pause inside a sentence. Also accepted as turn_detection.silence_duration_ms.","required":false,"metadata":{"ui":{"step":100,"control":"slider","section":"Recognition"}},"default":800,"min":200,"max":6000},{"name":"threshold","label":"Speech threshold","type":"number","description":"How clear speech must be before it is transcribed, from 0.0 to 1.0. A higher value ignores more background noise and can miss quiet speech. When omitted, the model's own default applies. Also accepted as turn_detection.threshold.","required":false,"metadata":{"ui":{"step":0.05,"section":"Recognition"}},"min":0,"max":1},{"name":"noise_reduction","label":"Noise reduction","type":"enum","description":"The microphone the speech detection is tuned for: near_field for a headset or a phone held close, far_field for a laptop or room microphone. Also accepted as input_audio_noise_reduction.type.","required":false,"metadata":{"ui":{"section":"Recognition"},"option_labels":{"far_field":"Far field","near_field":"Near field"}},"default":"far_field","options":["far_field","near_field"]},{"name":"keep_dialect","label":"Keep dialect","type":"boolean","description":"Keeps Chinese dialect words as spoken. When off, dialect speech is written as standard Mandarin.","required":false,"metadata":{"ui":{"section":"Recognition"}},"default":false}],"supported_endpoints":["WEBSOCKET /v1/realtime"],"pricing":{"prompt":"0.00000186","completion":"0.0000014","image":"0","request":"0","input_cache_read":"0.00000186"},"pricing_rows":[{"spec":"per 1M audio input tokens","label":"Input","value":"$1.86"},{"spec":"per 1M generated tokens","label":"Output","value":"$1.40"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.86","label":"Input"},{"unit":"1m_tokens","usd":"1.4","label":"Output"}],"limits":{"note":"**Connecting**\n\nLive transcription over a WebSocket at `wss://api.empiriolabs.ai/v1/realtime?model=qwen-audio-3-1-asr-stream`, authenticated with the ordinary Authorization Bearer header.\n\n**Sending audio**\n\nStream 16 kHz mono pcm16 audio with `input_audio_buffer.append`. Voice activity detection decides where each sentence ends, so there is no commit to send.\n\n**Session settings**\n\nSend `session.update` right after `session.created`, before the first audio, with any of these settings: `input_audio_transcription.language` (or the `language` query parameter of the connection URL; `auto` by default), `input_audio_transcription.prompt` with the names and terms the speaker uses (up to 400 characters), `turn_detection.silence_duration_ms` (200 to 6000, default 800) and `turn_detection.threshold` (0.0 to 1.0), and `input_audio_noise_reduction` (`near_field` or `far_field`). `keep_dialect` keeps Chinese dialect words as spoken. A setting changed while audio is streaming ends the sentence in progress and applies to the audio sent after it.\n\n**What comes back**\n\n`conversation.item.input_audio_transcription.delta` events carry the sentence so far while the speaker is still talking, and `conversation.item.input_audio_transcription.completed` carries the settled sentence at each pause.\n\n**Billing**\n\nInput and output tokens are priced per 1M, and each completed sentence is billed on its own from the usage the model reports."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen-audio-3-1-asr-stream","api_url":"https://docs.empiriolabs.ai/models/qwen-audio-3-1-asr-stream","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen-audio-3-1-asr-message","object":"model","created":1789948800,"owned_by":"alibaba","display_name":"Qwen Audio 3.1 ASR Message","author":"alibaba","provider":"alibaba","description":"Transcription tuned for voice messages and voice input over a socket, returning each utterance as one complete transcript when the speaker pauses.","modality":"audio","type":"realtime","category":"transcription","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio"],"output_modalities":["text"],"features":["transcription","speech_to_text","realtime","multilingual"],"aliases":["qwen-audio-3.1-asr-message","alibaba/qwen-audio-3-1-asr-message"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-09-21","is_new":true,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input_audio_format","label":"Input audio format","type":"enum","description":"Encoding of the audio you append to the input buffer: base64 16-bit PCM, mono, at 16 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"pcm16","options":["pcm16"]},{"name":"language","label":"Language","type":"enum","description":"Language of the speech, or auto to detect it from the audio. Set it with the language query parameter of the connection URL, or as input_audio_transcription.language in session.update.","required":false,"metadata":{"ui":{"section":"Recognition"},"option_labels":{"ar":"Arabic","bg":"Bulgarian","cs":"Czech","da":"Danish","de":"German","el":"Greek","en":"English","es":"Spanish","fi":"Finnish","fr":"French","hi":"Hindi","hr":"Croatian","hu":"Hungarian","id":"Indonesian","it":"Italian","ja":"Japanese","ko":"Korean","ms":"Malay","nl":"Dutch","no":"Norwegian","pl":"Polish","pt":"Portuguese","ro":"Romanian","ru":"Russian","sk":"Slovak","sv":"Swedish","th":"Thai","tl":"Filipino","vi":"Vietnamese","zh":"Chinese","auto":"Detect automatically"}},"default":"auto","options":["auto","zh","en","ja","ko","vi","th","id","ms","tl","hi","ar","fr","de","es","pt","ru","it","nl","sv","da","fi","no","el","pl","cs","hu","ro","bg","hr","sk"]},{"name":"silence_duration_ms","label":"Silence duration (ms)","type":"number","description":"The pause, in milliseconds, that ends a sentence, from 200 to 6000. A shorter pause settles each sentence sooner; a longer one keeps a pause inside a sentence. Also accepted as turn_detection.silence_duration_ms.","required":false,"metadata":{"ui":{"step":100,"control":"slider","section":"Recognition"}},"default":800,"min":200,"max":6000},{"name":"threshold","label":"Speech threshold","type":"number","description":"How clear speech must be before it is transcribed, from 0.0 to 1.0. A higher value ignores more background noise and can miss quiet speech. When omitted, the model's own default applies. Also accepted as turn_detection.threshold.","required":false,"metadata":{"ui":{"step":0.05,"section":"Recognition"}},"min":0,"max":1},{"name":"noise_reduction","label":"Noise reduction","type":"enum","description":"The microphone the speech detection is tuned for: near_field for a headset or a phone held close, far_field for a laptop or room microphone. Also accepted as input_audio_noise_reduction.type.","required":false,"metadata":{"ui":{"section":"Recognition"},"option_labels":{"far_field":"Far field","near_field":"Near field"}},"default":"far_field","options":["far_field","near_field"]},{"name":"keep_dialect","label":"Keep dialect","type":"boolean","description":"Keeps Chinese dialect words as spoken. When off, dialect speech is written as standard Mandarin.","required":false,"metadata":{"ui":{"section":"Recognition"}},"default":false},{"name":"partial_results","label":"Partial results","type":"boolean","description":"Also sends each utterance while it is spoken, as conversation.item.input_audio_transcription.delta events carrying the utterance so far, which can still change before it settles.","required":false,"metadata":{"ui":{"section":"Recognition"}},"default":false}],"supported_endpoints":["WEBSOCKET /v1/realtime"],"pricing":{"prompt":"0.00000186","completion":"0.0000014","image":"0","request":"0","input_cache_read":"0.00000186"},"pricing_rows":[{"spec":"per 1M audio input tokens","label":"Input","value":"$1.86"},{"spec":"per 1M generated tokens","label":"Output","value":"$1.40"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.86","label":"Input"},{"unit":"1m_tokens","usd":"1.4","label":"Output"}],"limits":{"note":"**Connecting**\n\nVoice message transcription over a WebSocket at `wss://api.empiriolabs.ai/v1/realtime?model=qwen-audio-3-1-asr-message`, authenticated with the ordinary Authorization Bearer header.\n\n**Sending audio**\n\nStream 16 kHz mono pcm16 audio with `input_audio_buffer.append`. Voice activity detection decides where each utterance ends, so there is no commit to send.\n\n**Session settings**\n\nSend `session.update` right after `session.created`, before the first audio, with any of these settings: `input_audio_transcription.language` (or the `language` query parameter of the connection URL; `auto` by default), `turn_detection.silence_duration_ms` (200 to 6000, default 800) and `turn_detection.threshold` (0.0 to 1.0), and `input_audio_noise_reduction` (`near_field` or `far_field`). `keep_dialect` keeps Chinese dialect words as spoken. A setting changed while audio is streaming ends the utterance in progress and applies to the audio sent after it.\n\n**What comes back**\n\nEach utterance arrives whole, as one `conversation.item.input_audio_transcription.completed` event once the speaker pauses. Set `partial_results` to also receive it while it is spoken, as `conversation.item.input_audio_transcription.delta` events that can still change before it settles. For live captions, `qwen-audio-3-1-asr-stream` always sends them.\n\n**Billing**\n\nInput and output tokens are priced per 1M, and each completed utterance is billed on its own from the usage the model reports."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen-audio-3-1-asr-message","api_url":"https://docs.empiriolabs.ai/models/qwen-audio-3-1-asr-message","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen-audio-3-1-tts","object":"model","created":1790121600,"owned_by":"alibaba","display_name":"Qwen Audio 3.1 TTS","author":"alibaba","provider":"alibaba","description":"Real-time speech synthesis with 19 voices, delivery direction in plain language, inline emotion and sound tags, and audio streamed over SSE or WebSocket.","modality":"audio","type":"tts","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["text_to_speech","multilingual","expressive_prosody","emotion_control","voice_tags","low_latency","streaming","realtime","voice_cloning"],"aliases":["qwen-audio-3.1-tts","qwen-audio-3.1-tts-flash","alibaba/qwen-audio-3-1-tts"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":60000,"model_released_at":"2026-09-23","is_new":true,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Text to synthesize, up to 10,000 characters per request. These inline tags change the delivery from the point where they appear: [sad], [amazed], [deep and loud shouting], [trembling], [angry], [excited], [sarcastic], [curious], [like dracula], [bored], [tired], [scornful], [shouting], [asmr], [panicked], [mischievously], [empathetic], [whispers], [reluctantly], [crying], [serious], [very slowly], [very fast]. These add a one-time sound at that point: [gasp], [sighing], [clears throat], [giggles], [laughing], [cough], [snorts].","required":true,"metadata":{"ui":{"control":"textarea","section":"Input"}},"max":10000},{"name":"voice","label":"Voice","type":"enum","description":"Voice preset. The 15 English voices read English, and the 4 multilingual voices read Chinese, English, and other languages. Every voice id ends in _v3.1, for example Emily_v3.1. custom clones a voice from voice_audio_url, and the response's voice_id then works here for 7 days. GET /v1/voices lists your custom voices with their ids.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Voice"},"saved_voices":true,"option_labels":{"custom":"Custom","Ava_v3.1":"Ava (English, American, Female)","Abby_v3.1":"Abby (English, American, Female)","Andy_v3.1":"Andy (English, American, Male)","Beth_v3.1":"Beth (English, American, Female)","Eric_v3.1":"Eric (English, British, Male)","Luca_v3.1":"Luca (English, British, Male)","Luna_v3.1":"Luna (English, British, Female)","Annie_v3.1":"Annie (English, American, Female)","Betty_v3.1":"Betty (English, American, Female)","Brian_v3.1":"Brian (English, American, Male)","Cally_v3.1":"Cally (English, American, Female)","Cindy_v3.1":"Cindy (English, American, Female)","David_v3.1":"David (English, American, Male)","Donna_v3.1":"Donna (English, American, Female)","Emily_v3.1":"Emily (English, British, Female)","longanhuan_v3.1":"An Huan (Multilingual, Female)","xunanchuan_v3.1":"Xu Nan Chuan (Multilingual, Male)","longanfengyue_v3.1":"An Feng Yue (Multilingual, Female)","longanlingxin_v3.1":"An Ling Xin (Multilingual, Female)"}},"default":"Emily_v3.1","options":["Emily_v3.1","Luna_v3.1","Eric_v3.1","Luca_v3.1","Abby_v3.1","Annie_v3.1","Ava_v3.1","Beth_v3.1","Betty_v3.1","Cally_v3.1","Cindy_v3.1","Donna_v3.1","Andy_v3.1","Brian_v3.1","David_v3.1","longanhuan_v3.1","longanlingxin_v3.1","longanfengyue_v3.1","xunanchuan_v3.1","custom"]},{"name":"voice_audio_url","label":"Reference audio URL","type":"string","description":"voice=custom only: an https URL to a 10 to 20 second recording of clear speech from one speaker, the voice to clone (WAV, MP3, M4A, OGG, WEBM or FLAC, up to 15 MB). Record it in a quiet room, without music or other voices.","required":false,"metadata":{"control":"audio-clip","max_seconds":20,"min_seconds":10,"visible_when":{"op":"eq","field":"voice","value":"custom"},"required_when":{"op":"eq","field":"voice","value":"custom"},"clear_when_hidden":true}},{"name":"response_format","label":"Response Format","type":"enum","description":"Audio container. mp3 and opus are compressed, wav is uncompressed PCM in a RIFF header, and pcm is headerless raw samples for chunked playback. On the realtime WebSocket the default is pcm and wav is not available.","required":false,"metadata":{"ui":{"control":"segmented","section":"Output"}},"default":"mp3","options":["mp3","wav","pcm","opus"]},{"name":"sample_rate","label":"Sample Rate","type":"enum","description":"Output sample rate in Hz. 24000 suits speech playback, and 48000 gives broadcast-quality output at a larger file size.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Output"}},"default":24000,"options":["8000","12000","16000","22050","24000","44100","48000"]},{"name":"speed","label":"Speed","type":"number","description":"Speaking rate multiplier. 0.5 is half speed and 2.0 is double speed.","required":false,"metadata":{"ui":{"step":0.05,"control":"slider","section":"Delivery"}},"default":1,"min":0.5,"max":2},{"name":"pitch","label":"Pitch","type":"number","description":"Pitch multiplier. Values below 1.0 lower the voice and values above raise it. Pitch also shifts the pace of the rendered audio, so pair it with speed when you want to keep the original duration.","required":false,"metadata":{"ui":{"step":0.05,"control":"slider","section":"Delivery"}},"default":1,"min":0.5,"max":2},{"name":"volume","label":"Volume","type":"number","description":"Output loudness, where 50 is the reference level.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Delivery"}},"default":50,"min":0,"max":100},{"name":"instruction","label":"Instruction","type":"string","description":"Natural-language direction for delivery, up to 1,000 characters. Controls emotion, tone, character, pace, and speaking style, for example 'Speak quickly in an excited, upbeat tone' or 'Read slowly like a late-night radio host'.","required":false,"metadata":{"ui":{"control":"textarea","section":"Delivery","placeholder":"Speak quickly in an excited, upbeat tone"}},"max":1000},{"name":"language_hints","label":"Language Hints","type":"string","description":"Language codes that bias pronunciation for mixed-language text, for example [\"zh\", \"en\"]. Leave unset to let the model detect the language.","required":false,"metadata":{"ui":{"control":"json","section":"Delivery"}}},{"name":"seed","label":"Seed","type":"number","description":"Sampling seed. Reuse a seed with identical input and settings for a repeatable render.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced"}},"default":0,"min":0,"max":65535},{"name":"bit_rate","label":"Bit Rate","type":"number","description":"Encoder bitrate in bps. Applies to the opus format only, and is ignored for mp3, wav, and pcm.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced"}},"default":32000,"min":6000,"max":510000},{"name":"pronunciation","label":"Pronunciation","type":"string","description":"Pronunciation overrides keyed by the written form, for example {\"重要\": \"zhong4 yao4\"}. Use it to fix names, acronyms, and homographs.","required":false,"metadata":{"ui":{"control":"json","section":"Advanced"}}},{"name":"replace","label":"Replace","type":"string","description":"Literal text substitutions applied before synthesis, for example {\"EmpirioLabs\": \"Empirio Labs\"}. Useful for brand names and abbreviations.","required":false,"metadata":{"ui":{"control":"json","section":"Advanced"}}},{"name":"enable_markdown_filter","label":"Markdown Filter","type":"boolean","description":"Strip Markdown syntax such as asterisks and underscores before synthesis so formatting characters are not read aloud.","required":false,"metadata":{"ui":{"control":"toggle","section":"Advanced"}},"default":false}],"supported_endpoints":["POST /v1/audio/speech","POST /v1/audio/speech:stream","WEBSOCKET /v1/realtime","GET /v1/voices"],"pricing":{"prompt":"0.00000046","completion":"0.00000374","image":"0","request":"0","input_cache_read":"0.00000046"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.46"},{"spec":"per 1M generated tokens","label":"Output","value":"$3.74"}],"unit_pricing":[{"unit":"1m_tokens","usd":"0.46","label":"Input"},{"unit":"1m_tokens","usd":"3.74","label":"Output"}],"limits":{"note":"**Voices**\n\n- 19 voices: 15 English voices and 4 multilingual voices. Emily, Luna, Eric, and Luca have British accents. Abby, Annie, Ava, Beth, Betty, Cally, Cindy, Donna, Andy, Brian, and David have American accents. The multilingual voices `longanhuan_v3.1`, `longanlingxin_v3.1`, `longanfengyue_v3.1`, and `xunanchuan_v3.1` read Chinese, English, and other languages.\n- Every voice id ends in `_v3.1`, for example `Emily_v3.1`.\n\n**Custom voices**\n\n- Set `voice` to `custom` and pass `voice_audio_url`, an https URL to 10 to 20 seconds of clear speech from one speaker.\n- WAV, MP3, M4A, OGG, WEBM and FLAC are accepted, up to 15 MB. Record in a quiet room, without music or other voices.\n- The response includes `voice_id` and `voice_id_expires_at`. Pass the `voice_id` as `voice` to reuse the voice for 7 days, on `POST /v1/audio/speech`, `POST /v1/audio/speech:stream` or the realtime socket, where `session.update` takes the same fields and `session.updated` returns the `voice_id`. Only the account that created it can use it.\n- Each account can hold 10 custom voices on this model at a time.\n- `GET /v1/voices?model=qwen-audio-3-1-tts` lists the model's voices, including your custom voices with their ids. Add `type=custom` to list custom voices alone.\n- `DELETE /v1/voices/{voice_id}?model=qwen-audio-3-1-tts` deletes a custom voice, which frees its place at once.\n- In the Playground, set Voice to Custom to use a saved voice again, copy its id, or delete it.\n- Creating, listing and deleting custom voices adds no charge.\n\n**Delivery direction**\n\n- `instruction` sets emotion, tone, character, pace, and speaking style in natural language, up to 1,000 characters.\n- Inline tags inside the text change the delivery from that point, for example `[excited]` or `[whispers]`, or add a one-time sound such as `[laughing]` or `[sighing]`. The full list of tags is on the `input` parameter.\n- SSML input is not supported.\n\n**Input limits**\n\n- Up to 10,000 characters per request.\n- `language_hints` biases pronunciation for mixed-language text.\n\n**Output**\n\n- MP3, WAV, PCM, or Opus at 8,000 to 48,000 Hz.\n- `POST /v1/audio/speech:stream` sends audio chunks while the speech is generated.\n\n**Realtime**\n\n- `WEBSOCKET /v1/realtime?model=qwen-audio-3-1-tts` takes text while it is still being written and returns audio as it is generated. Send `input_text_buffer.append` events, then `input_text_buffer.commit`, or `session.finish` to end the session.\n- Audio arrives in `response.audio.delta` events: 16-bit PCM at 24,000 Hz by default, or MP3 or Opus. Set the voice, instruction, format and other options with `session.update`; a change applies from the next segment.\n- Text is spoken in segments that end at sentence boundaries, and each segment ends with a `response.done` event carrying its usage.\n\n**Billing**\n\n- Input tokens are the text, and output tokens are the generated audio at 12.5 tokens per second.\n- Speed and pitch change the length of the rendered audio but not the billed tokens. An instruction that slows the delivery adds output tokens."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen-audio-3-1-tts","api_url":"https://docs.empiriolabs.ai/models/qwen-audio-3-1-tts","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen-image-2-1","object":"model","created":1790899200,"owned_by":"alibaba","display_name":"Qwen Image 2.1","author":"alibaba","provider":"alibaba","description":"Image generation and editing with Pro and Turbo variants, up to ten reference images, transparent PNG output, and custom sizes up to 2560x2560.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text","image"],"output_modalities":["image"],"features":["image_generation","image_editing","multi_image","multi_reference","transparent_background","text_rendering"],"aliases":["qwen-image-2.1","qwen-image-2.1-pro","qwen-image-2.1-turbo","alibaba/qwen-image-2-1","alibaba/qwen-image-2.1"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-10-02","is_new":true,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Describe the image to create. With input images attached, this becomes the editing instruction. An image-only edit uses a neutral preservation prompt.","required":false,"metadata":{"ui":{"control":"text_area","section":"Input"}}},{"name":"model_variant","label":"Variant","type":"enum","description":"Choose Pro for the highest image quality and complex edits, or Turbo for faster, lower-cost generation. When this is not set, the model id \"qwen-image-2.1-turbo\" selects Turbo and every other id of this model selects Pro.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Settings"},"option_labels":{"qwen-image-2.1-pro":"Pro","qwen-image-2.1-turbo":"Turbo"}},"default":"qwen-image-2.1-pro","options":["qwen-image-2.1-pro","qwen-image-2.1-turbo"]},{"name":"image","label":"Images","type":"string","description":"One to ten reference images as URLs, data URIs, or uploaded image objects.","required":false,"metadata":{"ui":{"accept":"image/*","control":"file","section":"Input","multiple":true,"max_files":10}}},{"name":"images","label":"Images","type":"string","description":"Plural alias for multiple uploaded image references.","required":false,"metadata":{"ui":{"hidden":true}}},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Optional output aspect ratio. Auto is the default. With a fixed 1K or 2K resolution, Auto uses that tier's square size. With Resolution set to Auto, the model chooses the complete output size.","required":false,"metadata":{"ui":{"control":"segmented","section":"Settings"}},"default":"auto","options":["auto","1:1","16:9","9:16","3:2","2:3","4:3","3:4","5:4","4:5"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output size preset. Defaults to 2K. Auto lets the model choose the size when Aspect Ratio is Auto; with a selected aspect ratio, Auto uses the 1K preset.","required":false,"metadata":{"ui":{"control":"segmented","section":"Settings"}},"default":"2K","options":["auto","1K","2K"]},{"name":"size","label":"Size","type":"string","description":"Exact output size as WIDTH*HEIGHT, for example 2048*1536. This overrides aspect_ratio and resolution.","required":false,"metadata":{"ui":{"section":"Advanced","hide_in_playground":true}}},{"name":"use_custom_size","label":"Use Custom Size","type":"boolean","description":"Use custom_width and custom_height instead of the aspect-ratio and resolution presets.","required":false,"metadata":{"ui":{"control":"toggle","section":"Settings"}},"default":false},{"name":"custom_width","label":"Custom Width","type":"number","description":"Custom output width in pixels. Total area must be between 512x512 and 2560x2560, with an aspect ratio from 1:8 to 8:1.","required":false,"metadata":{"ui":{"step":1,"control":"text_field","section":"Settings"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":182,"max":7240},{"name":"custom_height","label":"Custom Height","type":"number","description":"Custom output height in pixels. Total area must be between 512x512 and 2560x2560, with an aspect ratio from 1:8 to 8:1.","required":false,"metadata":{"ui":{"step":1,"control":"text_field","section":"Settings"},"visible_when":{"op":"eq","field":"use_custom_size","value":true},"clear_when_hidden":true},"min":182,"max":7240},{"name":"num_images","label":"Number of Images","type":"number","description":"Number of output images. Each output is billed separately.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Output"}},"default":1,"min":1,"max":6},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"Describe visual elements or qualities to avoid in the output.","required":false,"metadata":{"ui":{"control":"text_area","section":"Advanced"}},"default":""},{"name":"prompt_extend","label":"Prompt Extension","type":"boolean","description":"Expand the prompt automatically for stronger composition and detail. Turn it off when you ask for a transparent background.","required":false,"metadata":{"ui":{"control":"toggle","section":"Advanced"}},"default":true},{"name":"prompt_extend_mode","label":"Prompt Extension Mode","type":"enum","description":"Direct works for generation and editing. Agent performs deeper prompt refinement and is available for text-to-image requests only.","required":false,"metadata":{"ui":{"control":"segmented","section":"Advanced"},"visible_when":{"op":"eq","field":"prompt_extend","value":true}},"default":"direct","options":["direct","agent"]},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed. Leave empty for a random result.","required":false,"metadata":{"ui":{"step":1,"control":"text_field","section":"Advanced"}},"min":0,"max":2147483647},{"name":"watermark","label":"Watermark","type":"boolean","description":"Add the Qwen provenance watermark to the generated image. EmpirioLabs does not add a watermark of its own.","required":false,"metadata":{"ui":{"control":"toggle","section":"Advanced"}},"default":false},{"name":"response_format","label":"Response Format","type":"enum","description":"Return signed image URLs by default, or include base64 image data when b64_json is requested.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Output"}},"default":"url","options":["url","b64_json"]}],"supported_endpoints":["POST /v1/images/generations"],"pricing":{"prompt":"0","completion":"0","image":"0.04","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Pro","value":"$0.040"},{"spec":"per image","label":"Turbo","value":"$0.016"}],"unit_pricing":[{"unit":"image","usd":"0.04","label":"Pro"},{"unit":"image","usd":"0.016","label":"Turbo"}],"limits":{"note":"Qwen Image 2.1 combines Pro and Turbo image generation and editing in one model. Pro is selected by default, output starts at 2K, and aspect ratio starts in Auto. Turbo provides a faster, lower-cost option.\n\n**Variants**\n\n- Choose qwen-image-2.1-pro for the highest image quality and complex edits.\n- Choose qwen-image-2.1-turbo for faster, lower-cost generation and routine edits.\n- Choose with model_variant. Without it, the model id qwen-image-2.1-turbo runs Turbo and every other id of this model runs Pro.\n\n**Modes**\n\n- Text to image from a prompt.\n- Image editing and reference-guided generation from one to ten images.\n- Direct prompt extension works for generation and editing. Agent prompt extension provides deeper refinement for text-to-image requests only.\n\n**Transparent images**\n\n- Output images are PNG files. For a transparent background, set prompt_extend to false and describe the image in this form: \"This is an RGBA image with transparency. A glass perfume bottle. The image has alpha channel and the background is transparent.\"\n\n**Output limits**\n\n- One to six output images per request.\n- 1K, 2K, automatic, aspect-ratio presets, or an exact custom size.\n- Exact and custom sizes stay between 512x512 and 2560x2560 pixels in total area, with an aspect ratio from 1:8 to 8:1.\n\n**Billing**\n\n- Each output image is billed at its variant's rate. Reference images are not billed.\n\n**Content safety**\n\nGenerated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed."},"notes":"Qwen Image 2.1 combines Pro and Turbo image generation and editing in one model. Pro is selected by default, output starts at 2K, and aspect ratio starts in Auto. Turbo provides a faster, lower-cost option.\n\n**Variants**\n\n- Choose qwen-image-2.1-pro for the highest image quality and complex edits.\n- Choose qwen-image-2.1-turbo for faster, lower-cost generation and routine edits.\n\n**Modes**\n\n- Text to image from a prompt.\n- Image editing and reference-guided generation from one to ten images.\n- Direct prompt extension works for generation and editing. Agent prompt extension provides deeper refinement for text-to-image requests only.\n\n**Transparent images**\n\n- Output images are PNG files. For a transparent background, set prompt_extend to false and describe the image in this form: \"This is an RGBA image with transparency. A glass perfume bottle. The image has alpha channel and the background is transparent.\"\n\n**Output limits**\n\n- One to six output images per request.\n- 1K, 2K, automatic, aspect-ratio presets, or an exact custom size.\n- Exact and custom sizes stay between 512x512 and 2560x2560 pixels in total area, with an aspect ratio from 1:8 to 8:1.\n\n**Billing**\n\n- Each output image is billed at its variant's rate. Reference images are not billed.\n\n**Content safety**\n\nGenerated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen-image-2-1","api_url":"https://docs.empiriolabs.ai/models/qwen-image-2-1","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen-audio-3-1-tts-next","object":"model","created":1790121600,"owned_by":"alibaba","display_name":"Qwen Audio 3.1 TTS Next","author":"alibaba","provider":"alibaba","description":"Audio generation from a written description, with narration, dialogue in up to three cloned voices, sound effects, ambience, and music in one file.","modality":"audio","type":"tts","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text","audio"],"output_modalities":["audio"],"features":["text_to_speech","audio_generation","multi_speaker","voice_cloning","sound_effects","podcast"],"aliases":["qwen-audio-3.1-tts-next","alibaba/qwen-audio-3-1-tts-next"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":50000,"model_released_at":"2026-09-23","is_new":true,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"A description of the audio to generate, up to 3,000 characters: the voices, what they say, the delivery, and any sound effects, ambience, or music. Name reference clips as @voice1 to @voice3.","required":true,"metadata":{"ui":{"control":"textarea","section":"Input"}},"max":3000},{"name":"references","label":"Reference Clips","type":"string","description":"Up to 3 voice reference clips as URLs or base64 audio data URIs, each up to 30 seconds and 10 MB, in WAV, MP3, or OGG Opus. Name them @voice1 to @voice3 in input, in order.","required":false,"metadata":{"ui":{"accept":"audio/*","control":"file","section":"Input","multiple":true,"max_files":3}}},{"name":"response_format","label":"Response Format","type":"enum","description":"Audio container. mp3 is compressed, wav is uncompressed PCM in a RIFF header, and pcm is headerless raw samples.","required":false,"metadata":{"ui":{"control":"segmented","section":"Output"}},"default":"mp3","options":["mp3","wav","pcm"]},{"name":"sample_rate","label":"Sample Rate","type":"enum","description":"Output sample rate in Hz. 48000 suits music and ambience; 24000 is enough for speech alone.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Output"}},"default":48000,"options":["8000","16000","24000","44100","48000"]},{"name":"channels","label":"Channels","type":"enum","description":"1 for mono, 2 for stereo.","required":false,"metadata":{"ui":{"control":"segmented","section":"Output"}},"default":2,"options":["1","2"]},{"name":"speed","label":"Speed","type":"number","description":"Speaking rate multiplier. 0.5 is half speed and 2.0 is double speed.","required":false,"metadata":{"ui":{"step":0.05,"control":"slider","section":"Delivery"}},"default":1,"min":0.5,"max":2},{"name":"volume","label":"Volume","type":"number","description":"Output loudness, where 50 is the reference level.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Delivery"}},"default":50,"min":0,"max":100},{"name":"seed","label":"Seed","type":"number","description":"Generation seed. Reuse a seed with the same input and settings for a repeatable result.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced"}},"min":0,"max":2147483647},{"name":"bit_rate","label":"Bit Rate","type":"number","description":"Constant MP3 bitrate in bps. Applies to the mp3 format only; without it, MP3 uses a variable bitrate.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced"}},"min":32000,"max":320000},{"name":"watermark","label":"Watermark","type":"boolean","description":"Add an AI-generated content watermark to the audio.","required":false,"metadata":{"ui":{"control":"toggle","section":"Advanced"}},"default":false}],"supported_endpoints":["POST /v1/audio/speech"],"pricing":{"prompt":"0.00000165","completion":"0.000003301","image":"0","request":"0","input_cache_read":"0.00000165"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.65"},{"spec":"per 1M generated tokens","label":"Output","value":"$3.301"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.65","label":"Input"},{"unit":"1m_tokens","usd":"3.301","label":"Output"}],"limits":{"note":"**What it makes**\n\n- One finished audio file from a written description: narration, dialogue, sound effects, ambience, and music together.\n- Describe each voice, the delivery, and the sounds in `input`. There is no voice list.\n- Chinese and English.\n\n**Voices from reference clips**\n\n- `references` takes up to 3 clips as URLs or base64 audio data URIs, each up to 30 seconds and 10 MB, in WAV, MP3, or OGG Opus.\n- Name them in `input` as `@voice1`, `@voice2`, and `@voice3`, in order, for example: `@voice1 cheerfully says: \"What a lovely day.\"`\n\n**Input limits**\n\n- Up to 3,000 characters per request.\n- `instruction` and SSML are not used: all direction goes in `input`.\n\n**Output**\n\n- MP3 (the default), WAV, or PCM at 8,000 to 48,000 Hz, mono or stereo; the defaults are 48,000 Hz and stereo.\n- Up to 120 seconds per request, or 240 seconds for a podcast.\n- One complete file per request. This model does not stream.\n\n**Billing**\n\n- Input tokens are the description plus each reference clip. Output tokens are the generated audio, about 200 per second."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen-audio-3-1-tts-next","api_url":"https://docs.empiriolabs.ai/models/qwen-audio-3-1-tts-next","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"pixverse-v6-max","object":"model","created":1792454400,"owned_by":"pixverse","display_name":"PixVerse V6 Max","author":"pixverse","provider":"pixverse","description":"Text- and image-to-video up to 15 seconds at 1080p, with 5,000-character prompts, shot-by-shot direction, and native synchronized audio.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image"],"output_modalities":["video"],"features":["text_to_video","image_to_video","audio_sync","multi_shot","character_consistency"],"aliases":["pixverse/v6-max"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-10-20","is_new":true,"is_featured":false,"discount":{"label":"Save up to 20%","percent":20},"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description, up to 5000 characters. Describe several shots in order, such as Shot 1 and Shot 2, for a multi-shot clip.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"How your inputs are used. auto detects it from what you attach. t2v is text to video. i2v animates one image.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution. Higher resolutions bill at a higher per-second rate.","required":false,"metadata":{},"default":"720p","options":["360p","540p","720p","1080p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio for text-to-video. Image-to-video follows the source image instead.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"16:9","options":["16:9","4:3","1:1","3:4","9:16","2:3","3:2","21:9"]},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds.","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":5,"min":1,"max":15},{"name":"generate_audio_switch","label":"Generate Audio","type":"boolean","description":"Generate native synchronized audio with the video. Bills at the higher with-audio rate for the chosen resolution.","required":false,"metadata":{},"default":true},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed. The same seed with the same inputs returns a similar result.","required":false,"metadata":{},"min":0,"max":2147483647},{"name":"image","label":"Image","type":"string","description":"Source image URL for image-to-video.","required":false,"metadata":{"ui":{"hide_in_playground":true}}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"Standard 360p no audio","value":"$0.024534 (was $0.030667)"},{"spec":"per second","label":"Standard 360p with audio","value":"$0.0368 (was $0.046)"},{"spec":"per second","label":"Standard 540p no audio","value":"$0.0368 (was $0.046)"},{"spec":"per second","label":"Standard 540p with audio","value":"$0.044978 (was $0.056222)"},{"spec":"per second","label":"Standard 720p no audio","value":"$0.044978 (was $0.056222)"},{"spec":"per second","label":"Standard 720p with audio","value":"$0.061334 (was $0.076667)"},{"spec":"per second","label":"Standard 1080p no audio","value":"$0.089955 (was $0.112444)"},{"spec":"per second","label":"Standard 1080p with audio","value":"$0.114489 (was $0.143111)"}],"unit_pricing":[{"unit":"second","usd":"0.024534","label":"Standard 360p no audio"},{"unit":"second","usd":"0.0368","label":"Standard 360p with audio"},{"unit":"second","usd":"0.0368","label":"Standard 540p no audio"},{"unit":"second","usd":"0.044978","label":"Standard 540p with audio"},{"unit":"second","usd":"0.044978","label":"Standard 720p no audio"},{"unit":"second","usd":"0.061334","label":"Standard 720p with audio"},{"unit":"second","usd":"0.089955","label":"Standard 1080p no audio"},{"unit":"second","usd":"0.114489","label":"Standard 1080p with audio"}],"limits":{"note":"Text-to-video and image-to-video up to 15 seconds at 1080p, with native synchronized audio. Prompts can run to 5,000 characters, so one prompt can direct performance, camera movement and shot design in detail.\n\n**Modes**\n\n- `t2v`: text to video.\n- `i2v`: animate a single image.\n- `auto`, the default, uses `i2v` when an image is attached and `t2v` otherwise.\n\n**Output**\n\n- 360p, 540p, 720p and 1080p, 1 to 15 seconds.\n- Aspect ratios 16:9, 4:3, 1:1, 3:4, 9:16, 2:3, 3:2 and 21:9 on text-to-video. Image-to-video follows the source image.\n- Native synchronized audio is on by default; set `generate_audio_switch` to false for a video without it.\n- For several shots in one clip, describe them in order in the prompt, for example \"Shot 1: ... Shot 2: ...\".\n\n**Billing**\n\n- Billed per second of generated video at the rate for the output resolution, with a higher rate when audio is on.\n\n**Input limits**\n\n- One image: PNG, JPEG or WebP, up to 20MB and 10000px on the long edge.\n- First and last frame, reference images, video input and clip extension are not available on this model. Use PixVerse V6 for those."},"notes":"Text-to-video and image-to-video up to 15 seconds at 1080p, with native synchronized audio. Prompts can run to 5,000 characters, so one prompt can direct performance, camera movement and shot design in detail.\n\n**Modes**\n\n- `t2v`: text to video.\n- `i2v`: animate a single image.\n- `auto`, the default, uses `i2v` when an image is attached and `t2v` otherwise.\n\n**Output**\n\n- 360p, 540p, 720p and 1080p, 1 to 15 seconds.\n- Aspect ratios 16:9, 4:3, 1:1, 3:4, 9:16, 2:3, 3:2 and 21:9 on text-to-video. Image-to-video follows the source image.\n- Native synchronized audio is on by default; set `generate_audio_switch` to false for a video without it.\n- For several shots in one clip, describe them in order in the prompt, for example \"Shot 1: ... Shot 2: ...\".\n\n**Billing**\n\n- Billed per second of generated video at the rate for the output resolution, with a higher rate when audio is on.\n\n**Input limits**\n\n- One image: PNG, JPEG or WebP, up to 20MB and 10000px on the long edge.\n- First and last frame, reference images, video input and clip extension are not available on this model. Use PixVerse V6 for those.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=pixverse-v6-max","api_url":"https://docs.empiriolabs.ai/models/pixverse-v6-max","logo":"https://media.empiriolabs.ai/model-logos/pixverse-v6-max.png","status":"available"},{"id":"lightonocr-3-4b","object":"model","created":1791417600,"owned_by":"lighton","display_name":"LightOnOCR-3 4B","author":"lighton","provider":"lighton","description":"Document OCR that reads PDFs and images into structured Markdown, page by page, with tables, math, charts, image regions, and layout.","modality":"document","type":"ocr","category":"ocr","category_label":null,"modality_label":null,"modalities":["document","image","text"],"input_modalities":["image","document"],"output_modalities":["text"],"features":["document_ocr","pdf_to_markdown","tables","charts_to_data","math","layout_and_reading_order","image_regions","headers_and_footers"],"aliases":["lightonai/lightonocr-3-4b"],"structured_output":null,"native_inference":true,"weight_precision":"FP8","hugging_face_id":"lightonai/LightOnOCR-3-4B","batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-10-08","is_new":true,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"document","label":"Document","type":"string","description":"The PDF (document_url) or image (image_url) to read, as a public URL or a base64 data URI, up to 50 MB.","required":true,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"pages","label":"Pages","type":"string","description":"Zero-based pages to read, as a list such as [0, 2] or a string such as 0,2-4. Every page when empty, up to 1,000.","required":false,"metadata":{}},{"name":"include_image_base64","label":"Image Data","type":"boolean","description":"Return each image region on the page as a JPEG data URI.","required":false,"metadata":{},"default":false},{"name":"table_format","label":"Table Format","type":"enum","description":"Return each table separately in this format. Tables stay in the page Markdown as HTML when unset.","required":false,"metadata":{},"options":["markdown","html"]},{"name":"extract_header","label":"Extract Header","type":"boolean","description":"Move the page header out of the Markdown into its own field.","required":false,"metadata":{},"default":false},{"name":"extract_footer","label":"Extract Footer","type":"boolean","description":"Move the page footer out of the Markdown into its own field.","required":false,"metadata":{},"default":false},{"name":"image_limit","label":"Image Limit","type":"number","description":"Return at most this many images for the whole document, the first ones first.","required":false,"metadata":{},"min":0},{"name":"image_min_size","label":"Minimum Image Size","type":"number","description":"Leave out image regions narrower or shorter than this many pixels.","required":false,"metadata":{},"min":0},{"name":"include_blocks","label":"Layout Blocks","type":"boolean","description":"Include every region of each page in reading order, with its type, position and content.","required":false,"metadata":{},"default":true}],"supported_endpoints":["POST /v1/ocr"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per 1,000 pages, minimum 5 pages per request","label":"Document OCR","value":"$3.00"}],"unit_pricing":[{"unit":"1k_pages","usd":"3","label":"Document OCR","minimum_usd":"0.015"}],"limits":{"note":"Reads PDFs and images into Markdown, page by page: text in reading order, headings, lists, tables, math, captions, and charts with their data points as a table.\n\n**Input**\n\n- One PDF or image per request: PDF, PNG, JPEG, WebP, TIFF, BMP, GIF or AVIF, up to 50 MB, as a public URL or a base64 data URI.\n- Up to 1,000 pages per request. Choose pages with `pages`, zero-based, as a list such as `[0, 2]` or a string such as `0,2-4`.\n- Structured annotation fields are not supported.\n\n**Output**\n\n- Each page as Markdown, with the position of every image region and the page's layout blocks in reading order.\n- `include_image_base64` returns each image region as a JPEG data URI.\n- `table_format` set to `markdown` or `html` returns each table separately; otherwise tables stay in the Markdown as HTML.\n- `extract_header` and `extract_footer` move headers and footers out of the Markdown into their own fields.\n\n**Long documents**\n\n- A request still running after about four and a half minutes returns a job id to poll at `GET /v1/jobs/{job_id}`. Send `Prefer: respond-async` to get it at once.\n\n**Billing**\n\n- Billed per page read, with a minimum of 5 pages per request. A failed request is not billed for pages it did not return.\n\n**Weights**\n\n- FP8."},"notes":"Reads PDFs and images into Markdown, page by page: text in reading order, headings, lists, tables, math, captions, and charts with their data points as a table.\n\n**Input**\n\n- One PDF or image per request: PDF, PNG, JPEG, WebP, TIFF, BMP, GIF or AVIF, up to 50 MB, as a public URL or a base64 data URI.\n- Up to 1,000 pages per request. Choose pages with `pages`, zero-based, as a list such as `[0, 2]` or a string such as `0,2-4`.\n- Structured annotation fields are not supported.\n\n**Output**\n\n- Each page as Markdown, with the position of every image region and the page's layout blocks in reading order.\n- `include_image_base64` returns each image region as a JPEG data URI.\n- `table_format` set to `markdown` or `html` returns each table separately; otherwise tables stay in the Markdown as HTML.\n- `extract_header` and `extract_footer` move headers and footers out of the Markdown into their own fields.\n\n**Long documents**\n\n- A request still running after about four and a half minutes returns a job id to poll at `GET /v1/jobs/{job_id}`. Send `Prefer: respond-async` to get it at once.\n\n**Billing**\n\n- Billed per page read, with a minimum of 5 pages per request. A failed request is not billed for pages it did not return.\n\n**Weights**\n\n- FP8.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=lightonocr-3-4b","api_url":"https://docs.empiriolabs.ai/models/lightonocr-3-4b","logo":"https://media.empiriolabs.ai/model-logos/lightonocr-3-4b.png","status":"available"},{"id":"moss-image-turbo","object":"model","created":1792108800,"owned_by":"openmoss","display_name":"MOSS-Image Turbo","author":"openmoss","provider":"openmoss","description":"OpenMOSS text-to-image model that renders accurate English and Chinese text in signs, posters, and layouts, with aspect ratio and seed controls.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text"],"output_modalities":["image"],"features":["image_generation","text_rendering","multilingual_text","seed_control"],"aliases":[],"structured_output":null,"native_inference":true,"weight_precision":"INT8","hugging_face_id":"OpenMOSS-Team/MOSS-Image-SFT","batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-10-16","is_new":true,"is_featured":false,"discount":{"label":"Save up to 70%","percent":70},"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Text description of the image to generate, up to 4,000 characters.","required":true,"metadata":{}},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio. Used when size, width and height are unset.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"1:1","options":["1:1","16:9","9:16","4:3","3:4","3:2","2:3"]},{"name":"size","label":"Size","type":"string","description":"Explicit WIDTHxHEIGHT override. Each side is a multiple of 16 from 512 to 2048 pixels, and width x height is at most 1,048,576 pixels. Leave unset to use aspect_ratio.","required":false,"metadata":{"max_product_pixels":1048576}},{"name":"width","label":"Width","type":"number","description":"Output width in pixels, a multiple of 16. Set width and height together. Width x height must be at most 1,048,576 pixels.","required":false,"metadata":{"ui":{"step":16},"paired_dimension":"height","max_product_pixels":1048576},"min":512,"max":2048},{"name":"height","label":"Height","type":"number","description":"Output height in pixels, a multiple of 16. Set width and height together. Width x height must be at most 1,048,576 pixels.","required":false,"metadata":{"ui":{"step":16},"paired_dimension":"width","max_product_pixels":1048576},"min":512,"max":2048},{"name":"seed","label":"Seed","type":"number","description":"Random seed. Leave unset for a random one; each image returns the seed it used.","required":false,"metadata":{},"min":0,"max":2147483647},{"name":"num_images","label":"Num Images","type":"number","description":"How many images to generate (1-4).","required":false,"metadata":{},"default":1,"min":1,"max":4},{"name":"format","label":"Format","type":"enum","description":"Image file codec for the generated output.","required":false,"metadata":{"aliases":["output_format"]},"default":"webp","options":["webp","png","jpg","jpeg"]},{"name":"response_format","label":"Response Format","type":"enum","description":"Return a signed media URL by default, or base64 JSON when requested.","required":false,"metadata":{},"default":"url","options":["url","b64_json"]},{"name":"return_base64","label":"Return Base64","type":"boolean","description":"Compatibility alias for response_format=b64_json.","required":false,"metadata":{"aliases":["b64_json"],"visible_when":{"op":"eq","field":"response_format","value":"b64_json"}},"default":false}],"supported_endpoints":["POST /v1/images/generations"],"pricing":{"prompt":"0","completion":"0","image":"0.015","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Image generation","value":"$0.015 (was $0.05)"}],"unit_pricing":[{"unit":"image","usd":"0.015","label":"Image generation"}],"limits":{"note":"Generates images from text, with accurate English and Chinese text in signs, posters, labels, and layouts.\n\n**Input**\n\n- A text prompt of up to 4,000 characters. Image inputs, negative prompts, and LoRA adapters are not supported.\n- Size from `aspect_ratio` (1:1, 16:9, 9:16, 4:3, 3:4, 3:2, or 2:3), from `size` as `WIDTHxHEIGHT`, or from `width` and `height`. Each side is a multiple of 16 from 512 to 2,048 pixels, and width x height is at most 1,048,576 pixels. The default is 1024x1024.\n- Up to 4 images per request with `num_images`.\n\n**Output**\n\n- WebP by default, or PNG or JPEG with `format`.\n- A signed URL by default, or base64 with `response_format` set to `b64_json`.\n- Each image carries the `seed` it used.\n\n**Content safety**\n\nGenerated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.\n\n**Weights**\n\n- INT8."},"notes":"Generates images from text, with accurate English and Chinese text in signs, posters, labels, and layouts.\n\n**Input**\n\n- A text prompt of up to 4,000 characters. Image inputs, negative prompts, and LoRA adapters are not supported.\n- Size from `aspect_ratio` (1:1, 16:9, 9:16, 4:3, 3:4, 3:2, or 2:3), from `size` as `WIDTHxHEIGHT`, or from `width` and `height`. Each side is a multiple of 16 from 512 to 2,048 pixels, and width x height is at most 1,048,576 pixels. The default is 1024x1024.\n- Up to 4 images per request with `num_images`.\n\n**Output**\n\n- WebP by default, or PNG or JPEG with `format`.\n- A signed URL by default, or base64 with `response_format` set to `b64_json`.\n- Each image carries the `seed` it used.\n\n**Content safety**\n\nGenerated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.\n\n**Weights**\n\n- INT8.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=moss-image-turbo","api_url":"https://docs.empiriolabs.ai/models/moss-image-turbo","logo":"https://media.empiriolabs.ai/model-logos/moss-image-turbo.png","status":"available"},{"id":"stable-audio-3-medium","object":"model","created":1779235200,"owned_by":"stability","display_name":"Stable Audio 3 Medium","author":"stability","provider":"stability","description":"Stability AI text-to-audio model for music and sound effects, 44.1 kHz stereo clips up to 380 seconds, with length, step and seed controls.","modality":"audio","type":"generation","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["music_generation","text_to_audio","sound_effects","seed_control"],"aliases":["stabilityai/stable-audio-3-medium"],"structured_output":null,"native_inference":true,"weight_precision":"FP16","hugging_face_id":"stabilityai/stable-audio-3-medium","batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-05-20","is_new":true,"is_featured":false,"discount":{"label":"Save up to 27%","percent":27},"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"The music or sound to generate.","required":true,"metadata":{"aliases":["description"]}},{"name":"audio_duration","label":"Duration","type":"number","description":"Clip length in seconds, from 1 to 380.","required":false,"metadata":{"aliases":["duration","duration_seconds"]},"default":30,"min":1,"max":380},{"name":"num_inference_steps","label":"Steps","type":"number","description":"Sampling steps, from 4 to 8.","required":false,"metadata":{"aliases":["steps"]},"default":8,"min":4,"max":8},{"name":"seed","label":"Seed","type":"number","description":"Random seed. Leave unset for a random one.","required":false,"metadata":{},"min":0,"max":2147483647},{"name":"format","label":"Format","type":"enum","description":"Audio file format of the generated clip.","required":false,"metadata":{"aliases":["output_format"]},"default":"mp3","options":["mp3","wav","flac","ogg"]},{"name":"response_format","label":"Response Format","type":"enum","description":"Return a signed media URL by default, or base64 JSON when requested.","required":false,"metadata":{},"default":"url","options":["url","b64_json"]},{"name":"return_base64","label":"Return Base64","type":"boolean","description":"Compatibility alias for response_format=b64_json.","required":false,"metadata":{"aliases":["b64_json"],"visible_when":{"op":"eq","field":"response_format","value":"b64_json"}},"default":false}],"supported_endpoints":["POST /v1/audio/generations"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0.035","input_cache_read":"0"},"pricing_rows":[{"spec":"per request","label":"Generation","value":"$0.035 (was $0.0479)"}],"unit_pricing":[{"unit":"request","usd":"0.035","label":"Generation"}],"limits":{"note":"Generates music and sound effects from text: 44.1 kHz stereo, from 1 to 380 seconds per clip. Powered by Stability AI.\n\n**Input**\n\n- A text prompt describing the music or sound: genre, instruments, mood, tempo, or the effect.\n- `audio_duration` sets the length in seconds, from 1 to 380. The default is 30.\n- `num_inference_steps` from 4 to 8. The default is 8.\n- `seed` repeats a result. Negative prompts, lyrics and audio inputs are not supported.\n\n**Output**\n\n- MP3 by default, or WAV, FLAC or Ogg with `format`.\n- A signed URL by default, or base64 with `response_format` set to `b64_json`.\n\n**Billing**\n\n- Billed per clip, whatever its length. A request that fails is not billed.\n\n**Weights**\n\n- FP16."},"notes":"Generates music and sound effects from text: 44.1 kHz stereo, from 1 to 380 seconds per clip. Powered by Stability AI.\n\n**Input**\n\n- A text prompt describing the music or sound: genre, instruments, mood, tempo, or the effect.\n- `audio_duration` sets the length in seconds, from 1 to 380. The default is 30.\n- `num_inference_steps` from 4 to 8. The default is 8.\n- `seed` repeats a result. Negative prompts, lyrics and audio inputs are not supported.\n\n**Output**\n\n- MP3 by default, or WAV, FLAC or Ogg with `format`.\n- A signed URL by default, or base64 with `response_format` set to `b64_json`.\n\n**Billing**\n\n- Billed per clip, whatever its length. A request that fails is not billed.\n\n**Weights**\n\n- FP16.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=stable-audio-3-medium","api_url":"https://docs.empiriolabs.ai/models/stable-audio-3-medium","logo":"https://media.empiriolabs.ai/model-logos/stable-audio-3-medium.png","status":"available"},{"id":"qwen-audio-3-1-tts-plus","object":"model","created":1792540800,"owned_by":"alibaba","display_name":"Qwen Audio 3.1 TTS Plus","author":"alibaba","provider":"alibaba","description":"Speech synthesis for narration and dubbing, with 4 multilingual voices, plain-language delivery direction, inline emotion tags, and voice cloning.","modality":"audio","type":"tts","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["text"],"output_modalities":["audio"],"features":["text_to_speech","multilingual","expressive_prosody","emotion_control","voice_tags","streaming","realtime","voice_cloning"],"aliases":["qwen-audio-3.1-tts-plus","alibaba/qwen-audio-3-1-tts-plus"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-10-21","is_new":true,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input","label":"Input","type":"string","description":"Text to synthesize, up to 10,000 characters per request. These inline tags change the delivery from the point where they appear: [sad], [amazed], [deep and loud shouting], [trembling], [angry], [excited], [sarcastic], [curious], [like dracula], [bored], [tired], [scornful], [shouting], [asmr], [panicked], [mischievously], [empathetic], [whispers], [reluctantly], [crying], [serious], [very slowly], [very fast]. These add a one-time sound at that point: [gasp], [sighing], [clears throat], [giggles], [laughing], [cough], [snorts].","required":true,"metadata":{"ui":{"control":"textarea","section":"Input"}},"max":10000},{"name":"voice","label":"Voice","type":"enum","description":"Voice preset. The 4 voices read Chinese, English, and other languages. Every voice id ends in _v3.1, for example longanlingxin_v3.1. custom clones a voice from voice_audio_url, and the response's voice_id then works here for 7 days. GET /v1/voices lists your custom voices with their ids.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Voice"},"saved_voices":true,"option_labels":{"custom":"Custom","longanhuan_v3.1":"An Huan (Multilingual, Female)","xunanchuan_v3.1":"Xu Nan Chuan (Multilingual, Male)","longanfengyue_v3.1":"An Feng Yue (Multilingual, Female)","longanlingxin_v3.1":"An Ling Xin (Multilingual, Female)"}},"default":"longanlingxin_v3.1","options":["longanlingxin_v3.1","longanhuan_v3.1","longanfengyue_v3.1","xunanchuan_v3.1","custom"]},{"name":"voice_audio_url","label":"Reference audio URL","type":"string","description":"voice=custom only: an https URL to a 10 to 20 second recording of clear speech from one speaker, the voice to clone (WAV, MP3, M4A, OGG, WEBM or FLAC, up to 15 MB). Record it in a quiet room, without music or other voices.","required":false,"metadata":{"control":"audio-clip","max_seconds":20,"min_seconds":10,"visible_when":{"op":"eq","field":"voice","value":"custom"},"required_when":{"op":"eq","field":"voice","value":"custom"},"clear_when_hidden":true}},{"name":"response_format","label":"Response Format","type":"enum","description":"Audio container. mp3 and opus are compressed, wav is uncompressed PCM in a RIFF header, and pcm is headerless raw samples for chunked playback. On the realtime WebSocket the default is pcm and wav is not available.","required":false,"metadata":{"ui":{"control":"segmented","section":"Output"}},"default":"mp3","options":["mp3","wav","pcm","opus"]},{"name":"sample_rate","label":"Sample Rate","type":"enum","description":"Output sample rate in Hz. 24000 suits speech playback, and 48000 gives broadcast-quality output at a larger file size.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Output"}},"default":24000,"options":["8000","12000","16000","22050","24000","44100","48000"]},{"name":"speed","label":"Speed","type":"number","description":"Speaking rate multiplier. 0.5 is half speed and 2.0 is double speed.","required":false,"metadata":{"ui":{"step":0.05,"control":"slider","section":"Delivery"}},"default":1,"min":0.5,"max":2},{"name":"pitch","label":"Pitch","type":"number","description":"Pitch multiplier. Values below 1.0 lower the voice and values above raise it. Pitch also shifts the pace of the rendered audio, so pair it with speed when you want to keep the original duration.","required":false,"metadata":{"ui":{"step":0.05,"control":"slider","section":"Delivery"}},"default":1,"min":0.5,"max":2},{"name":"volume","label":"Volume","type":"number","description":"Output loudness, where 50 is the reference level.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Delivery"}},"default":50,"min":0,"max":100},{"name":"instruction","label":"Instruction","type":"string","description":"Natural-language direction for delivery, up to 1,000 characters. Controls emotion, tone, character, pace, and speaking style, for example 'Speak quickly in an excited, upbeat tone' or 'Read slowly like a late-night radio host'.","required":false,"metadata":{"ui":{"control":"textarea","section":"Delivery","placeholder":"Speak quickly in an excited, upbeat tone"}},"max":1000},{"name":"language_hints","label":"Language Hints","type":"string","description":"Language codes that bias pronunciation for mixed-language text, for example [\"zh\", \"en\"]. Leave unset to let the model detect the language.","required":false,"metadata":{"ui":{"control":"json","section":"Delivery"}}},{"name":"seed","label":"Seed","type":"number","description":"Sampling seed. Reuse a seed with identical input and settings for a repeatable render.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced"}},"default":0,"min":0,"max":65535},{"name":"bit_rate","label":"Bit Rate","type":"number","description":"Encoder bitrate in bps. Applies to the opus format only, and is ignored for mp3, wav, and pcm.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced"}},"default":32000,"min":6000,"max":510000},{"name":"pronunciation","label":"Pronunciation","type":"string","description":"Pronunciation overrides keyed by the written form, for example {\"重要\": \"zhong4 yao4\"}. Use it to fix names, acronyms, and homographs.","required":false,"metadata":{"ui":{"control":"json","section":"Advanced"}}},{"name":"replace","label":"Replace","type":"string","description":"Literal text substitutions applied before synthesis, for example {\"EmpirioLabs\": \"Empirio Labs\"}. Useful for brand names and abbreviations.","required":false,"metadata":{"ui":{"control":"json","section":"Advanced"}}},{"name":"enable_markdown_filter","label":"Markdown Filter","type":"boolean","description":"Strip Markdown syntax such as asterisks and underscores before synthesis so formatting characters are not read aloud.","required":false,"metadata":{"ui":{"control":"toggle","section":"Advanced"}},"default":false}],"supported_endpoints":["POST /v1/audio/speech","POST /v1/audio/speech:stream","WEBSOCKET /v1/realtime","GET /v1/voices"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per 10,000 characters","label":"Synthesis","value":"$0.60"}],"unit_pricing":[{"unit":"10k_characters","usd":"0.6","label":"Synthesis"}],"limits":{"note":"**Voices**\n\n- 4 voices that read Chinese, English, and other languages: `longanlingxin_v3.1`, `longanhuan_v3.1`, and `longanfengyue_v3.1` are female, and `xunanchuan_v3.1` is male.\n- Every voice id ends in `_v3.1`, for example `longanlingxin_v3.1`.\n\n**Custom voices**\n\n- Set `voice` to `custom` and pass `voice_audio_url`, an https URL to 10 to 20 seconds of clear speech from one speaker.\n- WAV, MP3, M4A, OGG, WEBM and FLAC are accepted, up to 15 MB. Record in a quiet room, without music or other voices.\n- The response includes `voice_id` and `voice_id_expires_at`. Pass the `voice_id` as `voice` to reuse the voice for 7 days, on `POST /v1/audio/speech`, `POST /v1/audio/speech:stream` or the realtime socket, where `session.update` takes the same fields and `session.updated` returns the `voice_id`. Only the account that created it can use it, on this model only.\n- Each account can hold 10 custom voices on this model at a time.\n- `GET /v1/voices?model=qwen-audio-3-1-tts-plus` lists the model's voices, including your custom voices with their ids. Add `type=custom` to list custom voices alone.\n- `DELETE /v1/voices/{voice_id}?model=qwen-audio-3-1-tts-plus` deletes a custom voice, which frees its place at once.\n- In the Playground, set Voice to Custom to use a saved voice again, copy its id, or delete it.\n- Creating, listing and deleting custom voices adds no charge.\n\n**Delivery direction**\n\n- `instruction` sets emotion, tone, character, pace, and speaking style in natural language, up to 1,000 characters.\n- Inline tags inside the text change the delivery from that point, for example `[excited]` or `[whispers]`, or add a one-time sound such as `[laughing]` or `[sighing]`. The full list of tags is on the `input` parameter.\n- SSML input is not supported.\n\n**Input limits**\n\n- Up to 10,000 characters per request.\n- `language_hints` biases pronunciation for mixed-language text.\n\n**Output**\n\n- MP3, WAV, PCM, or Opus at 8,000 to 48,000 Hz.\n- `POST /v1/audio/speech:stream` sends audio chunks while the speech is generated.\n\n**Realtime**\n\n- `WEBSOCKET /v1/realtime?model=qwen-audio-3-1-tts-plus` takes text while it is still being written and returns audio as it is generated. Send `input_text_buffer.append` events, then `input_text_buffer.commit`, or `session.finish` to end the session.\n- Audio arrives in `response.audio.delta` events: 16-bit PCM at 24,000 Hz by default, or MP3 or Opus. Set the voice, instruction, format and other options with `session.update`; a change applies from the next segment.\n- Text is spoken in segments that end at sentence boundaries, and each segment ends with a `response.done` event carrying its usage.\n\n**Billing**\n\n- Billed per character of the input text. A Chinese character counts as two characters, and inline tags count as characters. The instruction is not billed.\n- On the realtime socket each segment is billed for its own characters."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen-audio-3-1-tts-plus","api_url":"https://docs.empiriolabs.ai/models/qwen-audio-3-1-tts-plus","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen-audio-3-1-realtime-flash","object":"model","created":1793059200,"owned_by":"alibaba","display_name":"Qwen Audio 3.1 Realtime Flash","author":"alibaba","provider":"alibaba","description":"Duplex speech conversation over one socket, with 88 voices, tool calling, and separate text and audio token rates.","modality":"audio","type":"realtime","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio","text"],"output_modalities":["audio","text"],"features":["realtime","speech_to_speech","audio_in","audio_out","function_calling","multilingual"],"aliases":["qwen-audio-3.1-realtime-flash","alibaba/qwen-audio-3-1-realtime-flash"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":245760,"context_length":245760,"max_output_tokens":16384,"model_released_at":"2026-10-27","is_new":true,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"voice","label":"Voice","type":"enum","description":"Speaking voice for the session. Set it with session.update before the model produces any audio. These voices are specific to this model.","required":false,"metadata":{},"default":"longanqian_v3.1","options":["longanqian_v3.1","longanhuan_v3.1","longanlingxin_v3.1","longanfengyue_v3.1","xunanchuan_v3.1","beth_v3.1","betty_v3.1","cally_v3.1","longanqian","longanlingxin","longanlufeng","longanlingxi","longanxiaoxin","longanfengyue","longanyuanfei","longanhuan_v3.6","longjielidou_v3.6","longpaopao_v3.6","longhuohuo_v3.6","longchuanshu_v3.6","loongmary","loongeva_v3.6","loongjohn","daniel","echo","hannah","sherry","yuxiaoyun_v3.1","qiaoxiaojiao_v3.1","xiaxiaochen_v3.1","anmingyuan_v3.1","wenhuaiqing_v3.1","anxiaolan_v3.1","xieshurou_v3.1","baiqinglan_v3.1","xuyuyuan_v3.1","anruorou_v3.1","wenhuaizhi_v3.1","xiaoxingzhi_v3.1","guyunshu_v3.1","huozhuoshi_v3.1","yeqinghe_v3.1","yunhuanhuan_v3.1","xuxiaoqiao_v3.1","baianran_v3.1","xuyanchu_v3.1","yezhiqing_v3.1","andi_v3.1","anyuqing_v3.1","emily_v3.1","luna_v3.1","eric_v3.1","luca_v3.1","abby_v3.1","annie_v3.1","ava_v3.1","cindy_v3.1","donna_v3.1","andy_v3.1","brian_v3.1","david_v3.1","longanyuanfei_v3.1","longjielidou_v3.1","longanlingxi_v3.1","longhuohuo_v3.1","longyingtao_v3.1","longanya_v3.1","longwan_v3.1","longxing_v3.1","longhua_v3.1","longhan_v3.1","longanzhi_v3.1","longzhe_v3.1","longanyang_v3.1","libai_v3.1","longling_v3.1","longniuniu_v3.1","longshanshan_v3.1","longpaopao_v3.1","loongstella_v3.1","longyuan_v3.1","longmiao_v3.1","longsanshu_v3.1","longanli_v3.1","longanwen_v3.1","longanlang_v3.1","longxiaoxia_v3.1","longanchong_v3.1"]},{"name":"instructions","label":"Instructions","type":"string","description":"System guidance for how the model should behave and speak during the conversation.","required":false,"metadata":{}},{"name":"input_language","label":"Input language","type":"enum","description":"Language you speak. The transcript of your speech is written in it; auto detects it. Also accepted as input_audio_transcription.language.","required":false,"metadata":{"option_labels":{"ar":"Arabic","de":"German","en":"English","es":"Spanish","fr":"French","id":"Indonesian","it":"Italian","ja":"Japanese","ko":"Korean","pt":"Portuguese","ru":"Russian","th":"Thai","vi":"Vietnamese","zh":"Chinese","auto":"Auto-detect"}},"default":"auto","options":["auto","zh","en","ja","ko","vi","th","id","ar","fr","de","es","pt","ru","it"]},{"name":"output_language","label":"Output language","type":"enum","description":"Language the spoken reply is read in, for example Japanese or Chinese for the same characters. It does not translate the reply: ask for its language in your instructions. auto lets the model choose. Also accepted as output_audio.language.","required":false,"metadata":{"option_labels":{"ar":"Arabic","de":"German","en":"English","es":"Spanish","fr":"French","id":"Indonesian","it":"Italian","ja":"Japanese","ko":"Korean","pt":"Portuguese","ru":"Russian","th":"Thai","vi":"Vietnamese","zh":"Chinese","auto":"Automatic"}},"default":"auto","options":["auto","zh","en","ja","ko","vi","th","id","ar","fr","de","es","pt","ru","it"]},{"name":"speed","label":"Speed","type":"number","description":"Speaking rate of the reply, from 0.5 to 2. Lower values slow the speech and higher values speed it up. Also accepted as speech_rate. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider"}},"min":0.5,"max":2},{"name":"enable_speech_emotion","label":"Expressive delivery","type":"boolean","description":"More pronounced emotion in the spoken reply. Turn it off for a more even delivery.","required":false,"metadata":{},"default":true},{"name":"max_history_turns","label":"History turns","type":"number","description":"How many earlier exchanges the model reads for each reply, from 1 to 50. Fewer exchanges use fewer input tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number"}},"min":1,"max":50},{"name":"modalities","label":"Modalities","type":"string","description":"Which output types the model returns for a turn. Drop audio for a text-only reply.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":["text","audio"]},{"name":"input_audio_format","label":"Input audio format","type":"enum","description":"Encoding of the audio you append to the input buffer: base64 16-bit PCM at 16 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"pcm16","options":["pcm16"]},{"name":"output_audio_format","label":"Output audio format","type":"enum","description":"Encoding of the audio the model streams back: 16-bit PCM at 24 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":24000},"default":"pcm24","options":["pcm24"]},{"name":"turn_detection","label":"Turn detection","type":"string","description":"Voice activity detection: decides when you have finished speaking and the model should reply. It is on by default as server_vad, which ends your turn after a pause. smart_turn also weighs what you said, so filler sounds such as um do not end your turn or interrupt the reply, and smart_turn_v2 also answers bystanders and side remarks less often. threshold is a number from -1 to 1, 0.5 by default; a higher value needs clearer, louder speech to count. With server_vad, silence_duration_ms, from 200 to 6000 and 800 by default, is how long a pause must last to end your turn. Set turn_detection to null to end each turn yourself with input_audio_buffer.commit and response.create.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":{"type":"server_vad"}}],"supported_endpoints":["WEBSOCKET /v1/realtime"],"pricing":{"prompt":"0.00000046","completion":"0.0000014","image":"0","request":"0","input_cache_read":"0.00000046"},"pricing_rows":[{"spec":"per 1M audio input tokens","label":"Input: audio","value":"$1.86"},{"spec":"per 1M prompt tokens","label":"Input","value":"$0.46"},{"spec":"per 1M generated tokens, text-only replies","label":"Output","value":"$1.40"},{"spec":"per 1M generated audio tokens","label":"Output: audio","value":"$3.74"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.86","label":"Input: audio"},{"unit":"1m_tokens","usd":"0.46","label":"Input"},{"unit":"1m_tokens","usd":"3.74","label":"Output: audio"}],"limits":{"note":"**Connecting**\n\nFull-duplex voice over a WebSocket at `wss://api.empiriolabs.ai/v1/realtime?model=qwen-audio-3-1-realtime-flash`, authenticated with the ordinary Authorization Bearer header. Configure the session with `session.update` over the socket: voice, instructions, modalities, turn detection, languages and delivery.\n\n**Sending audio**\n\n- Append microphone audio as `input_audio_buffer.append` events.\n- Voice activity detection decides when you have stopped speaking, so keep streaming for about a second after the speech ends.\n\n**Language and delivery**\n\nSet `input_language` to the language you speak, which the transcript of your speech is written in, and `output_language` to the language the spoken reply is read in. Each takes auto or one of zh, en, ja, ko, vi, th, id, ar, fr, de, es, pt, ru and it. The output language does not translate the reply, so ask for its language in your instructions too. `speed` (0.5 to 2) sets the speaking rate, `enable_speech_emotion` the expressive delivery, and `max_history_turns` (1 to 50) how many earlier exchanges the model reads.\n\n**Voices**\n\nThe voices on this model are its own set. Pick one from the voice list rather than carrying a voice across from another model, or leave it unset and the default is supplied for you.\n\n**Billing**\n\nAudio and text tokens are priced separately in both directions. A spoken reply is billed for its audio output tokens only, and the text output rate applies to replies with no audio. Each completed turn is billed on its own from the usage the model reports."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen-audio-3-1-realtime-flash","api_url":"https://docs.empiriolabs.ai/models/qwen-audio-3-1-realtime-flash","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen-audio-3-0-realtime-plus","object":"model","created":1786320000,"owned_by":"alibaba","display_name":"Qwen Audio 3.0 Realtime Plus","author":"alibaba","provider":"alibaba","description":"Duplex speech conversation over one socket, with 19 voices, tool calling, and separate text and audio token rates.","modality":"audio","type":"realtime","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio","text"],"output_modalities":["audio","text"],"features":["realtime","speech_to_speech","audio_in","audio_out","function_calling","multilingual"],"aliases":["qwen-audio-3.0-realtime-plus","alibaba/qwen-audio-3-0-realtime-plus"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":16384,"context_length":16384,"max_output_tokens":8192,"model_released_at":"2026-08-10","is_new":true,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"voice","label":"Voice","type":"enum","description":"Speaking voice for the session. Set it with session.update before the model produces any audio. These voices are specific to this model.","required":false,"metadata":{},"default":"longanqian","options":["longanqian","longanlingxin","longanlufeng","longanlingxi","longanxiaoxin","longanfengyue","longanyuanfei","longanhuan_v3.6","longjielidou_v3.6","longpaopao_v3.6","longhuohuo_v3.6","longchuanshu_v3.6","loongmary","loongeva_v3.6","loongjohn","daniel","echo","hannah","sherry"]},{"name":"instructions","label":"Instructions","type":"string","description":"System guidance for how the model should behave and speak during the conversation.","required":false,"metadata":{}},{"name":"speed","label":"Speed","type":"number","description":"Speaking rate of the reply, from 0.5 to 2. Lower values slow the speech and higher values speed it up. Also accepted as speech_rate. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider"}},"min":0.5,"max":2},{"name":"enable_speech_emotion","label":"Expressive delivery","type":"boolean","description":"More pronounced emotion in the spoken reply. Turn it off for a more even delivery.","required":false,"metadata":{},"default":true},{"name":"max_history_turns","label":"History turns","type":"number","description":"How many earlier exchanges the model reads for each reply, from 1 to 50. Fewer exchanges use fewer input tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number"}},"min":1,"max":50},{"name":"modalities","label":"Modalities","type":"string","description":"Which output types the model returns for a turn. Drop audio for a text-only reply.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":["text","audio"]},{"name":"input_audio_format","label":"Input audio format","type":"enum","description":"Encoding of the audio you append to the input buffer: base64 16-bit PCM at 16 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"pcm16","options":["pcm16"]},{"name":"output_audio_format","label":"Output audio format","type":"enum","description":"Encoding of the audio the model streams back: 16-bit PCM at 24 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":24000},"default":"pcm24","options":["pcm24"]},{"name":"turn_detection","label":"Turn detection","type":"string","description":"Voice activity detection: decides when you have finished speaking and the model should reply. It is on by default as server_vad, which ends your turn after a pause. smart_turn also weighs what you said, so filler sounds such as um do not end your turn or interrupt the reply, and smart_turn_v2 also answers bystanders and side remarks less often. threshold is a number from -1 to 1, 0.5 by default; a higher value needs clearer, louder speech to count. With server_vad, silence_duration_ms, from 200 to 6000 and 800 by default, is how long a pause must last to end your turn. Set turn_detection to null to end each turn yourself with input_audio_buffer.commit and response.create.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":{"type":"server_vad"}}],"supported_endpoints":["WEBSOCKET /v1/realtime"],"pricing":{"prompt":"0.0000016","completion":"0.0000128","image":"0","request":"0","input_cache_read":"0.0000016"},"pricing_rows":[{"spec":"per 1M audio input tokens","label":"Input: audio","value":"$12.80"},{"spec":"per 1M prompt tokens","label":"Input","value":"$1.60"},{"spec":"per 1M generated tokens, text-only replies","label":"Output","value":"$12.80"},{"spec":"per 1M generated audio tokens","label":"Output: audio","value":"$48.00"}],"unit_pricing":[{"unit":"1m_tokens","usd":"12.8","label":"Input: audio"},{"unit":"1m_tokens","usd":"1.6","label":"Input"},{"unit":"1m_tokens","usd":"48","label":"Output: audio"}],"limits":{"note":"**Connecting**\n\nFull-duplex voice over a WebSocket at `wss://api.empiriolabs.ai/v1/realtime?model=qwen-audio-3-0-realtime-plus`, authenticated with the ordinary Authorization Bearer header. Configure the session with `session.update` over the socket: voice, instructions, modalities, turn detection and delivery.\n\n**Sending audio**\n\n- Append microphone audio as `input_audio_buffer.append` events.\n- Voice activity detection decides when you have stopped speaking, so keep streaming for about a second after the speech ends.\n\n**Delivery**\n\n`speed` (0.5 to 2) sets the speaking rate, `enable_speech_emotion` the expressive delivery, and `max_history_turns` (1 to 50) how many earlier exchanges the model reads. Ask for the reply's language in your instructions.\n\n**Voices**\n\nThe voices on this model are its own set. Pick one from the voice list rather than carrying a voice across from another model, or leave it unset and the default is supplied for you.\n\n**Billing**\n\nAudio and text tokens are priced separately in both directions. A spoken reply is billed for its audio output tokens only, and the text output rate applies to replies with no audio. Each completed turn is billed on its own from the usage the model reports."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen-audio-3-0-realtime-plus","api_url":"https://docs.empiriolabs.ai/models/qwen-audio-3-0-realtime-plus","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen-audio-3-0-realtime-flash","object":"model","created":1786320000,"owned_by":"alibaba","display_name":"Qwen Audio 3.0 Realtime Flash","author":"alibaba","provider":"alibaba","description":"Duplex speech conversation tuned for fast replies, with 19 voices, tool calling, and separate text and audio token rates.","modality":"audio","type":"realtime","category":"audio","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio","text"],"output_modalities":["audio","text"],"features":["realtime","speech_to_speech","audio_in","audio_out","function_calling","multilingual"],"aliases":["qwen-audio-3.0-realtime-flash","alibaba/qwen-audio-3-0-realtime-flash"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":16384,"context_length":16384,"max_output_tokens":8192,"model_released_at":"2026-08-10","is_new":true,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"voice","label":"Voice","type":"enum","description":"Speaking voice for the session. Set it with session.update before the model produces any audio. These voices are specific to this model.","required":false,"metadata":{},"default":"longanqian","options":["longanqian","longanlingxin","longanlufeng","longanlingxi","longanxiaoxin","longanfengyue","longanyuanfei","longanhuan_v3.6","longjielidou_v3.6","longpaopao_v3.6","longhuohuo_v3.6","longchuanshu_v3.6","loongmary","loongeva_v3.6","loongjohn","daniel","echo","hannah","sherry"]},{"name":"instructions","label":"Instructions","type":"string","description":"System guidance for how the model should behave and speak during the conversation.","required":false,"metadata":{}},{"name":"speed","label":"Speed","type":"number","description":"Speaking rate of the reply, from 0.5 to 2. Lower values slow the speech and higher values speed it up. Also accepted as speech_rate. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider"}},"min":0.5,"max":2},{"name":"enable_speech_emotion","label":"Expressive delivery","type":"boolean","description":"More pronounced emotion in the spoken reply. Turn it off for a more even delivery.","required":false,"metadata":{},"default":true},{"name":"max_history_turns","label":"History turns","type":"number","description":"How many earlier exchanges the model reads for each reply, from 1 to 50. Fewer exchanges use fewer input tokens. When omitted, the model's own default applies.","required":false,"metadata":{"ui":{"control":"number"}},"min":1,"max":50},{"name":"modalities","label":"Modalities","type":"string","description":"Which output types the model returns for a turn. Drop audio for a text-only reply.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":["text","audio"]},{"name":"input_audio_format","label":"Input audio format","type":"enum","description":"Encoding of the audio you append to the input buffer: base64 16-bit PCM at 16 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"pcm16","options":["pcm16"]},{"name":"output_audio_format","label":"Output audio format","type":"enum","description":"Encoding of the audio the model streams back: 16-bit PCM at 24 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":24000},"default":"pcm24","options":["pcm24"]},{"name":"turn_detection","label":"Turn detection","type":"string","description":"Voice activity detection: decides when you have finished speaking and the model should reply. It is on by default as server_vad, which ends your turn after a pause. smart_turn also weighs what you said, so filler sounds such as um do not end your turn or interrupt the reply, and smart_turn_v2 also answers bystanders and side remarks less often. threshold is a number from -1 to 1, 0.5 by default; a higher value needs clearer, louder speech to count. With server_vad, silence_duration_ms, from 200 to 6000 and 800 by default, is how long a pause must last to end your turn. Set turn_detection to null to end each turn yourself with input_audio_buffer.commit and response.create.","required":false,"metadata":{"ui":{"hide_in_playground":true}},"default":{"type":"server_vad"}}],"supported_endpoints":["WEBSOCKET /v1/realtime"],"pricing":{"prompt":"0.00000046","completion":"0.0000014","image":"0","request":"0","input_cache_read":"0.00000046"},"pricing_rows":[{"spec":"per 1M audio input tokens","label":"Input: audio","value":"$1.86"},{"spec":"per 1M prompt tokens","label":"Input","value":"$0.46"},{"spec":"per 1M generated tokens, text-only replies","label":"Output","value":"$1.40"},{"spec":"per 1M generated audio tokens","label":"Output: audio","value":"$3.74"}],"unit_pricing":[{"unit":"1m_tokens","usd":"1.86","label":"Input: audio"},{"unit":"1m_tokens","usd":"0.46","label":"Input"},{"unit":"1m_tokens","usd":"3.74","label":"Output: audio"}],"limits":{"note":"**Connecting**\n\nFull-duplex voice over a WebSocket at `wss://api.empiriolabs.ai/v1/realtime?model=qwen-audio-3-0-realtime-flash`, authenticated with the ordinary Authorization Bearer header. Configure the session with `session.update` over the socket: voice, instructions, modalities, turn detection and delivery.\n\n**Sending audio**\n\n- Append microphone audio as `input_audio_buffer.append` events.\n- Voice activity detection decides when you have stopped speaking, so keep streaming for about a second after the speech ends.\n\n**Delivery**\n\n`speed` (0.5 to 2) sets the speaking rate, `enable_speech_emotion` the expressive delivery, and `max_history_turns` (1 to 50) how many earlier exchanges the model reads. Ask for the reply's language in your instructions.\n\n**Voices**\n\nThe voices on this model are its own set. Pick one from the voice list rather than carrying a voice across from another model, or leave it unset and the default is supplied for you.\n\n**Billing**\n\nAudio and text tokens are priced separately in both directions. A spoken reply is billed for its audio output tokens only, and the text output rate applies to replies with no audio. Each completed turn is billed on its own from the usage the model reports."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen-audio-3-0-realtime-flash","api_url":"https://docs.empiriolabs.ai/models/qwen-audio-3-0-realtime-flash","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen-audio-3-0-asr","object":"model","created":1785369600,"owned_by":"alibaba","display_name":"Qwen Audio 3.0 ASR","author":"alibaba","provider":"alibaba","description":"Speech-to-text for short clips and long recordings, with timed sentence segments and recognition of 30 languages and the major Chinese dialects.","modality":"audio","type":"stt","category":"transcription","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio"],"output_modalities":["text"],"features":["transcription","speech_to_text","multilingual"],"aliases":["qwen-audio-3.0-asr","alibaba/qwen-audio-3-0-asr"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-07-30","is_new":true,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[],"supported_endpoints":["POST /v1/audio/transcriptions"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per hour of audio","label":"Transcription","value":"$0.252"}],"unit_pricing":[{"unit":"hour","usd":"0.252","label":"Transcription"}],"limits":{"note":"**Sending audio**\n\nSend a file as multipart `file`, or JSON with `audio_url` or `audio_base64`, in common audio formats. Short clips and long recordings are both accepted.\n\n**Getting the result**\n\nThe request returns a `job_id` and a `poll_url` right away. Poll `GET /v1/jobs/<job-id>` until `status` is `completed`. Short clips finish in seconds; long recordings take longer.\n\n**What comes back**\n\nThe `result` of the completed job holds the full transcript as `text` and sentence segments with start and end times. The language is detected automatically, including Chinese dialects.\n\n**Billing**\n\nBilled per second of audio, rounded up to the next whole second, at the hourly rate shown."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen-audio-3-0-asr","api_url":"https://docs.empiriolabs.ai/models/qwen-audio-3-0-asr","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen-audio-3-0-asr-stream","object":"model","created":1785369600,"owned_by":"alibaba","display_name":"Qwen Audio 3.0 ASR Stream","author":"alibaba","provider":"alibaba","description":"Live transcription over a socket, streaming partial words while the speaker talks and a settled sentence at each pause, priced per hour of audio.","modality":"audio","type":"realtime","category":"transcription","category_label":null,"modality_label":null,"modalities":["audio","text"],"input_modalities":["audio"],"output_modalities":["text"],"features":["transcription","speech_to_text","realtime","streaming_asr","multilingual"],"aliases":["qwen-audio-3.0-asr-stream","alibaba/qwen-audio-3-0-asr-stream"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-07-30","is_new":true,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":false,"audio":true,"video":false,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"input_audio_format","label":"Input audio format","type":"enum","description":"Encoding of the audio you append to the input buffer: base64 16-bit PCM, mono, at 16 kHz.","required":false,"metadata":{"ui":{"hide_in_playground":true},"sample_rate":16000},"default":"pcm16","options":["pcm16"]},{"name":"language","label":"Language","type":"enum","description":"Language of the speech, or auto to detect it from the audio. Set it with the language query parameter of the connection URL, or as input_audio_transcription.language in session.update.","required":false,"metadata":{"ui":{"section":"Recognition"},"option_labels":{"ar":"Arabic","bg":"Bulgarian","cs":"Czech","da":"Danish","de":"German","el":"Greek","en":"English","es":"Spanish","fi":"Finnish","fr":"French","hi":"Hindi","hr":"Croatian","hu":"Hungarian","id":"Indonesian","it":"Italian","ja":"Japanese","ko":"Korean","ms":"Malay","nl":"Dutch","no":"Norwegian","pl":"Polish","pt":"Portuguese","ro":"Romanian","ru":"Russian","sk":"Slovak","sv":"Swedish","th":"Thai","tl":"Filipino","vi":"Vietnamese","zh":"Chinese","auto":"Detect automatically"}},"default":"auto","options":["auto","zh","en","ja","ko","vi","th","id","ms","tl","hi","ar","fr","de","es","pt","ru","it","nl","sv","da","fi","no","el","pl","cs","hu","ro","bg","hr","sk"]},{"name":"prompt","label":"Prompt","type":"string","description":"Text that guides recognition, up to 400 characters: the names and terms the speaker uses, or the text spoken just before this audio. Write the words exactly as they should appear in the transcript. Also accepted as input_audio_transcription.prompt.","required":false,"metadata":{"ui":{"section":"Recognition"}}},{"name":"silence_duration_ms","label":"Silence duration (ms)","type":"number","description":"The pause, in milliseconds, that ends a sentence, from 200 to 6000. A shorter pause settles each sentence sooner; a longer one keeps a pause inside a sentence. Also accepted as turn_detection.silence_duration_ms.","required":false,"metadata":{"ui":{"step":100,"control":"slider","section":"Recognition"}},"default":800,"min":200,"max":6000},{"name":"threshold","label":"Speech threshold","type":"number","description":"How clear speech must be before it is transcribed, from 0.0 to 1.0. A higher value ignores more background noise and can miss quiet speech. When omitted, the model's own default applies. Also accepted as turn_detection.threshold.","required":false,"metadata":{"ui":{"step":0.05,"section":"Recognition"}},"min":0,"max":1},{"name":"noise_reduction","label":"Noise reduction","type":"enum","description":"The microphone the speech detection is tuned for: near_field for a headset or a phone held close, far_field for a laptop or room microphone. Also accepted as input_audio_noise_reduction.type.","required":false,"metadata":{"ui":{"section":"Recognition"},"option_labels":{"far_field":"Far field","near_field":"Near field"}},"default":"far_field","options":["far_field","near_field"]},{"name":"keep_dialect","label":"Keep dialect","type":"boolean","description":"Keeps Chinese dialect words as spoken. When off, dialect speech is written as standard Mandarin.","required":false,"metadata":{"ui":{"section":"Recognition"}},"default":false}],"supported_endpoints":["WEBSOCKET /v1/realtime"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per hour of audio","label":"Transcription","value":"$0.648"}],"unit_pricing":[{"unit":"hour","usd":"0.648","label":"Transcription"}],"limits":{"note":"**Connecting**\n\nLive transcription over a WebSocket at `wss://api.empiriolabs.ai/v1/realtime?model=qwen-audio-3-0-asr-stream`, authenticated with the ordinary Authorization Bearer header.\n\n**Sending audio**\n\nStream 16 kHz mono pcm16 audio with `input_audio_buffer.append`. Voice activity detection decides where each sentence ends, so there is no commit to send.\n\n**Session settings**\n\nSend `session.update` right after `session.created`, before the first audio, with any of these settings: `input_audio_transcription.language` (or the `language` query parameter of the connection URL; `auto` by default), `input_audio_transcription.prompt` with the names and terms the speaker uses (up to 400 characters), `turn_detection.silence_duration_ms` (200 to 6000, default 800) and `turn_detection.threshold` (0.0 to 1.0), and `input_audio_noise_reduction` (`near_field` or `far_field`). `keep_dialect` keeps Chinese dialect words as spoken. A setting changed while audio is streaming ends the sentence in progress and applies to the audio sent after it.\n\n**What comes back**\n\n`conversation.item.input_audio_transcription.delta` events carry the sentence so far while the speaker is still talking, and `conversation.item.input_audio_transcription.completed` carries the settled sentence at each pause.\n\n**Billing**\n\nBilled per second of the audio you stream, silence included, at the hourly rate shown. The session is billed when it ends."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen-audio-3-0-asr-stream","api_url":"https://docs.empiriolabs.ai/models/qwen-audio-3-0-asr-stream","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"minimax-h3-highspeed","object":"model","created":1735689600,"owned_by":"minimax","display_name":"MiniMax H3 Highspeed","author":"minimax","provider":"minimax","description":"Fast 4 to 15 second 768p clips with native stereo audio, from text, a first and last frame, or image, video, and audio references in one request.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image","audio"],"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"features":["video_generation","image_to_video","audio_out","audio_in","multimodal"],"aliases":["minimax/minimax-h3-highspeed","minimax/h3-highspeed"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":true,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description, up to 7000 characters. Can describe action, camera work, dialogue, sound effects, and on-screen text.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"auto: detect from the inputs. t2v: text-to-video. i2v: animate one image as the opening frame. flf: transition from a first frame to a last frame. r2v: reference-to-video from images, videos, and audio.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v","flf","r2v"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution.","required":false,"metadata":{},"default":"768p","options":["768p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio. Adaptive follows the supplied input media.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"adaptive","options":["adaptive","21:9","16:9","4:3","1:1","3:4","9:16"]},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds, whole numbers only.","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":6,"min":4,"max":15},{"name":"image","label":"Image","type":"string","description":"Image URL. One opening frame for image-to-video, or up to 9 reference images for reference-to-video.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"last_frame","label":"Last Frame","type":"string","description":"Closing frame image URL. Supplying it selects first and last frame mode.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"video","label":"Video","type":"string","description":"Reference video URL, up to 3 clips of 2 to 15 seconds each and 15 seconds in total. Reference video is billed for its own duration in addition to the generated clip.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"audio","label":"Audio","type":"string","description":"Reference audio URL, up to 3 clips of 2 to 15 seconds each. Requires an accompanying reference image or video.","required":false,"metadata":{"ui":{"hide_in_playground":true}}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"768p","value":"$0.06"},{"spec":"per input image after the first 5","label":"Reference image input","value":"$0.03"}],"unit_pricing":[{"unit":"second","usd":"0.06","label":"768p"}],"limits":{"note":"Generates 4 to 15 second clips at 24 fps in 768p, each with a native stereo audio track.\n\n**Modes**\n\n- Text to video: prompt only.\n- Image to video: one image becomes the opening frame.\n- First and last frame: supply an opening and a closing image.\n- Reference to video: up to 9 images, 3 videos and 3 audio clips, 12 reference files in total.\n\n**Reference media**\n\n- Images 256 to 5760 px per side, aspect ratio between 0.4 and 2.5, up to 30 MB each.\n- Videos 2 to 15 seconds each and 15 seconds in total, H.264 or H.265, up to 50 MB each.\n- Audio 2 to 15 seconds, WAV or MP3, up to 15 MB each. Reference audio requires an accompanying image or video reference.\n- Reference video and audio apply to reference-to-video only.\n- Prompts can be up to 7000 characters and may describe dialogue, sound effects, on-screen text, and camera work.\n\n**Billing**\n\n- Billed per second of the generated clip.\n- A reference video is billed for its own duration in addition to the generated clip, so a 5 second reference used to make a 6 second clip bills 11 seconds.\n- Reference audio is not billed.\n- The first 5 reference images are included. Each additional reference image is charged separately."},"notes":"Generates 4 to 15 second clips at 24 fps in 768p, each with a native stereo audio track.\n\n**Modes**\n\n- Text to video: prompt only.\n- Image to video: one image becomes the opening frame.\n- First and last frame: supply an opening and a closing image.\n- Reference to video: up to 9 images, 3 videos and 3 audio clips, 12 reference files in total.\n\n**Reference media**\n\n- Images 256 to 5760 px per side, aspect ratio between 0.4 and 2.5, up to 30 MB each.\n- Videos 2 to 15 seconds each and 15 seconds in total, H.264 or H.265, up to 50 MB each.\n- Audio 2 to 15 seconds, WAV or MP3, up to 15 MB each. Reference audio requires an accompanying image or video reference.\n- Reference video and audio apply to reference-to-video only.\n- Prompts can be up to 7000 characters and may describe dialogue, sound effects, on-screen text, and camera work.\n\n**Billing**\n\n- Billed per second of the generated clip.\n- A reference video is billed for its own duration in addition to the generated clip, so a 5 second reference used to make a 6 second clip bills 11 seconds.\n- Reference audio is not billed.\n- The first 5 reference images are included. Each additional reference image is charged separately.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=minimax-h3-highspeed","api_url":"https://docs.empiriolabs.ai/models/minimax-h3-highspeed","logo":"https://media.empiriolabs.ai/model-logos/minimax.png","status":"available"},{"id":"minimax-h3-lite","object":"model","created":1735689600,"owned_by":"minimax","display_name":"MiniMax H3 Lite","author":"minimax","provider":"minimax","description":"Lower-cost 4 to 15 second clips at 480p or 768p with native stereo audio, from text, a first and last frame, or image, video, and audio references.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image","audio"],"input_modalities":["text","image","video","audio"],"output_modalities":["video"],"features":["video_generation","image_to_video","audio_out","audio_in","multimodal"],"aliases":["minimax/minimax-h3-lite","minimax/h3-lite"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":null,"is_new":true,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description, up to 7000 characters. Can describe action, camera work, dialogue, sound effects, and on-screen text.","required":true,"metadata":{}},{"name":"mode","label":"Mode","type":"enum","description":"auto: detect from the inputs. t2v: text-to-video. i2v: animate one image as the opening frame. flf: transition from a first frame to a last frame. r2v: reference-to-video from images, videos, and audio.","required":false,"metadata":{},"default":"auto","options":["auto","t2v","i2v","flf","r2v"]},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution. 768p is billed at a higher per-second rate than 480p.","required":false,"metadata":{},"default":"768p","options":["480p","768p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio for text-to-video and reference-to-video. Image-to-video and first and last frame follow the input image. Adaptive uses 16:9 for text-to-video and reference-to-video.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"adaptive","options":["adaptive","21:9","16:9","4:3","1:1","3:4","9:16"]},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds, whole numbers only.","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":6,"min":4,"max":15},{"name":"image","label":"Image","type":"string","description":"Image URL. One opening frame for image-to-video, or up to 9 reference images for reference-to-video.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"last_frame","label":"Last Frame","type":"string","description":"Closing frame image URL. Supplying it selects first and last frame mode.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"video","label":"Video","type":"string","description":"Reference video URL, up to 3 clips of 2 to 15 seconds each and 15 seconds in total. Reference video is billed for its own duration in addition to the generated clip.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"audio","label":"Audio","type":"string","description":"Reference audio URL, up to 3 clips of 2 to 15 seconds each. Requires an accompanying reference image or video.","required":false,"metadata":{"ui":{"hide_in_playground":true}}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"480p","value":"$0.025"},{"spec":"per second","label":"768p","value":"$0.04"},{"spec":"per input image after the first 5","label":"Reference image input","value":"$0.02"}],"unit_pricing":[{"unit":"second","usd":"0.025","label":"480p"},{"unit":"second","usd":"0.04","label":"768p"}],"limits":{"note":"Generates 4 to 15 second clips at 24 fps in 480p or 768p, each with a native stereo audio track.\n\n**Modes**\n\n- Text to video: prompt only.\n- Image to video: one image becomes the opening frame.\n- First and last frame: supply an opening and a closing image.\n- Reference to video: up to 9 images, 3 videos and 3 audio clips, 12 reference files in total.\n\n**Aspect ratio**\n\nImage to video and first and last frame follow the input image. Text to video and reference to video use the ratio you choose, or 16:9 when it is left at adaptive.\n\n**Reference media**\n\n- Images 256 to 5760 px per side, aspect ratio between 0.4 and 2.5, up to 30 MB each.\n- Videos 2 to 15 seconds each and 15 seconds in total, H.264 or H.265, up to 50 MB each.\n- Audio 2 to 15 seconds, WAV or MP3, up to 15 MB each. Reference audio requires an accompanying image or video reference.\n- Reference video and audio apply to reference-to-video only.\n- Prompts can be up to 7000 characters and may describe dialogue, sound effects, on-screen text, and camera work.\n\n**Billing**\n\n- Billed per second of the generated clip at the resolution you request.\n- A reference video is billed for its own duration in addition to the generated clip, so a 5 second reference used to make a 6 second clip bills 11 seconds.\n- Reference audio is not billed.\n- The first 5 reference images are included. Each additional reference image is charged separately."},"notes":"Generates 4 to 15 second clips at 24 fps in 480p or 768p, each with a native stereo audio track.\n\n**Modes**\n\n- Text to video: prompt only.\n- Image to video: one image becomes the opening frame.\n- First and last frame: supply an opening and a closing image.\n- Reference to video: up to 9 images, 3 videos and 3 audio clips, 12 reference files in total.\n\n**Aspect ratio**\n\nImage to video and first and last frame follow the input image. Text to video and reference to video use the ratio you choose, or 16:9 when it is left at adaptive.\n\n**Reference media**\n\n- Images 256 to 5760 px per side, aspect ratio between 0.4 and 2.5, up to 30 MB each.\n- Videos 2 to 15 seconds each and 15 seconds in total, H.264 or H.265, up to 50 MB each.\n- Audio 2 to 15 seconds, WAV or MP3, up to 15 MB each. Reference audio requires an accompanying image or video reference.\n- Reference video and audio apply to reference-to-video only.\n- Prompts can be up to 7000 characters and may describe dialogue, sound effects, on-screen text, and camera work.\n\n**Billing**\n\n- Billed per second of the generated clip at the resolution you request.\n- A reference video is billed for its own duration in addition to the generated clip, so a 5 second reference used to make a 6 second clip bills 11 seconds.\n- Reference audio is not billed.\n- The first 5 reference images are included. Each additional reference image is charged separately.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=minimax-h3-lite","api_url":"https://docs.empiriolabs.ai/models/minimax-h3-lite","logo":"https://media.empiriolabs.ai/model-logos/minimax.png","status":"available"},{"id":"kling-4-0","object":"model","created":1792022400,"owned_by":"kling","display_name":"Kling 4.0","author":"kling","provider":"kling","description":"Makes 3 to 30 second clips at 720p or 1080p with native audio from text, first, middle and last frames, reference images and videos, or a video to edit.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image","video"],"output_modalities":["video"],"features":["video_generation","text_to_video","image_to_video","audio","editing"],"aliases":["kling-4.0","kling/kling-4-0"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-10-15","is_new":true,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description, up to 26,000 English or 11,000 non-English characters. Refer to images as @image_1, @image_2 and videos as @video_1 in the order they are supplied.","required":true,"metadata":{}},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution. 1080p is billed at a higher per-second rate than 720p.","required":false,"metadata":{},"default":"1080p","options":["720p","1080p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio for text-to-video and reference images. A first, middle or last frame, or a video to edit, sets the aspect ratio instead.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"16:9","options":["16:9","9:16","1:1","21:9"]},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds, whole numbers only. A video edit keeps the length of the video it edits.","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":5,"min":3,"max":30},{"name":"image","label":"Image","type":"string","description":"First frame image URL. The video starts on this image.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"image_end","label":"Last Frame","type":"string","description":"Last frame image URL. The video ends on this image.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"middle_images","label":"Middle Frames","type":"string","description":"Keyframe image URLs between the first and last frame, in order, as a list or comma-separated.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"reference_images","label":"Reference Images","type":"string","description":"Reference image URLs for characters, objects, scenes or style, as a list or comma-separated. Up to 10 images in total across all image inputs.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"video","label":"Video","type":"string","description":"Video URL to edit, 3 to 30 seconds. The result keeps its length and aspect ratio, and bills at the video input rate.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"reference_videos","label":"Reference Videos","type":"string","description":"Reference video URLs for motion, camera work or style, 3 to 30 seconds each, as a list or comma-separated. Up to 5 videos in total. Bills at the video input rate.","required":false,"metadata":{"ui":{"hide_in_playground":true}}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"Standard 720p","value":"$0.157"},{"spec":"per second","label":"Standard 1080p","value":"$0.235"},{"spec":"per second of input plus output, at least twice the output","label":"Video input 720p","value":"$0.094"},{"spec":"per second of input plus output, at least twice the output","label":"Video input 1080p","value":"$0.141"}],"unit_pricing":[{"unit":"second","usd":"0.157","label":"Standard 720p"},{"unit":"second","usd":"0.235","label":"Standard 1080p"}],"limits":{"note":"Generates 3 to 30 second clips at 24 fps in 720p or 1080p, each with a native stereo audio track.\n\n**Inputs**\n\n- Text to video: prompt only.\n- Keyframes: a first frame (`image`), middle frames (`middle_images`) and a last frame (`image_end`). The video follows the first frame's aspect ratio.\n- Reference images (`reference_images`): characters, objects, scenes or style to use.\n- Reference videos (`reference_videos`): motion, camera work or style to follow, 3 to 30 seconds each.\n- Video edit (`video`): a video to edit, 3 to 30 seconds. The result keeps its length and aspect ratio.\n- Up to 10 images and 5 videos per request. In the prompt, refer to images as @image_1, @image_2 (first frame, middle frames, last frame, then references) and to videos as @video_1, @video_2 (the video to edit first).\n\n**In the Playground**\n\nOne attached image is the first frame, two are the first and last frames, and three or more are references. The first attached video is the one edited; any others are references.\n\n**Media limits**\n\n- Images: JPG or PNG, at least 300 px, aspect ratio between 2:5 and 5:2, up to 30 MB.\n- Videos: MP4 or MOV, 3 to 30 seconds, 700 to 4553 px per side, up to 300 MB.\n\n**Billing**\n\n- Without a video input: billed per second of the generated clip at the resolution you request.\n- With a video input (a video to edit or a reference video): billed at the video input rate on twice the length of the generated clip, or on the input plus the output when the input is longer."},"notes":"Generates 3 to 30 second clips at 24 fps in 720p or 1080p, each with a native stereo audio track.\n\n**Inputs**\n\n- Text to video: prompt only.\n- Keyframes: a first frame (`image`), middle frames (`middle_images`) and a last frame (`image_end`). The video follows the first frame's aspect ratio.\n- Reference images (`reference_images`): characters, objects, scenes or style to use.\n- Reference videos (`reference_videos`): motion, camera work or style to follow, 3 to 30 seconds each.\n- Video edit (`video`): a video to edit, 3 to 30 seconds. The result keeps its length and aspect ratio.\n- Up to 10 images and 5 videos per request. In the prompt, refer to images as @image_1, @image_2 (first frame, middle frames, last frame, then references) and to videos as @video_1, @video_2 (the video to edit first).\n\n**In the Playground**\n\nOne attached image is the first frame, two are the first and last frames, and three or more are references. The first attached video is the one edited; any others are references.\n\n**Media limits**\n\n- Images: JPG or PNG, at least 300 px, aspect ratio between 2:5 and 5:2, up to 30 MB.\n- Videos: MP4 or MOV, 3 to 30 seconds, 700 to 4553 px per side, up to 300 MB.\n\n**Billing**\n\n- Without a video input: billed per second of the generated clip at the resolution you request.\n- With a video input (a video to edit or a reference video): billed at the video input rate on twice the length of the generated clip, or on the input plus the output when the input is longer.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=kling-4-0","api_url":"https://docs.empiriolabs.ai/models/kling-4-0","logo":"https://media.empiriolabs.ai/model-logos/kling-4-0.png","status":"available"},{"id":"kling-4-0-flash","object":"model","created":1793750400,"owned_by":"kling","display_name":"Kling 4.0 Flash","author":"kling","provider":"kling","description":"The faster, lower-cost Kling 4.0: 3 to 20 second clips at 720p with native audio from text, a first frame, reference images and videos, or a video to edit.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image","video"],"output_modalities":["video"],"features":["video_generation","text_to_video","image_to_video","audio","editing"],"aliases":["kling-4.0-flash","kling/kling-4-0-flash"],"structured_output":null,"native_inference":false,"weight_precision":null,"hugging_face_id":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-11-04","is_new":true,"is_featured":true,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"web_search":false,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"prompt","label":"Prompt","type":"string","description":"Scene description, up to 26,000 English or 11,000 non-English characters. Refer to reference images as @image_1, @image_2 and videos as @video_1 in the order they are supplied.","required":true,"metadata":{}},{"name":"resolution","label":"Resolution","type":"enum","description":"Output resolution.","required":false,"metadata":{},"default":"720p","options":["720p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio for text-to-video and references. A first frame on its own, or a video to edit, sets the aspect ratio instead.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"16:9","options":["16:9","9:16","1:1","4:3","3:4","21:9"]},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds, whole numbers only. A video edit keeps the length of the video it edits.","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":5,"min":3,"max":20},{"name":"image","label":"Image","type":"string","description":"First frame image URL. The video starts on this image.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"reference_images","label":"Reference Images","type":"string","description":"Reference image URLs for characters, objects, scenes or style, as a list or comma-separated. Up to 10 images in total.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"video","label":"Video","type":"string","description":"Video URL to edit, 3 to 20 seconds. The result keeps its length, and bills at the video input rate.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"reference_videos","label":"Reference Videos","type":"string","description":"Reference video URLs for motion, camera work or style, 3 to 20 seconds each and 20 seconds of video in total, as a list or comma-separated. Up to 5 videos in total. Bills at the video input rate.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"keep_original_sound","label":"Keep Original Sound","type":"boolean","description":"Video edit, and reference with a video, only. Keep the audio of the source video instead of generating new audio.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"-1","completion":"-1","image":"0","request":"0","input_cache_read":"-1"},"pricing_rows":[{"spec":"per second","label":"Standard 720p","value":"$0.094"},{"spec":"per second of input plus output, at least twice the output","label":"Video input 720p","value":"$0.063"}],"unit_pricing":[{"unit":"second","usd":"0.094","label":"Standard 720p"}],"limits":{"note":"Generates 3 to 20 second clips at 24 fps in 720p, each with a native stereo audio track.\n\n**Inputs**\n\n- Text to video: prompt only.\n- First frame (`image`): the video starts on this image and follows its aspect ratio.\n- Reference images (`reference_images`): characters, objects, scenes or style to use. A first frame can be sent with them.\n- Reference videos (`reference_videos`): motion, camera work or style to follow, 3 to 20 seconds each.\n- Video edit (`video`): a video to edit, 3 to 20 seconds. The result keeps its length.\n- Original sound (`keep_original_sound`): keeps the audio of the video being edited, or of the first reference video, instead of a new audio track.\n- Up to 10 images and 5 videos per request, with at most 20 seconds of video in total. In the prompt, refer to reference images as @image_1, @image_2 and to videos as @video_1, @video_2 (the video to edit first).\n- Last and middle frames and 1080p are available on Kling 4.0.\n\n**In the Playground**\n\nOne attached image is the first frame, and two or more are references. The first attached video is the one edited; any others are references.\n\n**Media limits**\n\n- Images: JPG or PNG, at least 300 px, aspect ratio between 2:5 and 5:2, up to 30 MB.\n- Videos: MP4 or MOV, 3 to 20 seconds, 700 to 4553 px per side, 24 to 60 fps, up to 300 MB.\n\n**Billing**\n\n- Without a video input: billed per second of the generated clip.\n- With a video input (a video to edit or a reference video): billed at the video input rate on twice the length of the generated clip, or on the input plus the output when the input is longer."},"notes":"Generates 3 to 20 second clips at 24 fps in 720p, each with a native stereo audio track.\n\n**Inputs**\n\n- Text to video: prompt only.\n- First frame (`image`): the video starts on this image and follows its aspect ratio.\n- Reference images (`reference_images`): characters, objects, scenes or style to use. A first frame can be sent with them.\n- Reference videos (`reference_videos`): motion, camera work or style to follow, 3 to 20 seconds each.\n- Video edit (`video`): a video to edit, 3 to 20 seconds. The result keeps its length.\n- Original sound (`keep_original_sound`): keeps the audio of the video being edited, or of the first reference video, instead of a new audio track.\n- Up to 10 images and 5 videos per request, with at most 20 seconds of video in total. In the prompt, refer to reference images as @image_1, @image_2 and to videos as @video_1, @video_2 (the video to edit first).\n- Last and middle frames and 1080p are available on Kling 4.0.\n\n**In the Playground**\n\nOne attached image is the first frame, and two or more are references. The first attached video is the one edited; any others are references.\n\n**Media limits**\n\n- Images: JPG or PNG, at least 300 px, aspect ratio between 2:5 and 5:2, up to 30 MB.\n- Videos: MP4 or MOV, 3 to 20 seconds, 700 to 4553 px per side, 24 to 60 fps, up to 300 MB.\n\n**Billing**\n\n- Without a video input: billed per second of the generated clip.\n- With a video input (a video to edit or a reference video): billed at the video input rate on twice the length of the generated clip, or on the input plus the output when the input is longer.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=kling-4-0-flash","api_url":"https://docs.empiriolabs.ai/models/kling-4-0-flash","logo":"https://media.empiriolabs.ai/model-logos/kling-4-0-flash.png","status":"available"}],"authors":[{"logo":"https://media.empiriolabs.ai/provider-logos/alibaba.png","name":"Alibaba Cloud","slug":"alibaba"},{"logo":"https://media.empiriolabs.ai/provider-logos/bytedance.png","name":"ByteDance","slug":"bytedance","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/bytedance.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/tencent.png","name":"Tencent","slug":"tencent"},{"logo":"https://media.empiriolabs.ai/provider-logos/xiaomi.png","name":"Xiaomi","slug":"xiaomi"},{"logo":"https://media.empiriolabs.ai/provider-logos/google.png","name":"Google","slug":"google","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/google.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/amazon.png","name":"Amazon","slug":"amazon","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/amazon.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/openai.png","name":"OpenAI","slug":"openai"},{"logo":"https://media.empiriolabs.ai/provider-logos/deepseek.png","name":"DeepSeek","slug":"deepseek","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/deepseek.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/mistral.png","name":"Mistral AI","slug":"mistral","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/mistral.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/stability.png","name":"Stability AI","slug":"stability","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/stability.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/perplexity.png","name":"Perplexity","slug":"perplexity","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/perplexity.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/tavily.png","name":"Tavily","slug":"tavily"},{"logo":"https://media.empiriolabs.ai/provider-logos/exa.png","name":"Exa","slug":"exa","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/exa.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/linkup.png","name":"Linkup","slug":"linkup"},{"logo":"https://media.empiriolabs.ai/provider-logos/kling.png","name":"Kling AI","slug":"kling","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/kling.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/pixverse.png","name":"PixVerse","slug":"pixverse"},{"logo":"https://media.empiriolabs.ai/provider-logos/manus.png","name":"Manus","slug":"manus"},{"logo":"https://media.empiriolabs.ai/provider-logos/deepgram.png","name":"Deepgram","slug":"deepgram"},{"logo":"https://media.empiriolabs.ai/provider-logos/gptzero.png","name":"GPTZero","slug":"gptzero"},{"logo":"https://media.empiriolabs.ai/provider-logos/openmoss.png","name":"OpenMOSS","slug":"openmoss"},{"logo":"https://media.empiriolabs.ai/provider-logos/soul-ai-lab.png","name":"Soul AI Lab","slug":"soul-ai-lab"},{"logo":"https://media.empiriolabs.ai/provider-logos/zhipu.png","name":"Z.ai","slug":"zhipu"},{"logo":"https://media.empiriolabs.ai/provider-logos/minimax.png","name":"MiniMax","slug":"minimax","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/minimax.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/vita-epfl.png","name":"VITA-Group / EPFL","slug":"vita-epfl"},{"logo":"https://media.empiriolabs.ai/provider-logos/winfunc.png","name":"WinFunc","slug":"winfunc"},{"logo":"https://media.empiriolabs.ai/provider-logos/black-forest-labs.png","name":"Black Forest Labs","slug":"black-forest-labs","logo_mono":"https://media.empiriolabs.ai/provider-logos-mono/black-forest-labs.png","logo_color":"https://media.empiriolabs.ai/provider-logos/black-forest-labs.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/ace-step.png","name":"ACE-Step","slug":"ace-step","logo_docs":"https://media.empiriolabs.ai/provider-logos/ace-step-docs.png","logo_mono":"https://media.empiriolabs.ai/provider-logos-mono/ace-step.png","logo_color":"https://media.empiriolabs.ai/provider-logos/ace-step.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/microsoft.png","name":"Microsoft","slug":"microsoft"},{"logo":"https://media.empiriolabs.ai/provider-logos/inworld.png","name":"Inworld","slug":"inworld","logo_docs":"https://media.empiriolabs.ai/provider-logos/inworld-docs.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/moonshot.png","name":"Moonshot AI","slug":"moonshot","logo_mono":"https://media.empiriolabs.ai/provider-logos-mono/moonshot.png","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/moonshot.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/xai.png","name":"xAI","slug":"xai","logo_docs":"https://media.empiriolabs.ai/provider-logos/xai-docs.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/sakana.png","name":"Sakana AI","slug":"sakana","logo_docs":"https://media.empiriolabs.ai/provider-logos/sakana-docs.png","logo_mono":"https://media.empiriolabs.ai/provider-logos-mono/sakana.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/stepfun.png","name":"StepFun","slug":"stepfun","logo_mono":"https://media.empiriolabs.ai/provider-logos-mono/stepfun.png","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/stepfun.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/meta.png","name":"Meta AI","slug":"meta","logo_docs":"https://media.empiriolabs.ai/provider-logos/meta-docs.png","logo_mono":"https://media.empiriolabs.ai/provider-logos-mono/meta.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/deemos.png","name":"Deemos","slug":"deemos","logo_mono":"https://media.empiriolabs.ai/provider-logos-mono/deemos.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/hitem3d.png","name":"Hitem3D","slug":"hitem3d","logo_mono":"https://media.empiriolabs.ai/provider-logos-mono/hitem3d.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/sonilo.png","name":"Sonilo","slug":"sonilo","logo_docs":"https://media.empiriolabs.ai/provider-logos/sonilo-docs.png","logo_mono":"https://media.empiriolabs.ai/provider-logos-mono/sonilo.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/empiriolabs.png","name":"EmpirioLabs","slug":"empiriolabs"},{"logo":"https://media.empiriolabs.ai/provider-logos/lighton.png","name":"LightOn","slug":"lighton"}],"providers":[{"logo":"https://media.empiriolabs.ai/provider-logos/alibaba.png","name":"Alibaba Cloud","slug":"alibaba"},{"logo":"https://media.empiriolabs.ai/provider-logos/bytedance.png","name":"ByteDance","slug":"bytedance","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/bytedance.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/tencent.png","name":"Tencent","slug":"tencent"},{"logo":"https://media.empiriolabs.ai/provider-logos/xiaomi.png","name":"Xiaomi","slug":"xiaomi"},{"logo":"https://media.empiriolabs.ai/provider-logos/google.png","name":"Google","slug":"google","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/google.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/amazon.png","name":"Amazon","slug":"amazon","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/amazon.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/openai.png","name":"OpenAI","slug":"openai"},{"logo":"https://media.empiriolabs.ai/provider-logos/deepseek.png","name":"DeepSeek","slug":"deepseek","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/deepseek.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/mistral.png","name":"Mistral AI","slug":"mistral","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/mistral.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/stability.png","name":"Stability AI","slug":"stability","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/stability.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/perplexity.png","name":"Perplexity","slug":"perplexity","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/perplexity.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/tavily.png","name":"Tavily","slug":"tavily"},{"logo":"https://media.empiriolabs.ai/provider-logos/exa.png","name":"Exa","slug":"exa","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/exa.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/linkup.png","name":"Linkup","slug":"linkup"},{"logo":"https://media.empiriolabs.ai/provider-logos/kling.png","name":"Kling AI","slug":"kling","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/kling.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/pixverse.png","name":"PixVerse","slug":"pixverse"},{"logo":"https://media.empiriolabs.ai/provider-logos/manus.png","name":"Manus","slug":"manus"},{"logo":"https://media.empiriolabs.ai/provider-logos/deepgram.png","name":"Deepgram","slug":"deepgram"},{"logo":"https://media.empiriolabs.ai/provider-logos/gptzero.png","name":"GPTZero","slug":"gptzero"},{"logo":"https://media.empiriolabs.ai/provider-logos/openmoss.png","name":"OpenMOSS","slug":"openmoss"},{"logo":"https://media.empiriolabs.ai/provider-logos/soul-ai-lab.png","name":"Soul AI Lab","slug":"soul-ai-lab"},{"logo":"https://media.empiriolabs.ai/provider-logos/zhipu.png","name":"Z.ai","slug":"zhipu"},{"logo":"https://media.empiriolabs.ai/provider-logos/minimax.png","name":"MiniMax","slug":"minimax","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/minimax.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/vita-epfl.png","name":"VITA-Group / EPFL","slug":"vita-epfl"},{"logo":"https://media.empiriolabs.ai/provider-logos/winfunc.png","name":"WinFunc","slug":"winfunc"},{"logo":"https://media.empiriolabs.ai/provider-logos/black-forest-labs.png","name":"Black Forest Labs","slug":"black-forest-labs","logo_mono":"https://media.empiriolabs.ai/provider-logos-mono/black-forest-labs.png","logo_color":"https://media.empiriolabs.ai/provider-logos/black-forest-labs.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/ace-step.png","name":"ACE-Step","slug":"ace-step","logo_docs":"https://media.empiriolabs.ai/provider-logos/ace-step-docs.png","logo_mono":"https://media.empiriolabs.ai/provider-logos-mono/ace-step.png","logo_color":"https://media.empiriolabs.ai/provider-logos/ace-step.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/microsoft.png","name":"Microsoft","slug":"microsoft"},{"logo":"https://media.empiriolabs.ai/provider-logos/inworld.png","name":"Inworld","slug":"inworld","logo_docs":"https://media.empiriolabs.ai/provider-logos/inworld-docs.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/moonshot.png","name":"Moonshot AI","slug":"moonshot","logo_mono":"https://media.empiriolabs.ai/provider-logos-mono/moonshot.png","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/moonshot.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/xai.png","name":"xAI","slug":"xai","logo_docs":"https://media.empiriolabs.ai/provider-logos/xai-docs.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/sakana.png","name":"Sakana AI","slug":"sakana","logo_docs":"https://media.empiriolabs.ai/provider-logos/sakana-docs.png","logo_mono":"https://media.empiriolabs.ai/provider-logos-mono/sakana.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/stepfun.png","name":"StepFun","slug":"stepfun","logo_mono":"https://media.empiriolabs.ai/provider-logos-mono/stepfun.png","logo_color":"https://media.empiriolabs.ai/assets/provider-logos-color/stepfun.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/meta.png","name":"Meta AI","slug":"meta","logo_docs":"https://media.empiriolabs.ai/provider-logos/meta-docs.png","logo_mono":"https://media.empiriolabs.ai/provider-logos-mono/meta.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/deemos.png","name":"Deemos","slug":"deemos","logo_mono":"https://media.empiriolabs.ai/provider-logos-mono/deemos.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/hitem3d.png","name":"Hitem3D","slug":"hitem3d","logo_mono":"https://media.empiriolabs.ai/provider-logos-mono/hitem3d.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/sonilo.png","name":"Sonilo","slug":"sonilo","logo_docs":"https://media.empiriolabs.ai/provider-logos/sonilo-docs.png","logo_mono":"https://media.empiriolabs.ai/provider-logos-mono/sonilo.png"},{"logo":"https://media.empiriolabs.ai/provider-logos/empiriolabs.png","name":"EmpirioLabs","slug":"empiriolabs"},{"logo":"https://media.empiriolabs.ai/provider-logos/lighton.png","name":"LightOn","slug":"lighton"}],"categories":[{"name":"Text Generation","slug":"text","order":1},{"name":"Image Generation","slug":"image","order":2},{"name":"Video Generation","slug":"video","order":3},{"name":"Audio Generation","slug":"audio","order":4},{"name":"Transcription","slug":"transcription","order":5},{"name":"Research & Search","slug":"research","order":6},{"name":"3D Generation","slug":"3d","order":7},{"name":"Embeddings","slug":"embedding","order":8},{"name":"Rerankers","slug":"reranker","order":9},{"name":"Tools & Agents","slug":"tools","order":10},{"name":"Decision Models","slug":"decision","order":11},{"name":"Document OCR","slug":"ocr","order":12}],"catalog_version":"2.10.66","catalog_updated_at":"2026-11-21"}