{"object":"list","data":[{"id":"kling-3-0-turbo","object":"model","display_name":"Kling 3.0 Turbo","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"],"structured_output":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":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":"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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per second","label":"720p","value":"$0.18"},{"spec":"per second","label":"1080p","value":"$0.225"}],"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 as `shot 1, <seconds>, <description>; shot 2, <seconds>, <description>;` (shot durations must sum to the total duration).\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 as `shot 1, <seconds>, <description>; shot 2, <seconds>, <description>;` (shot durations must sum to the total duration).\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-5-2","object":"model","display_name":"GLM 5.2","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":131072,"model_released_at":"2026-06-16","is_new":true,"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":"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","show_when":{"tool_web_search":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","show_when":{"tool_web_search":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","show_when":{"tool_web_search":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","show_when":{"tool_web_search":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"},"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"}],"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-k2-7-code","object":"model","display_name":"Kimi K2.7 Code","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"],"structured_output":"json_schema","batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"max_output_tokens":131072,"model_released_at":"2026-06-16","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":"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":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":"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":"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"},"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"}],"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":"fugu-ultra","object":"model","display_name":"Fugu Ultra","provider":"sakana","description":"Multi-agent conductor that orchestrates frontier expert models for hard reasoning, coding, and research, 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","cache"],"structured_output":"json_object","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":true,"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. The conductor needs room to work, so very small values can return empty output.","required":false,"metadata":{"ui":{"control":"slider","section":"Generation"}},"default":32768,"min":1,"max":131072},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"How hard Fugu Ultra reasons. Reasoning is always on. The default is high; xhigh and max are aliases of the same maximum effort (more thorough and slower than high).","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: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":"0.0000015","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"}],"limits":{"note":"Fugu Ultra is a 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- Leave generous max_tokens 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 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**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","api_url":"https://docs.empiriolabs.ai/models/fugu-ultra","logo":"https://media.empiriolabs.ai/model-logos/fugu.png","status":"available"},{"id":"qwen3-7-plus","object":"model","display_name":"Qwen3.7 Plus","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":65536,"model_released_at":"2026-06-01","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 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":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":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":"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},"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":256000},{"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":"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.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.03}},"default":true},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":true},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":true},{"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.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.03}},"default":true},{"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.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.03}},"default":true},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return raw provider-style output without EmpirioLabs source formatting where supported.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"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":{"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/qwen3-7-plus:generateContent"],"pricing":[{"prompt":"0.0000004","completion":"0.0000016","image":"0","request":"0","input_cache_read":"0"},{"prompt":"0.0000012","completion":"0.0000048","image":"0","request":"0","input_cache_read":"0","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 request when enabled","label":"Web search","value":"$0.03"},{"spec":"per call","label":"Image Search","value":"$0.03"}],"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","display_name":"Qwen3.7 Plus","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":65536,"model_released_at":"2026-06-01","is_new":true,"is_featured":true,"discount":{"label":"Save up to 64%","percent":64},"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 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":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":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":"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},"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":256000},{"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":"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.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.01}},"default":true},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":true},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":true},{"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.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.01}},"default":true},{"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.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.01}},"default":true},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return raw provider-style output without EmpirioLabs source formatting where supported.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"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":{"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/qwen3-7-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":"0.000000056","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 request when enabled","label":"Web search","value":"$0.01"},{"spec":"per call","label":"Image Search","value":"$0.01"}],"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","display_name":"Kimi K2.7 Code Highspeed","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"],"structured_output":"json_schema","batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"max_output_tokens":131072,"model_released_at":"2026-06-16","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":"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":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":"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":"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"},"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"}],"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":"minimax-m3","object":"model","display_name":"MiniMax M3","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":524288,"model_released_at":"2026-06-01","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":"temperature","label":"Temperature","type":"number","description":"Controls randomness. Lower values are more deterministic; higher values are more exploratory.","required":false,"metadata":{"step":0.01,"control":"slider"},"default":1,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Controls nucleus sampling by limiting generation to the most likely token mass.","required":false,"metadata":{"step":0.01,"control":"slider"},"default":0.95,"min":0,"max":1},{"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":"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":"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":{"ui":{"control":"toggle","section":"Tools"},"aliases":["web_search","linkup_web_search","tool_web_search_linkup"],"billing":{"source":"linkup_injector","price_per_search":0.013,"price_per_request":0.013},"powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"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":"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/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":"0.000000045","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 (Linkup)","value":"$0.013"}],"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. Linkup web search is available through web_search_linkup and adds $0.013 per successful search."},"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":"qwen3-7-max","object":"model","display_name":"Qwen3.7 Max","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":65536,"model_released_at":"2026-05-21","is_new":true,"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 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":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":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":"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},"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":"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 web search call.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02}},"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 web extractor call.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02},"visible_when":{"op":"eq","field":"tool_web_search","value":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 code interpreter call.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.02}},"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"}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return raw provider-style output without EmpirioLabs source formatting where supported.","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/qwen3-7-max:generateContent"],"pricing":{"prompt":"0.0000025","completion":"0.0000075","image":"0","request":"0","input_cache_read":"0"},"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"}],"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","display_name":"Qwen3.7 Max","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"],"structured_output":"json_object","batch_supported":"batch","batch_discount_pct":35,"context_window":1000000,"context_length":1000000,"max_output_tokens":65536,"model_released_at":"2026-05-21","is_new":true,"is_featured":true,"discount":"Save up to 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 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":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":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":"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},"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":"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 web search call.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.01}},"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 web extractor call.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.01},"visible_when":{"op":"eq","field":"tool_web_search","value":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 code interpreter call.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_call":0.01}},"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"}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Return raw provider-style output without EmpirioLabs source formatting where supported.","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/qwen3-7-max:variant1:generateContent"],"pricing":{"prompt":"0.00000165","completion":"0.000004951","image":"0","request":"0","input_cache_read":"0"},"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"}],"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":"ace-step-1-5-xl","object":"model","display_name":"ACE-Step 1.5 XL","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"],"structured_output":null,"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 33%","percent":33},"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. The model is most reliable up to ~4 minutes; longer durations risk OOM/quality drops during diffusion.","required":false,"metadata":{"ui":{"step":1,"control":"slider"},"aliases":["duration"]},"default":30,"min":10,"max":240},{"name":"num_inference_steps","label":"num_inference_steps","type":"number","description":"Number of diffusion steps. 8 is the recommended sweet spot for the Turbo variant; raise for more polish, lower for cheaper draft generations.","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":"negative_prompt","label":"negative_prompt","type":"string","description":"Negative prompt — anti-tags, anti-styles, instruments to exclude. Same comma-separated style as prompt.","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 container format for the response. FLAC = lossless, WAV = uncompressed, MP3 = small file size.","required":false,"metadata":{"aliases":["output_format"]},"default":"flac","options":["flac","wav","ogg","mp3"]},{"name":"response_format","label":"response_format","type":"enum","description":"How the worker returns the audio. 'url' returns a signed URL to the rendered file; 'base64' inlines the bytes in the response.","required":false,"metadata":{},"default":"url","options":["url","b64_json"]},{"name":"return_base64","label":"return_base64","type":"boolean","description":"When true, the response includes the rendered audio as base64 in addition to (or instead of, depending on response_format) the URL.","required":false,"metadata":{"aliases":["b64_json"]},"default":false}],"supported_endpoints":["POST /v1/audio/generations"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per generated second","label":"Music generation","value":"$0.00025 (was $0.0003)"}],"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, optional negative prompt when supported by the pinned pipeline, 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","display_name":"FLUX.2 Klein 4B","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"],"structured_output":null,"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 79%","percent":79},"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":"negative_prompt","label":"Negative Prompt","type":"string","description":"Text description of what to avoid in the image.","required":false,"metadata":{}},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio (1:1, 16:9, 9:16, 4:3, 3:2, etc.).","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)"}],"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. `negative_prompt` is accepted for compatibility but ignored by the distilled Klein pipeline.\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":"minimax-m2-7-highspeed","object":"model","display_name":"MiniMax M2.7 Highspeed","provider":"minimax","description":"High-speed M2.7 variant tuned for fast inference with strong general-purpose performance with strong agentic capabilities.","modality":null,"type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":200000,"context_length":200000,"max_output_tokens":32768,"model_released_at":"2026-03-18","is_new":false,"is_featured":true,"discount":{"label":"Save up to 50%","percent":50},"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":1,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.95,"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":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":"tools","label":"Tools","type":"string","description":"OpenAI-style function-calling tool definitions. Each entry has name, description, parameters.","required":false,"metadata":{}},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"auto | none | required | {type:function, function:{name:\"...\"}}. Controls when the model must call a tool.","required":false,"metadata":{}},{"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/minimax-m2-7-highspeed:generateContent"],"pricing":{"prompt":"0.0000003","completion":"0.0000012","image":"0","request":"0","input_cache_read":"0.00000003"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.30 (was $0.60)"},{"spec":"per 1M generated tokens","label":"Output","value":"$1.20 (was $2.40)"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.03 (was $0.06)"},{"spec":"per request when enabled","label":"Web search","value":"$0.013"}],"limits":{"note":"Same frontier performance as M2.7 with ~100 tokens/sec output. Interleaved thinking is always on (no toggle)."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=minimax-m2-7-highspeed","api_url":"https://docs.empiriolabs.ai/models/minimax-m2-7-highspeed","logo":"https://media.empiriolabs.ai/model-logos/minimax.png","status":"available"},{"id":"tts-2","object":"model","display_name":"TTS 2","provider":"inworld","description":"Realtime voice model with plain-English voice direction, one voice identity across 100+ languages, and sub-200ms streaming time-to-first-audio.","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"],"structured_output":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":true,"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.","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 (including cloned voices), 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 cloned and 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 100+ languages; 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"]},{"name":"output_format","label":"Output format","type":"enum","description":"Audio container/codec. WAV = LINEAR16 inside RIFF (ubiquitous). MP3 / OGG = compressed. PCM = headerless raw, useful for chunked real-time playback. 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 Inworld's default and what their voice models train at; raise to 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, Inworld expands numbers / abbreviations / dates into spoken form (\"USD 5\" → \"five US dollars\").","required":false,"metadata":{},"default":"ON","options":["ON","OFF"]},{"name":"timestamp_type","label":"Timestamps","type":"enum","description":"If non-NONE, the response includes per-word or per-character timestamps in timestamp_info. Useful for caption / highlight UIs.","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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 1M characters","label":"Synthesis","value":"$22.00 (was $25.00)"}],"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 200 ms (Inworld benchmark)\n\n**Voices**\n\n- One voice identity held across 100+ languages\n- Curated presets in the dropdown; pass any other voice ID via `voice_id`\n- Plain-English voice direction to steer tone and delivery"},"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","display_name":"TTS 1.5 Mini","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"],"structured_output":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 + various accents. For the full 271-voice catalog (including cloned voices), 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 voices outside the curated 20-preset list. Inworld TTS 1.5 ships 271+ named voices across 15 languages (regional accents, gendered variants). Example: Maitê, Olivia, or any voice name from GET /v1/voices.","required":false,"metadata":{}},{"name":"language","label":"Language","type":"enum","description":"BCP-47 language code. Inworld TTS 1.5 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 = headerless raw, useful for chunked real-time playback. 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 Inworld's default and what their voice models train at; raise to 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, Inworld expands numbers / abbreviations / dates into spoken form (\"USD 5\" → \"five US dollars\").","required":false,"metadata":{},"default":"ON","options":["ON","OFF"]},{"name":"timestamp_type","label":"Timestamps","type":"enum","description":"If non-NONE, the response includes per-word or per-character timestamps in timestamp_info. Useful for caption / highlight UIs.","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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 1M characters","label":"Synthesis","value":"$17.50 (was $25.00)"}],"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","display_name":"TTS 1.5 Max","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"],"structured_output":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 + various accents. For the full 271-voice catalog (including cloned voices), 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 voices outside the curated 20-preset list. Inworld TTS 1.5 ships 271+ named voices across 15 languages (regional accents, gendered variants). Example: Maitê, Olivia, or any voice name from GET /v1/voices.","required":false,"metadata":{}},{"name":"language","label":"Language","type":"enum","description":"BCP-47 language code. Inworld TTS 1.5 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 = headerless raw, useful for chunked real-time playback. 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 Inworld's default and what their voice models train at; raise to 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, Inworld expands numbers / abbreviations / dates into spoken form (\"USD 5\" → \"five US dollars\").","required":false,"metadata":{},"default":"ON","options":["ON","OFF"]},{"name":"timestamp_type","label":"Timestamps","type":"enum","description":"If non-NONE, the response includes per-word or per-character timestamps in timestamp_info. Useful for caption / highlight UIs.","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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 1M characters","label":"Synthesis","value":"$29.75 (was $35.00)"}],"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","display_name":"GLM 5.1","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"],"structured_output":"json_schema","batch_supported":null,"batch_discount_pct":null,"context_window":202000,"context_length":202000,"max_output_tokens":null,"model_released_at":"2026-04-07","is_new":true,"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 number of output tokens to generate.","required":false,"metadata":{"ui":{"control":"slider","section":"Generation"}},"default":4096,"min":1,"max":128000},{"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":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,"max":2},{"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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","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. Disable this for strict structured output.","required":false,"metadata":{"ui":{"control":"toggle","section":"Reasoning"}},"default":true},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens available for reasoning content 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 supported.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"}},"default":true},{"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":"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":"Structured Output","hide_in_playground":true},"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","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":"0.000000165","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 request when enabled","label":"Web search","value":"$0.013"}],"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","display_name":"Kimi K2.6","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"],"structured_output":"json_schema","batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"max_output_tokens":16000,"model_released_at":"2026-04-20","is_new":true,"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, 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 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":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.","required":false,"metadata":{},"default":true},{"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":"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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","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 request when enabled","label":"Web search","value":"$0.013"}],"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-flash:variant2","object":"model","display_name":"DeepSeek V4 Flash (Variant 2)","provider":"deepseek","description":"DeepSeek V4 Flash is a lightweight MoE reasoning model with 1M context, high throughput, 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"],"structured_output":"json_schema","batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":384000,"model_released_at":"2026-04-24","is_new":true,"is_featured":true,"discount":{"label":"Save up to 2%","percent":2},"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.","required":false,"metadata":{},"default":4096,"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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","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 the reasoning process. Up to 393216.","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-flash:variant2:generateContent"],"pricing":{"prompt":"0.000000138","completion":"0.000000275","image":"0","request":"0","input_cache_read":"0.000000028"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.138 (was $0.14)"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.275 (was $0.28)"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.028"},{"spec":"per request when enabled","label":"Web search","value":"$0.01"}],"limits":null,"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=deepseek-v4-flash:variant2","api_url":"https://docs.empiriolabs.ai/models/deepseek-v4-flash#variant2","logo":"https://media.empiriolabs.ai/model-logos/deepseek.png","status":"available"},{"id":"deepseek-v4-pro:variant2","object":"model","display_name":"DeepSeek V4 Pro (Variant 2)","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"],"structured_output":"json_schema","batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":384000,"model_released_at":"2026-04-24","is_new":true,"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.","required":false,"metadata":{},"default":4096,"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":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for the reasoning process. Up to 393216.","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":"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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"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"}],"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":"minimax-m2-7","object":"model","display_name":"MiniMax M2.7","provider":"minimax","description":"MiniMax M2.7 is a general-purpose reasoning chat model with interleaved thinking, function calling, and prompt caching.","modality":null,"type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","function_calling","cache"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":200000,"context_length":200000,"max_output_tokens":32768,"model_released_at":"2026-03-18","is_new":true,"is_featured":true,"discount":{"label":"Save up to 50%","percent":50},"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":1,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Lower = more focused.","required":false,"metadata":{},"default":0.95,"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":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":"tools","label":"Tools","type":"string","description":"OpenAI-style function-calling tool definitions. Each entry has name, description, parameters.","required":false,"metadata":{}},{"name":"tool_choice","label":"Tool Choice","type":"string","description":"auto | none | required | {type:function, function:{name:\"...\"}}. Controls when the model must call a tool.","required":false,"metadata":{}},{"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/minimax-m2-7:generateContent"],"pricing":{"prompt":"0.00000015","completion":"0.0000006","image":"0","request":"0","input_cache_read":"0.00000003"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.15 (was $0.30)"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.60 (was $1.20)"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.03 (was $0.06)"},{"spec":"per request when enabled","label":"Web search","value":"$0.013"}],"limits":{"note":"Supports interleaved thinking, function calling, and implicit prompt cache reads. Thinking is always on and billed as output tokens."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=minimax-m2-7","api_url":"https://docs.empiriolabs.ai/models/minimax-m2-7","logo":"https://media.empiriolabs.ai/model-logos/minimax.png","status":"available"},{"id":"trellis-2-4b","object":"model","display_name":"TRELLIS.2 4B","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"],"structured_output":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":true,"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":"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.","required":false,"metadata":{"ui":{"control":"segmented","section":"Generation"}},"default":"1024","options":["512","1024","1536"]},{"name":"pipeline_type","label":"Pipeline Type","type":"enum","description":"Explicit TRELLIS pipeline. Leave on 1024 cascade unless you need the 512 or 1536 path.","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 signed media URLs by default, or inline base64 JSON when requested.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Output"}},"default":"url","options":["url","b64_json"]},{"name":"verbose","label":"Verbose Export","type":"boolean","description":"Enable verbose mesh export logging.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"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"}],"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","display_name":"Qwen3.5 122B-A10B","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"max_output_tokens":64000,"model_released_at":"2026-02-24","is_new":true,"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 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":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","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":"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":"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"},{"prompt":"0.000000287","completion":"0.000002294","image":"0","request":"0","input_cache_read":"0","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"}],"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","display_name":"Qwen3.5 397B-A17B","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"max_output_tokens":64000,"model_released_at":"2026-02-16","is_new":true,"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 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":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","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":"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":"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"},{"prompt":"0.00000043","completion":"0.00000258","image":"0","request":"0","input_cache_read":"0","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"}],"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","display_name":"Qwen3.5 35B-A3B","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"max_output_tokens":64000,"model_released_at":"2026-02-24","is_new":true,"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 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":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","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":"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":"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"},{"prompt":"0.000000229","completion":"0.000001835","image":"0","request":"0","input_cache_read":"0","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"}],"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","display_name":"Qwen3.5 27B","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"max_output_tokens":64000,"model_released_at":"2026-02-24","is_new":true,"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 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":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","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":"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":"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"},{"prompt":"0.000000258","completion":"0.000002064","image":"0","request":"0","input_cache_read":"0","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"}],"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":"qwen3-6-27b","object":"model","display_name":"Qwen3.6 27B","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"max_output_tokens":64000,"model_released_at":"2026-04-22","is_new":true,"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 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":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","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":"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":"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"},"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"}],"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","display_name":"Qwen3.6 Flash","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":65536,"model_released_at":"2026-04-16","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 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":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":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":"Thinking","type":"boolean","description":"Enable reasoning before answering.","required":false,"metadata":{},"default":true},{"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":"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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"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 $0.02 to the request cost when enabled.","required":false,"metadata":{"ui":{"control":"toggle","section":"Tools"},"billing":{"price_per_query":0.02}},"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":{"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"},{"prompt":"0.000001","completion":"0.000004","image":"0","request":"0","input_cache_read":"0","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 query when enabled","label":"Web search","value":"$0.02"}],"limits":{"note":"Supports text, image, and video input. Web search is available through tool_web_search and adds $0.02 per query 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","display_name":"Qwen3.6 Flash (Variant 1)","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":65536,"model_released_at":"2026-04-16","is_new":true,"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 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":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":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":"Thinking","type":"boolean","description":"Enable reasoning before answering.","required":false,"metadata":{},"default":true},{"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":"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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"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_query":0.01}},"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":{"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"},{"prompt":"0.00000066","completion":"0.000003961","image":"0","request":"0","input_cache_read":"0","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 query when enabled","label":"Web search","value":"$0.01"}],"limits":{"note":"Supports text, image, and video input. Web search is available through tool_web_search and adds $0.01 per query 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","display_name":"Qwen3.6 Plus (Variant 1)","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"],"structured_output":"json_object","batch_supported":"batch","batch_discount_pct":35,"context_window":1000000,"context_length":1000000,"max_output_tokens":65536,"model_released_at":"2026-04-02","is_new":true,"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 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":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":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":"Thinking","type":"boolean","description":"Enable reasoning before answering.","required":false,"metadata":{},"default":true},{"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":"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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"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_query":0.01}},"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":{"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"},{"prompt":"0.000001101","completion":"0.000006602","image":"0","request":"0","input_cache_read":"0","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 query when enabled","label":"Web search","value":"$0.01"}],"limits":{"note":"Supports text, image, and video input. Web search is available through tool_web_search and adds $0.01 per query 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","display_name":"Qwen3.5 Plus (Variant 1)","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"],"structured_output":"json_object","batch_supported":"batch","batch_discount_pct":35,"context_window":1000000,"context_length":1000000,"max_output_tokens":65536,"model_released_at":"2026-02-16","is_new":true,"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 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":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":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":"Thinking","type":"boolean","description":"Enable reasoning before answering.","required":false,"metadata":{},"default":true},{"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":"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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"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_query":0.01}},"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":{"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"},{"prompt":"0.000000573","completion":"0.00000344","image":"0","request":"0","input_cache_read":"0","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 (was $1.08)"},{"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 (was $6.62)"},{"spec":"per query when enabled","label":"Web search","value":"$0.01"}],"limits":{"note":"Supports text, image, and video input. Web search is available through tool_web_search and adds $0.01 per query 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","display_name":"Qwen3.5 Flash (Variant 1)","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"],"structured_output":"json_object","batch_supported":"batch","batch_discount_pct":35,"context_window":1000000,"context_length":1000000,"max_output_tokens":65536,"model_released_at":"2026-02-24","is_new":true,"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 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":0.9,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{},"default":4096,"min":1,"max":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":"Thinking","type":"boolean","description":"Enable reasoning before answering.","required":false,"metadata":{},"default":true},{"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":"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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"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_query":0.01}},"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":{"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"},{"prompt":"0.000000172","completion":"0.00000172","image":"0","request":"0","input_cache_read":"0","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 query when enabled","label":"Web search","value":"$0.01"}],"limits":{"note":"Supports text, image, and video input. Web search is available through tool_web_search and adds $0.01 per query 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","display_name":"Gemma 4 26B-A4B","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"],"structured_output":"json_schema","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":true,"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. Lower values are more deterministic.","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.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Model"}},"default":0.95,"min":0,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens.","required":false,"metadata":{"ui":{"control":"number","section":"Model"}},"default":4096,"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. none disables thinking; low, medium, high, and max set bounded thinking budgets.","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 the model reasoning channel before final output.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum thinking tokens before the final answer. If max_tokens is lower, the service reserves room for the answer.","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,"max":200},{"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":"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":"Penalty used by SGLang to reduce repeated text.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":1,"min":0.1,"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":"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"}},"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":"stream","label":"Stream","type":"boolean","description":"Stream response deltas using server-sent events.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"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":{"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","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 request when enabled","label":"Web search","value":"$0.013"}],"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"},{"id":"qwen3-5-9b","object":"model","display_name":"Qwen3.5 9B","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"],"structured_output":"json_schema","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":true,"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,"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":"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 effort. none disables thinking; low, medium, high, and max set bounded thinking budgets.","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 the model reasoning channel before final output.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum thinking tokens before the final answer. If max_tokens is lower, the service reserves room for the answer.","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,"max":200},{"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":"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":"Penalty used by SGLang to reduce repeated text.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":1,"min":0.1,"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":"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"}},"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":"stream","label":"Stream","type":"boolean","description":"Stream response deltas using server-sent events.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"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":{"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","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 request when enabled","label":"Web search","value":"$0.013"}],"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"},{"id":"qwen3-5-4b","object":"model","display_name":"Qwen3.5 4B","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"],"structured_output":"json_schema","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":true,"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,"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":"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 effort. none disables thinking; low, medium, high, and max set bounded thinking budgets.","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 the model reasoning channel before final output.","required":false,"metadata":{"ui":{"control":"toggle","section":"Model"}},"default":true},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum thinking tokens before the final answer. If max_tokens is lower, the service reserves room for the answer.","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,"max":200},{"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":"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":"Penalty used by SGLang to reduce repeated text.","required":false,"metadata":{"ui":{"step":0.01,"control":"slider","section":"Advanced sampling"}},"default":1,"min":0.1,"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":"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"}},"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":"stream","label":"Stream","type":"boolean","description":"Stream response deltas using server-sent events.","required":false,"metadata":{"ui":{"control":"toggle","section":"Output"}},"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":{"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","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 request when enabled","label":"Web search","value":"$0.013"}],"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"},{"id":"glm-4-7-flash","object":"model","display_name":"GLM 4.7 Flash","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":200000,"context_length":200000,"max_output_tokens":131072,"model_released_at":"2026-01-19","is_new":true,"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. GLM-4.7-Flash and GLM-4.6V-Flash default to 1.0; GLM-4.5-Flash defaults to 0.6.","required":false,"metadata":{},"default":1,"min":0,"max":1},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Z.AI documents a 0.95 default for the GLM-4.7, GLM-4.6, and GLM-4.5 series.","required":false,"metadata":{},"default":0.95,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens for GLM-4.7-Flash: 131072.","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":"Controls Z.AI thinking mode. Enabled is the default and makes GLM-4.7-Flash think; disable it 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\"}. GLM-4.7-Flash thinks when enabled.","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":"Controls whether the model may use tools. Z.AI documents auto tool selection; 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"}],"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","display_name":"GLM 4.5 Flash","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":200000,"context_length":200000,"max_output_tokens":98304,"model_released_at":"2025-07-28","is_new":true,"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. GLM-4.7-Flash and GLM-4.6V-Flash default to 1.0; GLM-4.5-Flash defaults to 0.6.","required":false,"metadata":{},"default":0.6,"min":0,"max":1},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Z.AI documents a 0.95 default for the GLM-4.7, GLM-4.6, and GLM-4.5 series.","required":false,"metadata":{},"default":0.95,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens for GLM-4.5-Flash: 98304.","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":"Controls Z.AI thinking mode. Enabled is the default; GLM-4.5-Flash automatically decides whether to think when enabled.","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\"}. GLM-4.5-Flash automatically decides whether to think when enabled.","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":"Controls whether the model may use tools. Z.AI documents auto tool selection; 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"}],"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-4-6v-flash","object":"model","display_name":"GLM 4.6V Flash","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":128000,"context_length":128000,"max_output_tokens":32768,"model_released_at":"2025-12-08","is_new":true,"is_featured":false,"discount":null,"capabilities":{"streaming":true,"system_prompt":true,"web_search":true,"images":true,"audio":false,"video":true,"three_d":false,"reasoning":false},"supported_parameters":[{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. Lower values are more deterministic. GLM-4.7-Flash and GLM-4.6V-Flash default to 1.0; GLM-4.5-Flash defaults to 0.6.","required":false,"metadata":{},"default":1,"min":0,"max":1},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling probability mass. Z.AI documents a 0.95 default for the GLM-4.7, GLM-4.6, and GLM-4.5 series.","required":false,"metadata":{},"default":0.95,"min":0.01,"max":1},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum output tokens for GLM-4.6V-Flash: 32768.","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":"Controls Z.AI thinking mode. Enabled is the default; GLM-4.6V-Flash automatically decides whether to think when enabled.","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\"}. GLM-4.6V-Flash automatically decides whether to think when enabled.","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":"Controls whether the model may use tools. Z.AI documents auto tool selection; 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"}],"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":"amazon-nova-canvas","object":"model","display_name":"Amazon Nova Canvas","provider":"amazon","description":"Image generation and editing model creating and modifying images from text or image inputs, with inpainting, virtual try-on, and style controls.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text","image"],"output_modalities":["image"],"features":["inpainting","background_removal"],"structured_output":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2024-12-03","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 description of the image to generate.","required":true,"metadata":{}},{"name":"task_type","label":"Task Type","type":"enum","description":"TEXT_IMAGE | INPAINTING | OUTPAINTING | IMAGE_VARIATION | COLOR_GUIDED_GENERATION | BACKGROUND_REMOVAL | VIRTUAL_TRY_ON.","required":false,"metadata":{},"default":"TEXT_IMAGE","options":["TEXT_IMAGE","IMAGE_VARIATION","INPAINTING","OUTPAINTING","BACKGROUND_REMOVAL","COLOR_GUIDED_GENERATION","VIRTUAL_TRY_ON"]},{"name":"quality","label":"Quality","type":"enum","description":"standard | premium. Premium is slower but higher fidelity.","required":false,"metadata":{},"default":"standard","options":["standard","premium"]},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"Text description of what to avoid in the image.","required":false,"metadata":{},"default":""},{"name":"number_of_images","label":"Number Of Images","type":"number","description":"How many images to generate (1-5).","required":false,"metadata":{},"default":1,"min":1,"max":5},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio (1:1, 16:9, 9:16, 4:3, 3:2, etc.).","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"1:1","options":["1:1","3:4","2:3","9:16","1:2","1:3","1:4","4:3","3:2","16:9","2:1","3:1","4:1"]},{"name":"size_scale","label":"Size Scale","type":"enum","description":"Output resolution scale. Higher = larger image, slower generation.","required":false,"metadata":{},"default":"small","options":["small","large"]},{"name":"cfg_scale","label":"Cfg Scale","type":"number","description":"Prompt adherence (1.1-10). Higher = closer to prompt but less creative.","required":false,"metadata":{},"default":7.5,"min":1,"max":20},{"name":"seed","label":"Seed","type":"number","description":"Random seed for reproducibility. Same seed + prompt = same output.","required":false,"metadata":{}},{"name":"image","label":"Image","type":"string","description":"Source image (URL or base64) for inpainting / outpainting / variation tasks.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"reference_image","label":"Reference Image","type":"string","description":"Reference image for style or content matching.","required":false,"metadata":{"ui":{"hide_in_playground":true},"visible_when":{"op":"in","field":"task_type","values":["VIRTUAL_TRY_ON","COLOR_GUIDED_GENERATION"]},"clear_when_hidden":true}},{"name":"mask_image","label":"Mask Image","type":"string","description":"Black/white mask defining the region to edit (white = edit, black = keep).","required":false,"metadata":{"visible_when":{"op":"in","field":"task_type","values":["INPAINTING","OUTPAINTING"]},"clear_when_hidden":true}},{"name":"mask_prompt","label":"Mask Prompt","type":"string","description":"Natural-language description of the region to mask for inpainting.","required":false,"metadata":{"visible_when":{"op":"eq","field":"task_type","value":"OUTPAINTING"},"clear_when_hidden":true}},{"name":"inpaint_mask_prompt","label":"Inpaint Mask Prompt","type":"string","description":"Same as mask_prompt, for inpainting tasks specifically.","required":false,"metadata":{"visible_when":{"op":"eq","field":"task_type","value":"INPAINTING"},"clear_when_hidden":true}},{"name":"tryon_mask_prompt","label":"Tryon Mask Prompt","type":"string","description":"Natural-language description of the garment region for virtual try-on.","required":false,"metadata":{"visible_when":{"op":"eq","field":"task_type","value":"VIRTUAL_TRY_ON"},"clear_when_hidden":true}},{"name":"similarity_strength","label":"Similarity Strength","type":"number","description":"How closely to match the reference image (0-1). Lower = looser interpretation.","required":false,"metadata":{"visible_when":{"op":"eq","field":"task_type","value":"IMAGE_VARIATION"},"clear_when_hidden":true},"default":0.7,"min":0.2,"max":1},{"name":"outpainting_mode","label":"Outpainting Mode","type":"enum","description":"DEFAULT | PRECISE. Precise preserves edges; default is more creative.","required":false,"metadata":{"visible_when":{"op":"eq","field":"task_type","value":"OUTPAINTING"},"clear_when_hidden":true},"default":"DEFAULT","options":["DEFAULT","PRECISE"]},{"name":"color_palette","label":"Color Palette","type":"string","description":"Predefined color palette name for color-guided generation.","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"colors","label":"Colors","type":"string","description":"Comma-separated hex codes (e.g. \"#FF0000,#00FF00\") to constrain the palette.","required":false,"metadata":{"control":"color-list","visible_when":{"op":"eq","field":"task_type","value":"COLOR_GUIDED_GENERATION"},"clear_when_hidden":true}},{"name":"mask_type","label":"Mask Type","type":"enum","description":"image | prompt. image = use mask_image, prompt = use mask_prompt to derive the mask.","required":false,"metadata":{"visible_when":{"op":"eq","field":"task_type","value":"VIRTUAL_TRY_ON"},"clear_when_hidden":true},"default":"GARMENT","options":["GARMENT","PROMPT"]},{"name":"garment_class","label":"Garment Class","type":"string","description":"Garment category for virtual try-on (top, bottom, dress, etc.).","required":false,"metadata":{"visible_when":{"op":"eq","field":"task_type","value":"VIRTUAL_TRY_ON"},"clear_when_hidden":true}},{"name":"response_format","label":"Response Format","type":"enum","description":"url (default) returns a signed URL; b64_json returns inline base64.","required":false,"metadata":{},"default":"url","options":["url","b64_json"]}],"supported_endpoints":["POST /v1/images/generations"],"pricing":{"prompt":"0","completion":"0","image":"0.12","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Small Standard (≤1024×1024)","value":"$0.12"},{"spec":"per image","label":"Small Premium (≤1024×1024)","value":"$0.18"},{"spec":"per image","label":"Large Standard (≤2048×2048)","value":"$0.18"},{"spec":"per image","label":"Large Premium (≤2048×2048)","value":"$0.24"}],"limits":{"note":"**Task types**\n\n- TEXT_IMAGE\n- IMAGE_VARIATION\n- INPAINTING\n- OUTPAINTING\n- BACKGROUND_REMOVAL\n- COLOR_GUIDED_GENERATION\n- VIRTUAL_TRY_ON\n\n**Mask**\n\n- Image-based or text-prompt-based\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=amazon-nova-canvas","api_url":"https://docs.empiriolabs.ai/models/amazon-nova-canvas","logo":"https://media.empiriolabs.ai/model-logos/amazon-nova-canvas.png","status":"available"},{"id":"amazon-nova-reel-1-1","object":"model","display_name":"Amazon Nova Reel 1.1","provider":"amazon","description":"Video generation model producing up to 2-minute multi-shot videos from text and optional image prompts with improved quality and consistency.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image"],"output_modalities":["video"],"features":["camera_control"],"structured_output":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-04-07","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":"Text description of the output to generate.","required":true,"metadata":{}},{"name":"duration","label":"Duration","type":"number","description":"Length of the generated clip in seconds.","required":false,"metadata":{"ui":{"step":6,"control":"slider"},"step":6},"default":6,"min":6,"max":120},{"name":"seed","label":"Seed","type":"number","description":"Random seed for reproducibility. Same seed + prompt = same output.","required":false,"metadata":{}},{"name":"manual_mode","label":"Manual Mode","type":"boolean","description":"Multi-shot mode: provide image_shots","required":false,"metadata":{"visible_when":{"op":"gt","field":"duration","value":6},"clear_when_hidden":true},"default":false},{"name":"image_shots","label":"Image Shots","type":"string","description":"JSON array of {prompt, image} for manual_mode","required":false,"metadata":{"visible_when":{"op":"eq","field":"manual_mode","value":true},"clear_when_hidden":true}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per second","label":"Per Second","value":"$0.14"}],"limits":{"note":"**Multi-shot output**\n\n- Up to 2 minutes total, in 6-second increments\n- Manual mode: provide one prompt per 6-second shot, with optional starting image (1280x720 PNG/JPEG)\n\n**Retention**\n\n- Generated videos are deleted after 48 hours.\n\n**Uploaded media preprocessing**\n\n- Uploaded starter images are resized to 1280x720 before generation.\n- Duration is generated in 6-second increments."},"notes":"**Multi-shot output**\n\n- Up to 2 minutes total, in 6-second increments\n- Manual mode: provide one prompt per 6-second shot, with optional starting image (1280x720 PNG/JPEG)\n\n**Retention**\n\n- Generated videos are deleted after 48 hours.\n\n**Uploaded media preprocessing**\n\n- Uploaded starter images are resized to 1280x720 before generation.\n- Duration is generated in 6-second increments.","chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=amazon-nova-reel-1-1","api_url":"https://docs.empiriolabs.ai/models/amazon-nova-reel-1-1","logo":"https://media.empiriolabs.ai/model-logos/amazon-nova-reel-1-1.png","status":"available"},{"id":"deepgram-nova-3","object":"model","display_name":"Deepgram Nova 3","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"],"structured_output":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":false},{"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},{"name":"generate_pdf","label":"Generate PDF","type":"boolean","description":"When true, Deepgram returns a PDF transcript alongside the JSON.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/audio/transcriptions"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per minute of audio","label":"Transcription","value":"$0.014"}],"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","display_name":"DeepReasoning","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"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 both the R1 reasoning stage and the Claude synthesis stage.","required":false,"metadata":{},"default":0.7,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Nucleus sampling. Applies to both the R1 reasoning stage and the Claude synthesis 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":65536},{"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.","required":false,"metadata":{},"default":"claude-sonnet-4-5-20250929","options":["claude-sonnet-4-5-20250929","claude-haiku-4-5-20251001","claude-opus-4-5-20251101","claude-opus-4-1-20250805","claude-opus-4-20250514","claude-sonnet-4-20250514"]},{"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","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","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 1K tokens","label":"R1-0528 + Claude Sonnet 4.5 (Default)","value":"In $0.012 / Out $0.058"},{"spec":"per 1K tokens","label":"R1-0528 + Claude Haiku 4.5","value":"In $0.0048 / Out $0.023"},{"spec":"per 1K tokens","label":"R1-0528 + Claude Opus 4.5","value":"In $0.019 / Out $0.092"},{"spec":"per 1K tokens","label":"R1-0528 + Claude Sonnet 4","value":"In $0.012 / Out $0.058"},{"spec":"per 1K tokens","label":"R1-0528 + Claude Opus 4.1","value":"In $0.053 / Out $0.26"},{"spec":"per 1K tokens","label":"R1-0528 + Claude Opus 4","value":"In $0.053 / Out $0.26"},{"spec":"per request when enabled","label":"Web search","value":"$0.013"}],"limits":{"note":"R1-0528 reasoning paired with one of: Claude Sonnet 4.5 (default), Haiku 4.5, Opus 4.5, Sonnet 4, Opus 4.1, Opus 4, Sonnet 3.7, Haiku 3.5, Opus 3.\n\n**About \"Native Inference\" for this model**\n\nEmpirioLabs hosts the project's open-source API/orchestration logic from its GitHub repo on our own infrastructure — that's the \"native\" part. The underlying models (R1-0528 reasoning + the Claude completion model you pick) are still dialed via their respective official APIs. We don't host the model weights themselves."},"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-prover-v2","object":"model","display_name":"DeepSeek Prover V2","provider":"deepseek","description":"Open-source LLM specialized in formal theorem proving in Lean 4, built on a recursive theorem-proving pipeline.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["math","reasoning"],"structured_output":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-04-30","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":[],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1beta/models/deepseek-prover-v2:generateContent"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0.02","input_cache_read":"0"},"pricing_rows":[{"spec":"fixed","label":"Per Message","value":"$0.020"}],"limits":{"note":"Specialized for formal theorem proving in Lean 4. Routed through OpenRouter."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=deepseek-prover-v2","api_url":"https://docs.empiriolabs.ai/models/deepseek-prover-v2","logo":"https://media.empiriolabs.ai/model-logos/deepseek-prover-v2.png","status":"available"},{"id":"deepseek-v3-2","object":"model","display_name":"DeepSeek V3.2","provider":"deepseek","description":"Open-source Mixture-of-Experts LLM tuned for high-efficiency reasoning, coding, and general language tasks across long-form prompts.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning"],"structured_output":"json_schema","batch_supported":null,"batch_discount_pct":null,"context_window":128000,"context_length":128000,"max_output_tokens":32768,"model_released_at":"2025-12-01","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","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":"Max output tokens","required":false,"metadata":{},"default":4096,"min":1,"max":65536},{"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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","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 the reasoning process. Up to 393216.","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":"enable_search","label":"Web Search","type":"boolean","description":"Allow real-time web search. Billed only when the provider reports search usage.","required":false,"metadata":{},"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-v3-2:generateContent"],"pricing":{"prompt":"0.00000057","completion":"0.00000171","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.57"},{"spec":"per 1M generated tokens","label":"Output","value":"$1.71"},{"spec":"per request when enabled","label":"Web search","value":"$0.015"}],"limits":{"note":"Web search calls cost $0.015 each — only billed when invoked. Reasoning tokens (CoT) bill as output tokens."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=deepseek-v3-2","api_url":"https://docs.empiriolabs.ai/models/deepseek-v3-2","logo":"https://media.empiriolabs.ai/model-logos/deepseek.png","status":"available"},{"id":"deepseek-v4-flash","object":"model","display_name":"DeepSeek V4 Flash","provider":"deepseek","description":"Lightweight MoE model with 284B total / 13B active parameters and native 1M context, tuned for low-latency, cost-effective high-concurrency use.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning"],"structured_output":"json_schema","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":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.","required":false,"metadata":{},"default":4096,"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":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for the reasoning process. Up to 393216.","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":"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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","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:generateContent"],"pricing":{"prompt":"0.00000014","completion":"0.00000028","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.14"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.28"},{"spec":"per request when enabled","label":"Web search","value":"$0.013"}],"limits":null,"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=deepseek-v4-flash","api_url":"https://docs.empiriolabs.ai/models/deepseek-v4-flash","logo":"https://media.empiriolabs.ai/model-logos/deepseek.png","status":"available"},{"id":"deepseek-v4-pro","object":"model","display_name":"DeepSeek V4 Pro","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"],"structured_output":"json_schema","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.","required":false,"metadata":{},"default":4096,"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":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for the reasoning process. Up to 393216.","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":"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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","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"},"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 request when enabled","label":"Web search","value":"$0.013"}],"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","display_name":"Exa Answer","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"],"structured_output":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":"Skip the EmpirioLabs Markdown formatting (citation [[N]](url) rewriting + References block). The raw upstream answer with plain [N] citations is returned; the structured citations array still passes through.","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"}],"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","display_name":"Exa Search","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"],"structured_output":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 | answer | research. Determines which Exa endpoint runs.","required":false,"metadata":{},"default":"search","options":["search","similar","contents","code"]},{"name":"search_type","label":"Search Type","type":"enum","description":"Choose the search algorithm: auto, neural, keyword, fast, or full. Alias of type.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"search"},"clear_when_hidden":true},"default":"auto","options":["auto","instant","neural","deep","fast"]},{"name":"type","label":"Type","type":"enum","description":"auto | keyword | neural. Auto picks the best mode per query.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"search"},"clear_when_hidden":true},"default":"auto","options":["auto","instant","neural","deep","fast"]},{"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 (research-paper, news, github, etc.).","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"search"},"clear_when_hidden":true},"options":["company","research paper","news","github","tweet","movie","song","personal site","pdf"]},{"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.","required":false,"metadata":{"visible_when":{"op":"in","field":"operation","values":["search","similar"]},"clear_when_hidden":true}},{"name":"include_text","label":"Include Text","type":"string","description":"Comma-separated text snippets that must appear","required":false,"metadata":{"visible_when":{"op":"in","field":"operation","values":["search","similar"]},"clear_when_hidden":true}},{"name":"exclude_text","label":"Exclude Text","type":"string","description":"Comma-separated text snippets to exclude","required":false,"metadata":{"visible_when":{"op":"in","field":"operation","values":["search","similar"]},"clear_when_hidden":true}},{"name":"start_crawl_date","label":"Start Crawl Date","type":"string","description":"Only return results crawled after this date. ISO 8601 (e.g. 2024-01-01T00:00:00Z).","required":false,"metadata":{"visible_when":{"op":"in","field":"operation","values":["search","similar"]},"clear_when_hidden":true}},{"name":"end_crawl_date","label":"End Crawl Date","type":"string","description":"Only return results crawled before this date. ISO 8601.","required":false,"metadata":{"visible_when":{"op":"in","field":"operation","values":["search","similar"]},"clear_when_hidden":true}},{"name":"start_published_date","label":"Start Published Date","type":"string","description":"Only return results published after this date. ISO 8601.","required":false,"metadata":{"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.","required":false,"metadata":{"visible_when":{"op":"in","field":"operation","values":["search","similar"]},"clear_when_hidden":true}},{"name":"return_text","label":"Return Text","type":"boolean","description":"Fetch the full page text content for each result. Alias of text.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":false},{"name":"show_content","label":"Show Content","type":"boolean","description":"Display the complete page content in results. Alias of text.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":false},{"name":"text","label":"Text","type":"boolean","description":"Return full page text","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":false},{"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.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":false},{"name":"highlights","label":"Highlights","type":"boolean","description":"Include relevant text snippets (\"highlights\") per result.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"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_sentences","label":"Highlights Sentences","type":"number","description":"Number of sentences to include per highlight.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":3,"min":1,"max":10},{"name":"highlights_per_url","label":"Highlights Per Url","type":"number","description":"Max highlights returned per URL.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":3,"min":1,"max":10},{"name":"return_summary","label":"Return Summary","type":"boolean","description":"Get an AI-generated summary of each result. Alias of summary.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":false},{"name":"summary","label":"Summary","type":"boolean","description":"Return an LLM-generated summary of each result.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"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":"livecrawl","label":"Livecrawl","type":"enum","description":"never | fallback | always. Fetch a fresh crawl instead of cached content.","required":false,"metadata":{"visible_when":{"op":"eq","field":"operation","value":"contents"},"clear_when_hidden":true},"default":"fallback","options":["always","fallback","never","preferred"]},{"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":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Skip the EmpirioLabs Markdown formatting (Sources / References / Code blocks added by the renderer). The raw upstream Exa search JSON is returned for power users / agents that want to parse the schema directly.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/search"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per search","label":"Search (1-25 results)","value":"$0.0060"},{"spec":"per search","label":"Search (26-100 results)","value":"$0.030"},{"spec":"per page/feature","label":"Content (Text/Highlights/Summary)","value":"$0.0060"},{"spec":"per 1k tokens","label":"Code Search","value":"$0.0060"}],"limits":{"note":"**Operations**\n\n- search, similar pages, contents, code search\n\n**Search types**\n\n- Auto, Instant (sub-150ms), Neural (embeddings), Deep Search (Exa 2.1), Fast\n\n**Categories**\n\n- Company, Research Paper, News, PDF, GitHub, Tweet, Personal Site, LinkedIn Profile, Financial Report"},"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","display_name":"Gemini 2.5 Flash TTS","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"],"structured_output":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"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":{},"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"},"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 (mp3, wav, opus, flac, etc.).","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, 24000, 44100, 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"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.50"},{"spec":"per 1M generated tokens","label":"Output","value":"$30.00"}],"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","display_name":"Gemini 2.5 Pro TTS","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"],"structured_output":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"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":{},"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"},"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 (mp3, wav, opus, flac, etc.).","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, 24000, 44100, 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"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$3.00"},{"spec":"per 1M generated tokens","label":"Output","value":"$60.00"}],"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","display_name":"Gemini 3.1 Flash TTS","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"],"structured_output":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"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":{},"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"},"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 (mp3, wav, opus, flac, etc.).","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, 24000, 44100, 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"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$2.60"},{"spec":"per 1M generated tokens","label":"Output","value":"$52.00"}],"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","display_name":"Gemma 3 27B","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"],"structured_output":"none","batch_supported":null,"batch_discount_pct":null,"context_window":128000,"context_length":128000,"max_output_tokens":8192,"model_released_at":"2025-03-10","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":0.7,"min":0,"max":2},{"name":"top_p","label":"top_p","type":"number","description":"Nucleus sampling","required":false,"metadata":{},"default":1,"min":0,"max":1},{"name":"max_tokens","label":"max_tokens","type":"number","description":"Max output tokens","required":false,"metadata":{},"default":4096,"min":1,"max":65536},{"name":"frequency_penalty","label":"frequency_penalty","type":"number","description":"Penalty for repeated tokens. >0 reduces repetition, <0 encourages it.","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.","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":"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","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 request when enabled","label":"Web search","value":"$0.013"}],"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","display_name":"GLM TTS","provider":"zhipu","description":"LLM-based text-to-speech with zero-shot voice cloning from 3-10s of audio 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"],"structured_output":null,"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. The reference recording must contain the speaker reading this exact consent phrase aloud, 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.\" Reference audio without the phrase is rejected.","required":false,"metadata":{}},{"name":"output_format","label":"Output Format","type":"enum","description":"Output media file format (mp3, wav, mp4, png, jpg, etc., depending on the endpoint).","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":["24000","16000"]},{"name":"volume","label":"Volume","type":"number","description":"Output gain multiplier.","required":false,"metadata":{},"default":1,"min":0.1,"max":2},{"name":"use_cache","label":"Use Cache","type":"boolean","description":"Speeds up repeated identical generations.","required":false,"metadata":{},"default":true},{"name":"optimize_input","label":"Optimize Input","type":"boolean","description":"Auto-fix pronunciation of technical terms, acronyms, and special characters.","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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 1k characters","label":"Fast (INT8)","value":"$0.20"},{"spec":"per 1k characters","label":"Quality (FP16)","value":"$0.21"}],"limits":{"note":"**Limits**\n\n- Max input: 5,000 characters\n- Generation: 5-10 minutes\n\n**Voice cloning**\n\n- Reference audio: 3-10 seconds\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","display_name":"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"],"structured_output":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. Bibliography: analyze citations and references. Sources / Fact Check: find supporting sources for claims in your text.","required":false,"metadata":{},"default":"ai_detection","options":["ai_detection","bibliography","sources","fact_check"]},{"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). The worker downloads the file and forwards it to GPTZero's multipart files endpoint. 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":"Select a specific GPTZero model version, or leave as __latest__ for the newest rolling release. Choosing an explicit multilingual release overrides the separate multilingual flag.","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":"Canonical name for model_version. Pin a specific upstream snapshot, or leave as __latest__ for the default rolling alias.","required":false,"metadata":{"examples":["__latest__","2024-08-01"]},"default":"__latest__"},{"name":"multilingual","label":"Multilingual","type":"boolean","description":"Use GPTZero's multilingual detection path. Applies to text scans when Model Version is __latest__; file scans use whichever model version is selected.","required":false,"metadata":{"visible_when":{"op":"eq","field":"scan_type","value":"ai_detection"},"clear_when_hidden":true},"default":false},{"name":"ai_threshold","label":"Ai Threshold","type":"number","description":"Probability cutoff for flagging sentences as AI-generated. Lower = more sensitive. Range 0.10 to 0.99.","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":"Maximum number of sentences shown in the per-sentence breakdown section.","required":false,"metadata":{"visible_when":{"op":"eq","field":"scan_type","value":"ai_detection"},"clear_when_hidden":true},"default":15,"min":1,"max":50},{"name":"source_sentence","label":"Source Sentence","type":"string","description":"Optional. The exact sentence or claim you want to find supporting sources for. If left blank, the full input text is used as the claim. (sources / fact_check scan only.)","required":false,"metadata":{"visible_when":{"op":"eq","field":"scan_type","value":"sources"},"clear_when_hidden":true}},{"name":"max_sources","label":"Max Sources","type":"number","description":"Maximum number of sources to retrieve for each identified claim. (sources / fact_check scan only.)","required":false,"metadata":{"visible_when":{"op":"eq","field":"scan_type","value":"sources"},"clear_when_hidden":true},"default":3,"min":1,"max":10},{"name":"confidence_threshold","label":"Confidence Threshold","type":"number","description":"Minimum confidence required for a source-match to be returned. Range 0 to 1. (sources / fact_check scan only.)","required":false,"metadata":{"visible_when":{"op":"eq","field":"scan_type","value":"sources"},"clear_when_hidden":true},"default":0.5,"min":0,"max":1},{"name":"claim_extractor","label":"Claim Extractor","type":"string","description":"Method used to extract claims from your text. claimbuster is faster; llm_claim_extractor is more thorough. (sources / fact_check scan only.)","required":false,"metadata":{"visible_when":{"op":"eq","field":"scan_type","value":"sources"},"clear_when_hidden":true},"default":"claimbuster"},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Skip the EmpirioLabs Markdown report (per-sentence highlights / scan summary / sources list). The raw upstream GPTZero JSON response is returned.","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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 1,000 words","label":"Text Scan","value":"$0.39"}],"limits":{"note":"**File limits**\n\n- Max 50 files per request\n- Combined size cap: 15 MB\n- Each document truncated to 50,000 characters\n\n**Supported formats**\n\n- PDF, DOC, DOCX, TXT, ODT"},"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","display_name":"HappyHorse 1.0","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"],"structured_output":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":true,"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.","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":5,"min":3,"max":15},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio (1:1, 16:9, 9:16, 4:3, 3:2, etc.).","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":"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":"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 audio from the reference video.","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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per second","label":"All Modes 720P","value":"$0.14"},{"spec":"per second","label":"All Modes 1080P","value":"$0.24"}],"limits":{"note":"**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**Uploaded media preprocessing**\n\n- Video inputs are capped to 15 seconds.\n- Uploaded video inputs are normalized to provider-compatible MP4 when needed."},"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**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","display_name":"Hunyuan Image 3","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"],"structured_output":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.","required":true,"metadata":{}},{"name":"size","label":"Size","type":"enum","description":"Output resolution. Square, portrait, and landscape presets.","required":false,"metadata":{},"default":"1024x1024","options":["1024x1024","768x1024","1024x768","1024x1536","1536x1024","512x512"]},{"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":"num_inference_steps","label":"Num Inference Steps","type":"number","description":"Diffusion steps. More = higher fidelity, slower.","required":false,"metadata":{},"default":28,"min":10,"max":50},{"name":"guidance_scale","label":"Guidance Scale","type":"number","description":"Classifier-free guidance. Higher = follows prompt more strictly.","required":false,"metadata":{},"default":7.5,"min":1,"max":20},{"name":"seed","label":"Seed","type":"number","description":"Reproducibility seed.","required":false,"metadata":{}},{"name":"response_format","label":"Response Format","type":"enum","description":"url (default) returns a signed URL; b64_json returns inline base64.","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"}],"limits":{"note":"Diffusion image model with configurable steps and guidance scale.\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","display_name":"Hunyuan Video 1.5","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"],"structured_output":null,"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 25%","percent":25},"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 (1:1, 16:9, 9:16, 4:3, 3:2, etc.).","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":{}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"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"}],"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":"janus-pro-deepseek","object":"model","display_name":"Janus-Pro DeepSeek","provider":"deepseek","description":"Autoregressive framework on the Janus Pro 7B model that unifies multimodal understanding and image generation in one architecture.","modality":"image","type":"generation","category":"image","category_label":null,"modality_label":null,"modalities":["image","text"],"input_modalities":["text","image"],"output_modalities":["text","image"],"features":["vision","image_generation"],"structured_output":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2025-01-27","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 description for image generation.","required":true,"metadata":{}},{"name":"generation_image_size","label":"Generation Image Size","type":"enum","description":"Output image dimensions (e.g. 384x384, 768x768).","required":false,"metadata":{},"default":"square","options":["square","square_hd","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9"]},{"name":"generation_temperature","label":"Generation Temperature","type":"number","description":"Sampling temperature for image generation. Higher = more variation.","required":false,"metadata":{},"default":1,"min":0.1,"max":2},{"name":"generation_cfg_weight","label":"Generation Cfg Weight","type":"number","description":"Classifier-free guidance weight. Higher = closer to prompt but less creative.","required":false,"metadata":{},"default":5,"min":1,"max":20},{"name":"generation_num_images","label":"Generation Num Images","type":"number","description":"How many images to generate (1-4).","required":false,"metadata":{},"default":1,"min":1,"max":4},{"name":"generation_seed","label":"Generation Seed","type":"number","description":"Random seed for reproducibility. Same seed + prompt = same output.","required":false,"metadata":{}},{"name":"image_url","label":"Image Url","type":"string","description":"URL of an image to analyze (image-understanding mode).","required":false,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"question","label":"Question","type":"string","description":"Question to answer about the supplied image.","required":false,"metadata":{}},{"name":"analysis_temperature","label":"Analysis Temperature","type":"number","description":"Sampling temperature for image analysis. Higher = more variation.","required":false,"metadata":{},"default":0.1,"min":0,"max":1},{"name":"analysis_top_p","label":"Analysis Top P","type":"number","description":"Nucleus sampling probability mass for image analysis.","required":false,"metadata":{},"default":0.95,"min":0.1,"max":1},{"name":"analysis_seed","label":"Analysis Seed","type":"number","description":"Random seed for analysis output reproducibility.","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/images/generations","POST /v1/chat/completions","POST /v1/images/analysis","POST /v1beta/models/janus-pro-deepseek:generateContent"],"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 uploaded image","label":"Image Analysis","value":"$0.030"}],"limits":{"note":"Image generation and image analysis both billed per image.\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=janus-pro-deepseek","api_url":"https://docs.empiriolabs.ai/models/janus-pro-deepseek","logo":"https://media.empiriolabs.ai/model-logos/janus-pro-deepseek.png","status":"available"},{"id":"kling-o3","object":"model","display_name":"Kling O3","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"],"structured_output":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":"Kling O3 supports landscape, square, and portrait only.","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"16:9","options":["16:9","1:1","9:16"]},{"name":"duration","label":"Duration","type":"number","description":"Per-scene duration in seconds.","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.","required":false,"metadata":{},"default":true},{"name":"keep_original_sound","label":"Keep Original Sound","type":"boolean","description":"video_edit only. Keep audio from the source video.","required":false,"metadata":{},"default":true},{"name":"image","label":"Image","type":"string","description":"Reference image URL 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":"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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"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"}],"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","display_name":"Kling v3 Motion Control","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"],"structured_output":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":"Reference image URL — provides the character/subject.","required":true,"metadata":{"ui":{"hide_in_playground":true}}},{"name":"reference_video","label":"Reference Video","type":"string","description":"Reference video URL — 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":"Seconds. Capped at 10 when character_orientation=image, 30 when character_orientation=video.","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":5,"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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per second","label":"Standard (720p)","value":"$0.14"},{"spec":"per second","label":"Pro (1080p)","value":"$0.18"}],"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","display_name":"Linkup Deep Search","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"],"structured_output":null,"batch_supported":null,"batch_discount_pct":null,"context_window":100000,"context_length":100000,"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":"searchResults | sourcedAnswer. sourcedAnswer returns a synthesized answer with citations; searchResults returns raw hits.","required":false,"metadata":{},"default":"sourcedAnswer","options":["sourcedAnswer","searchResults"]},{"name":"domain_filter_mode","label":"Domain Filter Mode","type":"enum","description":"include | exclude. Whether the domain filter lists allowed or blocked 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"}],"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","display_name":"Linkup Standard","provider":"linkup","description":"AI-powered web search with detailed overviews and answers, faster than Deep Search. Ranks #1 on OpenAI SimpleQA benchmark.","modality":"text","type":"search","category":"research","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["web_search"],"structured_output":null,"batch_supported":null,"batch_discount_pct":null,"context_window":100000,"context_length":100000,"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":"searchResults | sourcedAnswer. sourcedAnswer returns a synthesized answer with citations; searchResults returns raw hits.","required":false,"metadata":{},"default":"sourcedAnswer","options":["sourcedAnswer","searchResults","structured"]},{"name":"domain_filter_mode","label":"Domain Filter Mode","type":"enum","description":"include | exclude. Whether the domain filter lists allowed or blocked 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"}],"limits":{"note":"#1 globally on the OpenAI SimpleQA benchmark for factual accuracy."},"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":"magistral-medium-2509-thinking","object":"model","display_name":"Magistral Medium 2509 Thinking","provider":"mistral","description":"Reasoning model tuned for tasks needing longer thought and higher accuracy: legal research, financial forecasting, software, and storytelling.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","thinking"],"structured_output":"json_object","batch_supported":"batch","batch_discount_pct":35,"context_window":40000,"context_length":40000,"max_output_tokens":40000,"model_released_at":"2025-09-17","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","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":1,"min":0,"max":1},{"name":"max_tokens","label":"max_tokens","type":"number","description":"Max output tokens","required":false,"metadata":{},"default":4096,"min":1,"max":65536},{"name":"frequency_penalty","label":"frequency_penalty","type":"number","description":"Penalty for repeated tokens. >0 reduces repetition, <0 encourages it.","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.","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":"include_reasoning","label":"Include reasoning","type":"boolean","description":"When true, the response includes the model's reasoning trace alongside the final answer.","required":false,"metadata":{},"default":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":{"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/magistral-medium-2509-thinking:generateContent"],"pricing":{"prompt":"0.0000026","completion":"0.0000065","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$2.60"},{"spec":"per 1M generated tokens","label":"Output","value":"$6.50"},{"spec":"per request when enabled","label":"Web search","value":"$0.013"}],"limits":{"note":"Standard Magistral Medium 2509 chat parameters. No separate thinking budget is exposed."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=magistral-medium-2509-thinking","api_url":"https://docs.empiriolabs.ai/models/magistral-medium-2509-thinking","logo":"https://media.empiriolabs.ai/model-logos/magistral-medium-2509-thinking.png","status":"available"},{"id":"mistral-medium-3","object":"model","display_name":"Mistral Medium 3","provider":"mistral","description":"Cost-efficient language model offering strong reasoning and multimodal performance for general production workloads at competitive latency.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image"],"input_modalities":["text","image"],"output_modalities":["text"],"features":["vision"],"structured_output":"json_object","batch_supported":"batch","batch_discount_pct":35,"context_window":130000,"context_length":130000,"max_output_tokens":40000,"model_released_at":"2025-05-07","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":0.7,"min":0,"max":2},{"name":"top_p","label":"top_p","type":"number","description":"Nucleus sampling","required":false,"metadata":{},"default":1,"min":0,"max":1},{"name":"max_tokens","label":"max_tokens","type":"number","description":"Max output tokens","required":false,"metadata":{},"default":4096,"min":1,"max":65536},{"name":"frequency_penalty","label":"frequency_penalty","type":"number","description":"Penalty for repeated tokens. >0 reduces repetition, <0 encourages it.","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.","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":"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/mistral-medium-3:generateContent"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0.015","input_cache_read":"0"},"pricing_rows":[{"spec":"fixed","label":"Per Message","value":"$0.015"},{"spec":"per request when enabled","label":"Web search","value":"$0.013"}],"limits":null,"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=mistral-medium-3","api_url":"https://docs.empiriolabs.ai/models/mistral-medium-3","logo":"https://media.empiriolabs.ai/model-logos/mistral-medium-3.png","status":"available"},{"id":"mistral-medium-3-1","object":"model","display_name":"Mistral Medium 3.1","provider":"mistral","description":"Enterprise-grade model with strong reasoning, coding, and STEM performance, supporting hybrid, on-prem, and in-VPC deployments.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text","image"],"input_modalities":["text","image"],"output_modalities":["text"],"features":["vision"],"structured_output":"json_object","batch_supported":"batch","batch_discount_pct":35,"context_window":131000,"context_length":131000,"max_output_tokens":40000,"model_released_at":"2025-08-12","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":0.7,"min":0,"max":2},{"name":"top_p","label":"top_p","type":"number","description":"Nucleus sampling","required":false,"metadata":{},"default":1,"min":0,"max":1},{"name":"max_tokens","label":"max_tokens","type":"number","description":"Max output tokens","required":false,"metadata":{},"default":4096,"min":1,"max":65536},{"name":"frequency_penalty","label":"frequency_penalty","type":"number","description":"Penalty for repeated tokens. >0 reduces repetition, <0 encourages it.","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.","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":"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/mistral-medium-3-1:generateContent"],"pricing":{"prompt":"0.00000052","completion":"0.0000026","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.52"},{"spec":"per 1M generated tokens","label":"Output","value":"$2.60"},{"spec":"per request when enabled","label":"Web search","value":"$0.013"}],"limits":null,"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=mistral-medium-3-1","api_url":"https://docs.empiriolabs.ai/models/mistral-medium-3-1","logo":"https://media.empiriolabs.ai/model-logos/mistral-medium-3-1.png","status":"available"},{"id":"mistral-small-3-1","object":"model","display_name":"Mistral Small 3.1","provider":"mistral","description":"24B-parameter multimodal model with 128K context 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"],"structured_output":"json_schema","batch_supported":null,"batch_discount_pct":null,"context_window":128000,"context_length":128000,"max_output_tokens":32000,"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, 2 = maximum randomness.","required":false,"metadata":{},"default":0.7,"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":1,"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":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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","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 request when enabled","label":"Web search","value":"$0.013"}],"limits":null,"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","display_name":"Mistral Small 4","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"],"structured_output":"json_object","batch_supported":"batch","batch_discount_pct":35,"context_window":256000,"context_length":256000,"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":false,"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 (maps to reasoning: high|none)","required":false,"metadata":{},"default":true},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable web_search tool","required":false,"metadata":{},"default":true},{"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":true},{"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":true},{"name":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 2 = maximum randomness.","required":false,"metadata":{},"default":0.7,"min":0,"max":1.5},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum tokens in the response.","required":false,"metadata":{},"default":4096,"min":1,"max":32768},{"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":"Skip the EmpirioLabs Markdown formatting (citation [[N]](url) rewriting + References block when the web_search tool was used). The raw upstream answer with plain [N] citations is returned.","required":false,"metadata":{},"default":false}],"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"},"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"}],"limits":{"note":"Tools (web search, code interpreter, image generation) are billed only when actually invoked.","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","display_name":"MOSS Video and Audio","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"],"structured_output":null,"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":"t2v: pure text-to-video. i2v: animate the attached image.","required":false,"metadata":{},"default":"t2v","options":["t2v","i2v"]},{"name":"resolution","label":"Resolution","type":"enum","description":"720p uses a separate higher-VRAM endpoint.","required":false,"metadata":{},"default":"720p","options":["360p","720p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"MOSS only supports landscape (16:9) and portrait (9:16).","required":false,"metadata":{"ui":{"control":"segmented"}},"default":"landscape","options":["landscape","portrait"]},{"name":"duration","label":"Duration","type":"number","description":"Clip length in seconds. The upstream model is hard-capped at 8s.","required":false,"metadata":{"ui":{"step":1,"control":"slider"}},"default":8,"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":{}}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0.17","input_cache_read":"0"},"pricing_rows":[{"spec":"per video","label":"360p Video","value":"$0.17"},{"spec":"per video","label":"720p Video","value":"$2.82"},{"spec":"additional fee","label":"T2V Fast","value":"$0.065"},{"spec":"additional fee","label":"T2V Quality","value":"$0.13"}],"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","display_name":"Nova Lite 1.0","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"],"structured_output":"json_object","batch_supported":"batch","batch_discount_pct":35,"context_window":300000,"context_length":300000,"max_output_tokens":5000,"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. 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 tokens in the response.","required":false,"metadata":{},"default":4096,"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":"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","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 request when enabled","label":"Web search","value":"$0.013"}],"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","display_name":"Nova Lite 2","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"],"structured_output":"json_object","batch_supported":"batch","batch_discount_pct":35,"context_window":1000000,"context_length":1000000,"max_output_tokens":32000,"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":false},"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 tokens in the response.","required":false,"metadata":{},"default":4096,"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_reasoning","label":"Enable Reasoning","type":"boolean","description":"Enable the model's reasoning mode. Slower but improves multi-step problems.","required":false,"metadata":{},"default":true},{"name":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable extended reasoning before the final answer. Alias of enable_reasoning.","required":false,"metadata":{},"default":true},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort level (low | medium | high). Higher = more thinking time.","required":false,"metadata":{"visible_when":{"op":"eq","field":"enable_reasoning","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":"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","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 request when enabled","label":"Web search","value":"$0.013"}],"limits":{"note":"Reasoning traces are NOT exposed from AWS. 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","display_name":"Nova Micro 1.0","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"],"structured_output":"json_object","batch_supported":"batch","batch_discount_pct":35,"context_window":128000,"context_length":128000,"max_output_tokens":5000,"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. 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 tokens in the response.","required":false,"metadata":{},"default":4096,"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":"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","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 request when enabled","label":"Web search","value":"$0.013"}],"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-premier-1-0","object":"model","display_name":"Nova Premier 1.0","provider":"amazon","description":"Most capable model in the family. Multimodal text/image/video on a 1M context with chain-of-thought reasoning across tools and data sources.","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"],"structured_output":"json_object","batch_supported":"batch","batch_discount_pct":35,"context_window":1000000,"context_length":1000000,"max_output_tokens":32000,"model_released_at":"2025-04-30","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. 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 tokens in the response.","required":false,"metadata":{},"default":4096,"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":"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","required":false,"metadata":{"group":"tools"},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/nova-premier-1-0:generateContent"],"pricing":{"prompt":"0.000003","completion":"0.000015","image":"0","request":"0","input_cache_read":"0.00000168"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$3.00"},{"spec":"per 1M generated tokens","label":"Output","value":"$15.00"},{"spec":"per 1M tokens","label":"Cached input","value":"$1.68"},{"spec":"per request when enabled","label":"Web search","value":"$0.013"}],"limits":{"note":"Supports text, image, and video inputs with standard chat parameters."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=nova-premier-1-0","api_url":"https://docs.empiriolabs.ai/models/nova-premier-1-0","logo":"https://media.empiriolabs.ai/model-logos/nova-premier-1-0.png","status":"available"},{"id":"nova-pro-1-0","object":"model","display_name":"Nova Pro 1.0","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"],"structured_output":"json_object","batch_supported":"batch","batch_discount_pct":35,"context_window":300000,"context_length":300000,"max_output_tokens":5000,"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. 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 tokens in the response.","required":false,"metadata":{},"default":4096,"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":"latency_optimized","label":"Latency Optimized","type":"boolean","description":"Prefer faster routing at a slight quality cost.","required":false,"metadata":{},"default":false},{"name":"enable_latency_optimized","label":"Latency Optimized","type":"boolean","description":"Enable latency-optimized routing for faster responses, billed at the catalog Latency Optimized rate ($3.00 input / $12.00 output per 1M tokens) instead of the Standard rate.","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"}},{"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":"When enabled, the gateway will not append the \"Sources\" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.","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"},"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 request when enabled","label":"Web search","value":"$0.013"}],"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","display_name":"OpenAI Whisper 1","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"],"structured_output":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2022-09-21","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":"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":"Overridden to verbose_json when timestamps=true.","required":false,"metadata":{},"default":"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"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per minute","label":"Per Minute of Audio","value":"$0.030"}],"limits":null,"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","display_name":"Perplexity Advanced Deep Research","provider":"perplexity","description":"Institutional-grade research powered by Claude Opus 4.6 reasoning, with maximum depth, enhanced tool access, 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"],"structured_output":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":true,"audio":false,"video":false,"three_d":false,"reasoning":true},"supported_parameters":[{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Level of reasoning depth. Higher effort = more thorough analysis.","required":false,"metadata":{},"default":"high","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. Higher = more content per source but slower. Default is 4096.","required":false,"metadata":{},"default":4096,"min":4096,"max":16384},{"name":"search_domain_filter","label":"Search Domain Filter","type":"string","description":"Comma-separated domains. Prefix with '-' to exclude. Max 20.","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. Cannot be combined with specific dates.","required":false,"metadata":{},"default":"none","options":["none","day","week","month","year"]},{"name":"search_after_date","label":"Search After Date","type":"string","description":"Only include sources published after this date. Use YYYY-MM-DD or natural language.","required":false,"metadata":{}},{"name":"search_before_date","label":"Search Before Date","type":"string","description":"Only include sources published before this date. Use YYYY-MM-DD or natural language.","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.","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"},"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"}],"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","display_name":"Perplexity Deep Research","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"],"structured_output":null,"batch_supported":null,"batch_discount_pct":null,"context_window":128000,"context_length":128000,"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":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 2 = maximum randomness.","required":false,"metadata":{},"default":0.2,"min":0,"max":2},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum tokens in the response.","required":false,"metadata":{},"default":16384,"min":1,"max":65536},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Level of reasoning depth. Higher effort = more thorough analysis but slower.","required":false,"metadata":{},"default":"high","options":["low","medium","high"]},{"name":"search_mode","label":"Search Mode","type":"enum","description":"Filter search results by source type. Academic = scholarly papers, SEC = financial filings.","required":false,"metadata":{},"default":"default","options":["default"]},{"name":"search_domain_filter","label":"Search Domain Filter","type":"string","description":"Comma-separated domains. Prefix with '-' to exclude. Max 20.","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_after_date_filter","label":"Search After Date Filter","type":"string","description":"Only include sources published after this date. Use YYYY-MM-DD or natural language.","required":false,"metadata":{}},{"name":"search_before_date_filter","label":"Search Before Date Filter","type":"string","description":"Only include sources published before this date. Use YYYY-MM-DD or natural language.","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.","required":false,"metadata":{}},{"name":"last_updated_before_filter","label":"Last Updated Before Filter","type":"string","description":"Only include sources last updated before this date.","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"},"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"}],"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","display_name":"Perplexity Pro Search","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"],"structured_output":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":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":0.2,"min":0,"max":2},{"name":"max_tokens","label":"Max Tokens","type":"number","description":"Maximum tokens in the response.","required":false,"metadata":{},"default":4096,"min":1,"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 = scholarly papers, SEC = financial filings.","required":false,"metadata":{},"default":"default","options":["default","academic","sec"]},{"name":"stream_mode","label":"Stream Mode","type":"enum","description":"Concise streams the final answer only. Full also streams research progress in real time.","required":false,"metadata":{},"default":"concise","options":["concise","full"]},{"name":"search_domain_filter","label":"Search Domain Filter","type":"string","description":"Comma-separated domains. Prefix with '-' to exclude. Max 20.","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_after_date","label":"Search After Date","type":"string","description":"Only include sources published after this date. Use YYYY-MM-DD or natural language.","required":false,"metadata":{}},{"name":"search_before_date","label":"Search Before Date","type":"string","description":"Only include sources published before this date. Use YYYY-MM-DD or natural language.","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 YYYY-MM-DD or natural language.","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 YYYY-MM-DD or natural language.","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":"return_images","label":"Return Images","type":"boolean","description":"Include relevant images alongside the search results.","required":false,"metadata":{},"default":false},{"name":"image_domain_filter","label":"Image Domain Filter","type":"string","description":"Comma-separated domains for image results. Prefix with '-' to exclude. Max 10.","required":false,"metadata":{"visible_when":{"op":"eq","field":"return_images","value":true},"clear_when_hidden":true}},{"name":"image_format_filter","label":"Image Format Filter","type":"string","description":"Comma-separated image file formats to allow (jpg, png, etc.).","required":false,"metadata":{}},{"name":"return_videos","label":"Return Videos","type":"boolean","description":"Include relevant videos alongside the search results.","required":false,"metadata":{},"default":false},{"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"},"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"}],"limits":{"note":"**Search context size**\n\n- Low / Medium / High — controls depth and cost\n\n**Search modes**\n\n- `academic` — academic sources only\n- `sec` — SEC filings only\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- Returns inline images and embedded video previews"},"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","display_name":"Perplexity Search","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"],"structured_output":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 20.","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 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 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 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 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":{}},{"name":"display_server_time","label":"Display Server Time","type":"boolean","description":"Include the server-time timestamp in the response payload.","required":false,"metadata":{},"default":false}],"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"}],"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","display_name":"Perplexity Sonar","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"],"structured_output":null,"batch_supported":null,"batch_discount_pct":null,"context_window":127000,"context_length":127000,"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":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 2 = maximum randomness.","required":false,"metadata":{},"default":0.2,"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 tokens in the response.","required":false,"metadata":{},"default":1024,"min":1,"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 = scholarly papers, SEC = financial filings.","required":false,"metadata":{},"default":"default","options":["default","academic","sec"]},{"name":"search_domain_filter","label":"Search Domain Filter","type":"string","description":"Comma-separated list of domains (allow with no prefix, deny with leading -)","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_after_date","label":"Search After Date","type":"string","description":"Use YYYY-MM-DD. Only include sources after this date.","required":false,"metadata":{}},{"name":"search_before_date","label":"Search Before Date","type":"string","description":"Use YYYY-MM-DD. Only include sources before this date.","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":"Use 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 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 (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":"return_images","label":"Return Images","type":"boolean","description":"Include relevant images alongside the search results.","required":false,"metadata":{},"default":false},{"name":"image_domain_filter","label":"Image Domain Filter","type":"string","description":"Comma-separated domains for image results. Prefix with '-' to exclude. Max 10.","required":false,"metadata":{"visible_when":{"op":"eq","field":"return_images","value":true},"clear_when_hidden":true}},{"name":"image_format_filter","label":"Image Format Filter","type":"string","description":"Comma-separated image file formats to allow (jpg, png, etc.).","required":false,"metadata":{}},{"name":"return_videos","label":"Return Videos","type":"boolean","description":"Include relevant videos alongside the search results.","required":false,"metadata":{},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Skip the EmpirioLabs Markdown formatting (citation [[N]](url) rewriting + References block + Images / Videos blocks). The raw upstream answer with plain [N] citations is returned; structured search_results / citations still pass through where Perplexity emits them.","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"},"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"}],"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","display_name":"Perplexity Sonar Pro","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"],"structured_output":null,"batch_supported":null,"batch_discount_pct":null,"context_window":200000,"context_length":200000,"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":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 2 = maximum randomness.","required":false,"metadata":{},"default":0.2,"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 tokens in the response.","required":false,"metadata":{},"default":4096,"min":1,"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 = scholarly papers, SEC = financial filings.","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 20.","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_after_date","label":"Search After Date","type":"string","description":"Use YYYY-MM-DD. Only include sources after this date.","required":false,"metadata":{}},{"name":"search_before_date","label":"Search Before Date","type":"string","description":"Use YYYY-MM-DD. Only include sources before this date.","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":"Use 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 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 (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":"return_images","label":"Return Images","type":"boolean","description":"Include relevant images alongside the search results.","required":false,"metadata":{},"default":false},{"name":"image_domain_filter","label":"Image Domain Filter","type":"string","description":"Comma-separated domains for image results. Prefix with '-' to exclude. Max 10.","required":false,"metadata":{"visible_when":{"op":"eq","field":"return_images","value":true},"clear_when_hidden":true}},{"name":"image_format_filter","label":"Image Format Filter","type":"string","description":"Comma-separated image file formats to allow (jpg, png, etc.).","required":false,"metadata":{}},{"name":"return_videos","label":"Return Videos","type":"boolean","description":"Include relevant videos alongside the search results.","required":false,"metadata":{},"default":false},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Skip the EmpirioLabs Markdown formatting (citation [[N]](url) rewriting + References block + Images / Videos blocks). The raw upstream answer with plain [N] citations is returned; structured search_results / citations still pass through where Perplexity emits them.","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"},"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"}],"limits":{"note":"Double the citations and larger context window vs Sonar. Max output 8K 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","display_name":"Perplexity Sonar Reasoning Pro","provider":"perplexity","description":"Reasoning model on the uncensored open-source R1-1776 with web search, outperforming leading search engines and LLMs on the SimpleQA benchmark.","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"],"structured_output":null,"batch_supported":null,"batch_discount_pct":null,"context_window":128000,"context_length":128000,"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":"temperature","label":"Temperature","type":"number","description":"Sampling temperature. 0 = deterministic, 2 = maximum randomness.","required":false,"metadata":{},"default":0.2,"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 tokens in the response.","required":false,"metadata":{},"default":8192,"min":1,"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 = scholarly papers, SEC = financial filings.","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 20.","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_after_date","label":"Search After Date","type":"string","description":"Use YYYY-MM-DD. Only include sources after this date.","required":false,"metadata":{}},{"name":"search_before_date","label":"Search Before Date","type":"string","description":"Use YYYY-MM-DD. Only include sources before this date.","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":"Use 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 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 (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":"return_images","label":"Return Images","type":"boolean","description":"Include relevant images alongside the search results.","required":false,"metadata":{},"default":false},{"name":"image_domain_filter","label":"Image Domain Filter","type":"string","description":"Comma-separated domains for image results. Prefix with '-' to exclude. Max 10.","required":false,"metadata":{"visible_when":{"op":"eq","field":"return_images","value":true},"clear_when_hidden":true}},{"name":"image_format_filter","label":"Image Format Filter","type":"string","description":"Comma-separated image file formats to allow (jpg, png, etc.).","required":false,"metadata":{}},{"name":"return_videos","label":"Return Videos","type":"boolean","description":"Include relevant videos alongside the search results.","required":false,"metadata":{},"default":false},{"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"},"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"}],"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","display_name":"Pixverse v5","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"],"structured_output":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":"t2v: text-to-video. i2v: animate the attached image. transition: morph between image (start) and image_end.","required":false,"metadata":{},"default":"t2v","options":["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 (1:1, 16:9, 9:16, 4:3, 3:2, etc.).","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":"0.45","input_cache_read":"0"},"pricing_rows":[{"spec":"per video","label":"360p/540p 5s","value":"$0.45"},{"spec":"per video","label":"360p/540p 8s","value":"$0.90"},{"spec":"per video","label":"720p 5s","value":"$0.60"},{"spec":"per video","label":"720p 8s","value":"$1.20"},{"spec":"per video","label":"1080p 5s","value":"$1.20"}],"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","display_name":"Pixverse v5.6","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"],"structured_output":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":"t2v: text-to-video. i2v: animate the attached image.","required":false,"metadata":{},"default":"t2v","options":["t2v","i2v"]},{"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 (1:1, 16:9, 9:16, 4:3, 3:2, etc.).","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.","required":false,"metadata":{},"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.","required":false,"metadata":{},"default":"auto","options":["auto","enabled","disabled"]},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"What to avoid (≤2048 chars).","required":false,"metadata":{},"default":""},{"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":"0.4","input_cache_read":"0"},"pricing_rows":[{"spec":"per video","label":"360p/540p 5s no audio","value":"$0.40"},{"spec":"per video","label":"360p/540p 5s audio","value":"$0.80"},{"spec":"per video","label":"360p/540p 8s no audio","value":"$0.80"},{"spec":"per video","label":"360p/540p 8s audio","value":"$1.60"},{"spec":"per video","label":"360p/540p 10s no audio","value":"$0.88"},{"spec":"per video","label":"360p/540p 10s audio","value":"$1.76"},{"spec":"per video","label":"720p 5s no audio","value":"$0.65"},{"spec":"per video","label":"720p 5s audio","value":"$1.30"},{"spec":"per video","label":"720p 8s no audio","value":"$1.30"},{"spec":"per video","label":"720p 8s audio","value":"$2.60"},{"spec":"per video","label":"720p 10s no audio","value":"$1.43"},{"spec":"per video","label":"720p 10s audio","value":"$2.86"},{"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":"$3.00"}],"limits":{"note":"Generates videos from text or 1-2 frame image prompts up to 1080p with optional audio.\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 or 1-2 frame image prompts up to 1080p with optional audio.\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","display_name":"Qwen Image 2.0","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"],"structured_output":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"]},{"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":"Response Format","type":"enum","description":"url (default) returns a signed URL; b64_json returns inline base64.","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)"}],"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":"qwen3-5-flash","object":"model","display_name":"Qwen3.5 Flash","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"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":false},"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 tokens in the response.","required":false,"metadata":{},"default":4096,"min":1,"max":32768},{"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":"vl_high_resolution_images","label":"Vl High Resolution Images","type":"boolean","description":"Use higher resolution for input images. Better detail at higher cost.","required":false,"metadata":{},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixels per input image. Larger = more detail but slower / more tokens.","required":false,"metadata":{"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":1,"max":99999999},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information.","required":false,"metadata":{},"default":false},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking.","required":false,"metadata":{},"default":true},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking.","required":false,"metadata":{},"default":true},{"name":"tool_web_search_image","label":"Text-to-Image Search","type":"boolean","description":"Search the web for images from text descriptions.","required":false,"metadata":{},"default":true},{"name":"tool_image_search","label":"Image-to-Image Search","type":"boolean","description":"Find similar images from an uploaded image.","required":false,"metadata":{},"default":true},{"name":"video_fps","label":"Video Fps","type":"number","description":"Frames-per-second sampled from input video for analysis.","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 input images as a video for temporal reasoning.","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"}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Skip the EmpirioLabs Markdown formatting (citation [[N]](url) rewriting + References block when web search / tools were used). The raw upstream answer with plain [N] citations is returned.","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"},"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 request when enabled","label":"Web search","value":"$0.015"},{"spec":"per call","label":"Image Search","value":"$0.012"}],"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","display_name":"Qwen3.5 Omni Flash","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"],"structured_output":"json_schema","batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"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":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"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 tokens in the response.","required":false,"metadata":{},"default":4096,"min":1,"max":32768},{"name":"output_mode","label":"Output Mode","type":"enum","description":"Output format mode. text = text only, audio = include synthesized speech.","required":false,"metadata":{},"default":"text","options":["text","text_audio"]},{"name":"voice","label":"Voice","type":"string","description":"Voice name for audio output (when output_mode = audio).","required":false,"metadata":{"visible_when":{"op":"eq","field":"output_mode","value":"text_audio"},"clear_when_hidden":true},"default":"Tina"},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Allow the model to perform web searches when needed.","required":false,"metadata":{},"default":false},{"name":"video_fps","label":"Video Fps","type":"number","description":"Frames-per-second sampled from input video for analysis.","required":false,"metadata":{},"default":2,"min":0.1,"max":10},{"name":"vl_high_resolution_images","label":"Vl High Resolution Images","type":"boolean","description":"Use higher resolution for input images. Better detail at higher cost.","required":false,"metadata":{},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixels per input image. Larger = more detail but slower / more tokens.","required":false,"metadata":{"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":1,"max":99999999},{"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 /v1/audio/speech","POST /v1beta/models/qwen3-5-omni-flash:generateContent"],"pricing":{"prompt":"0.0000004","completion":"0.0000022","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"per 1M prompt tokens $0.40; per 1M prompt tokens $3.00"},{"spec":"per 1M generated tokens","label":"Output","value":"per 1M generated tokens $2.20; per 1M generated tokens $11.90"},{"spec":"per request","label":"Web search","value":"$0.015"}],"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","display_name":"Qwen3.5 Omni Plus","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"],"structured_output":"json_schema","batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"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":false,"images":true,"audio":true,"video":true,"three_d":false,"reasoning":false},"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 tokens in the response.","required":false,"metadata":{},"default":4096,"min":1,"max":32768},{"name":"output_mode","label":"Output Mode","type":"enum","description":"Output format mode. text = text only, audio = include synthesized speech.","required":false,"metadata":{},"default":"text","options":["text","text_audio"]},{"name":"voice","label":"Voice","type":"string","description":"Voice name for audio output (when output_mode = audio).","required":false,"metadata":{"visible_when":{"op":"eq","field":"output_mode","value":"text_audio"},"clear_when_hidden":true},"default":"Tina"},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Allow the model to perform web searches when needed.","required":false,"metadata":{},"default":false},{"name":"video_fps","label":"Video Fps","type":"number","description":"Frames-per-second sampled from input video for analysis.","required":false,"metadata":{},"default":2,"min":0.1,"max":10},{"name":"vl_high_resolution_images","label":"Vl High Resolution Images","type":"boolean","description":"Use higher resolution for input images. Better detail at higher cost.","required":false,"metadata":{},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixels per input image. Larger = more detail but slower / more tokens.","required":false,"metadata":{"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":1,"max":99999999},{"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 /v1/audio/speech","POST /v1beta/models/qwen3-5-omni-plus:generateContent"],"pricing":{"prompt":"0.0000014","completion":"0.0000083","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"per 1M prompt tokens $1.40; per 1M prompt tokens $11.00"},{"spec":"per 1M generated tokens","label":"Output","value":"per 1M generated tokens $8.30; per 1M generated tokens $44.00"},{"spec":"per request","label":"Web search","value":"$0.015"}],"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","display_name":"Qwen3.5 Plus","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":65536,"model_released_at":"2026-02-16","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 = 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 tokens in the response.","required":false,"metadata":{},"default":4096,"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 extended thinking mode. Slower but improves reasoning-heavy tasks.","required":false,"metadata":{},"default":true},{"name":"vl_high_resolution_images","label":"Vl High Resolution Images","type":"boolean","description":"Use higher resolution for input images. Better detail at higher cost.","required":false,"metadata":{},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixels per input image. Larger = more detail but slower / more tokens.","required":false,"metadata":{"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":1,"max":99999999},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information.","required":false,"metadata":{},"default":false},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking.","required":false,"metadata":{},"default":true},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking.","required":false,"metadata":{},"default":true},{"name":"tool_web_search_image","label":"Text-to-Image Search","type":"boolean","description":"Search the web for images from text descriptions.","required":false,"metadata":{},"default":true},{"name":"tool_image_search","label":"Image-to-Image Search","type":"boolean","description":"Find similar images from an uploaded image.","required":false,"metadata":{},"default":true},{"name":"video_fps","label":"Video Fps","type":"number","description":"Frames-per-second sampled from input video for analysis.","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 input images as a video for temporal reasoning.","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"}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Skip the EmpirioLabs Markdown formatting (citation [[N]](url) rewriting + References block when web search / tools were used). The raw upstream answer with plain [N] citations is returned.","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"},{"prompt":"0.00000108","completion":"0.00000662","image":"0","request":"0","input_cache_read":"0","min_context":256000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=256K $0.36 (was $0.40); 256K-1M $1.08 (was $1.20)"},{"spec":"per 1M generated tokens","label":"Output","value":"<=256K $2.21 (was $2.40); 256K-1M $6.62 (was $7.20)"},{"spec":"per request when enabled","label":"Web search","value":"$0.015"},{"spec":"per call","label":"Image Search","value":"$0.012"}],"limits":{"note":"Pricing is 3x 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-max-preview","object":"model","display_name":"Qwen3.6 Max Preview","provider":"alibaba","description":"Largest preview variant in the 3.6 series (text-only): improved coding agent execution, stronger front-end skills, and broader long-tail knowledge.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","agentic_coding","web_search"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"max_output_tokens":65536,"model_released_at":"2026-04-20","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","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":1,"min":0,"max":1},{"name":"max_tokens","label":"max_tokens","type":"number","description":"Max output tokens","required":false,"metadata":{},"default":4096,"min":1,"max":65536},{"name":"frequency_penalty","label":"frequency_penalty","type":"number","description":"Penalty for repeated tokens. >0 reduces repetition, <0 encourages it.","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.","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":"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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","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":"Reason step-by-step before answering","required":false,"metadata":{},"default":true},{"name":"thinking_budget","label":"Thinking Budget","type":"number","description":"Tokens reserved for thinking","required":false,"metadata":{"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":"Search the web for real-time information.","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"}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Skip the EmpirioLabs Markdown formatting (citation [[N]](url) rewriting + References block when web search / tools were used). The raw upstream answer with plain [N] citations is returned.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-6-max-preview:generateContent"],"pricing":[{"prompt":"0.00000131","completion":"0.00000788","image":"0","request":"0","input_cache_read":"0"},{"prompt":"0.00000197","completion":"0.00001182","image":"0","request":"0","input_cache_read":"0","min_context":128000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=128K $1.31; 128K-256K $1.97"},{"spec":"per 1M generated tokens","label":"Output","value":"<=128K $7.88; 128K-256K $11.82"},{"spec":"per request when enabled","label":"Web search","value":"$0.020"}],"limits":{"note":"Pricing is ~1.5x above 128K tokens. Plain-text capabilities only in this preview; multimodal not yet enabled.","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-max-preview","api_url":"https://docs.empiriolabs.ai/models/qwen3-6-max-preview","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-6-plus","object":"model","display_name":"Qwen3.6 Plus","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","cache","function_calling","reasoning","video","vision","web_search"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"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 = 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 tokens in the response.","required":false,"metadata":{},"default":4096,"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 extended thinking mode. Slower but improves reasoning-heavy tasks.","required":false,"metadata":{},"default":true},{"name":"vl_high_resolution_images","label":"Vl High Resolution Images","type":"boolean","description":"Use higher resolution for input images. Better detail at higher cost.","required":false,"metadata":{},"default":true},{"name":"max_pixels","label":"Max Pixels","type":"number","description":"Maximum pixels per input image. Larger = more detail but slower / more tokens.","required":false,"metadata":{"visible_when":{"op":"eq","field":"vl_high_resolution_images","value":false},"clear_when_hidden":true},"default":2621440,"min":1,"max":99999999},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information.","required":false,"metadata":{},"default":false},{"name":"tool_web_extractor","label":"Web Extractor","type":"boolean","description":"Extract and read content from URLs. Requires Web Search and Thinking.","required":false,"metadata":{},"default":true},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Run Python code in a sandbox. Requires Thinking.","required":false,"metadata":{},"default":true},{"name":"tool_web_search_image","label":"Text-to-Image Search","type":"boolean","description":"Search the web for images from text descriptions.","required":false,"metadata":{},"default":true},{"name":"tool_image_search","label":"Image-to-Image Search","type":"boolean","description":"Find similar images from an uploaded image.","required":false,"metadata":{},"default":true},{"name":"video_fps","label":"Video Fps","type":"number","description":"Frames-per-second sampled from input video for analysis.","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 input images as a video for temporal reasoning.","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"}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Skip the EmpirioLabs Markdown formatting (citation [[N]](url) rewriting + References block when web search / tools were used). The raw upstream answer with plain [N] citations is returned.","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"},{"prompt":"0.000002","completion":"0.000006","image":"0","request":"0","input_cache_read":"0","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 request when enabled","label":"Web search","value":"$0.026"},{"spec":"per call","label":"Image Search","value":"$0.0208"}],"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-max","object":"model","display_name":"Qwen3 Max","provider":"alibaba","description":"256K-context flagship with major improvements in reasoning, instruction following, and multilingual support, plus higher coding/math accuracy.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","code_interpreter","web_search"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"max_output_tokens":65536,"model_released_at":"2025-09-23","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 tokens in the response.","required":false,"metadata":{},"default":4096,"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":"tool_web_search","label":"Web Search","type":"boolean","description":"Search the web for real-time information.","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"}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Skip the EmpirioLabs Markdown formatting (citation [[N]](url) rewriting + References block when web search / tools were used). The raw upstream answer with plain [N] citations is returned.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-max:generateContent"],"pricing":[{"prompt":"0.00000108","completion":"0.00000552","image":"0","request":"0","input_cache_read":"0"},{"prompt":"0.0000027","completion":"0.0000138","image":"0","request":"0","input_cache_read":"0","min_context":128000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=32K $1.08 (was $1.20); 32K-128K $2.16 (was $2.40); 128K-256K $2.70 (was $3.00)"},{"spec":"per 1M generated tokens","label":"Output","value":"<=32K $5.52 (was $6.00); 32K-128K $11.04 (was $12.00); 128K-256K $13.80 (was $15.00)"},{"spec":"per request","label":"Web search","value":"$0.015"}],"limits":{"note":"Optional web search adds $0.015/call when invoked."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-max","api_url":"https://docs.empiriolabs.ai/models/qwen3-max","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-max-preview","object":"model","display_name":"Qwen3 Max Preview","provider":"alibaba","description":"Preview release with major gains over the 2.5 series in Chinese-English understanding, complex instructions, multilingual ability, and tool use.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","code_interpreter","web_search"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"max_output_tokens":65536,"model_released_at":"2025-09-05","is_new":false,"is_featured":true,"discount":{"label":"Save up to 20%","percent":20},"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":{},"default":0.7,"min":0,"max":2},{"name":"top_p","label":"top_p","type":"number","description":"Nucleus sampling","required":false,"metadata":{},"default":1,"min":0,"max":1},{"name":"max_tokens","label":"max_tokens","type":"number","description":"Max output tokens","required":false,"metadata":{},"default":4096,"min":1,"max":65536},{"name":"frequency_penalty","label":"frequency_penalty","type":"number","description":"Penalty for repeated tokens. >0 reduces repetition, <0 encourages it.","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.","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":"Model thinks step-by-step before responding.","required":false,"metadata":{},"default":true},{"name":"tool_code_interpreter","label":"Code Interpreter","type":"boolean","description":"Allow the model to write and execute Python code.","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"}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Skip the EmpirioLabs Markdown formatting (citation [[N]](url) rewriting + References block when web search / tools were used). The raw upstream answer with plain [N] citations is returned.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-max-preview:generateContent"],"pricing":[{"prompt":"0.00000108","completion":"0.0000048","image":"0","request":"0","input_cache_read":"0"},{"prompt":"0.0000027","completion":"0.000012","image":"0","request":"0","input_cache_read":"0","min_context":128000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=32K $1.08 (was $1.20); 32K-128K $2.16 (was $2.40); 128K-256K $2.70 (was $3.00)"},{"spec":"per 1M generated tokens","label":"Output","value":"<=32K $4.80 (was $6.00); 32K-128K $9.60 (was $12.00); 128K-256K $12.00 (was $15.00)"}],"limits":{"note":"Deep thinking + code interpreter both available as opt-in toggles."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=qwen3-max-preview","api_url":"https://docs.empiriolabs.ai/models/qwen3-max-preview","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-max-thinking","object":"model","display_name":"Qwen3 Max Thinking","provider":"alibaba","description":"Reasoning model with adaptive tool use (search, memory, code interpreter) and test-time scaling for higher accuracy on complex tasks.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","code_interpreter","web_search","thinking"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"max_output_tokens":65536,"model_released_at":"2025-09-23","is_new":false,"is_featured":true,"discount":{"label":"Save up to 10%","percent":10},"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 tokens in the response.","required":false,"metadata":{},"default":4096,"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 extended thinking mode. Slower but improves reasoning-heavy tasks.","required":false,"metadata":{},"default":true},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Allow the model to perform web searches when needed.","required":false,"metadata":{},"default":false},{"name":"web_search_mode","label":"Web Search Mode","type":"enum","description":"standard = single search, thorough = multiple deeper searches.","required":false,"metadata":{"visible_when":{"op":"eq","field":"enable_web_search","value":true},"clear_when_hidden":true},"default":"standard","options":["standard","thorough"]},{"name":"tool_code_interpreter","label":"Enable Code Interpreter","type":"boolean","description":"Allow the model to execute Python code in a sandbox to compute / analyze data.","required":false,"metadata":{},"default":true},{"name":"tool_web_extractor","label":"Enable Web Extractor","type":"boolean","description":"Allow the model to fetch and read content from URLs it discovers.","required":false,"metadata":{},"default":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":{"control":"structured-output","so_tier":"json_object"}},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Skip the EmpirioLabs Markdown formatting (citation [[N]](url) rewriting + References block when web search / tools were used). The raw upstream answer with plain [N] citations is returned.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/qwen3-max-thinking:generateContent"],"pricing":[{"prompt":"0.00000108","completion":"0.00000552","image":"0","request":"0","input_cache_read":"0"},{"prompt":"0.0000027","completion":"0.0000138","image":"0","request":"0","input_cache_read":"0","min_context":128000}],"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"<=32K $1.08 (was $1.20); 32K-128K $2.16 (was $2.40); 128K-256K $2.70 (was $3.00)"},{"spec":"per 1M generated tokens","label":"Output","value":"<=32K $5.52 (was $6.00); 32K-128K $11.04 (was $12.00); 128K-256K $13.80 (was $15.00)"},{"spec":"per request","label":"Web search","value":"$0.015"}],"limits":{"note":"Web search modes: Standard (efficient) or Thorough (comprehensive, requires thinking).","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-max-thinking","api_url":"https://docs.empiriolabs.ai/models/qwen3-max-thinking","logo":"https://media.empiriolabs.ai/model-logos/qwen.png","status":"available"},{"id":"qwen3-rerank","object":"model","display_name":"Qwen3 Rerank","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"],"structured_output":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":{},"default":10,"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"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.10"}],"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","display_name":"Seed 2.0 Code","provider":"bytedance","description":"Coding-tuned 256K-context 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"],"structured_output":"none","batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"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":"Max output tokens","required":false,"metadata":{},"default":4096,"min":1,"max":65536},{"name":"frequency_penalty","label":"frequency_penalty","type":"number","description":"Penalty for repeated tokens. >0 reduces repetition, <0 encourages it.","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.","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 BytePlus Ark MCP web search.","required":false,"metadata":{},"default":false},{"name":"enable_caching","label":"enable_caching","type":"boolean","description":"Cache the prompt prefix for ~10 min so follow-up requests reuse it and pay fewer input tokens for the cached portion.","required":false,"metadata":{},"default":false},{"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"},{"prompt":"0.0000008","completion":"0.0000048","image":"0","request":"0","input_cache_read":"0","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"}],"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","display_name":"Seed 2.0 Lite","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"],"structured_output":"json_schema","batch_supported":"batch","batch_discount_pct":35,"context_window":256000,"context_length":256000,"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":"Max output tokens","required":false,"metadata":{},"default":4096,"min":1,"max":65536},{"name":"frequency_penalty","label":"frequency_penalty","type":"number","description":"Penalty for repeated tokens. >0 reduces repetition, <0 encourages it.","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.","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 BytePlus Ark MCP web search.","required":false,"metadata":{},"default":false},{"name":"enable_caching","label":"enable_caching","type":"boolean","description":"Cache the prompt prefix for ~10 min so follow-up requests reuse it and pay fewer input tokens for the cached portion.","required":false,"metadata":{},"default":false},{"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"},{"prompt":"0.00000062","completion":"0.000005","image":"0","request":"0","input_cache_read":"0","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"}],"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","display_name":"Seed 2.0 Mini","provider":"bytedance","description":"Latency-focused multimodal model with 256K context, 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"],"structured_output":"json_schema","batch_supported":"batch","batch_discount_pct":35,"context_window":256000,"context_length":256000,"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":1,"min":0,"max":1},{"name":"max_tokens","label":"max_tokens","type":"number","description":"Max output tokens","required":false,"metadata":{},"default":4096,"min":1,"max":65536},{"name":"frequency_penalty","label":"frequency_penalty","type":"number","description":"Penalty for repeated tokens. >0 reduces repetition, <0 encourages it.","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.","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 BytePlus Ark MCP web search.","required":false,"metadata":{},"default":false},{"name":"enable_caching","label":"enable_caching","type":"boolean","description":"Cache the prompt prefix for ~10 min so follow-up requests reuse it and pay fewer input tokens for the cached portion.","required":false,"metadata":{},"default":false},{"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"},{"prompt":"0.00000024","completion":"0.000001","image":"0","request":"0","input_cache_read":"0","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"}],"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","display_name":"Seed 2.0 Pro","provider":"bytedance","description":"Flagship general model with 256K context 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"],"structured_output":"json_schema","batch_supported":"batch","batch_discount_pct":35,"context_window":256000,"context_length":256000,"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":"Max output tokens","required":false,"metadata":{},"default":4096,"min":1,"max":65536},{"name":"frequency_penalty","label":"frequency_penalty","type":"number","description":"Penalty for repeated tokens. >0 reduces repetition, <0 encourages it.","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.","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 BytePlus Ark MCP web search.","required":false,"metadata":{},"default":false},{"name":"enable_caching","label":"enable_caching","type":"boolean","description":"Cache the prompt prefix for ~10 min so follow-up requests reuse it and pay fewer input tokens for the cached portion.","required":false,"metadata":{},"default":false},{"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"},{"prompt":"0.00000126","completion":"0.00000758","image":"0","request":"0","input_cache_read":"0","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"}],"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","display_name":"Seedance 2.0 Fast","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"],"structured_output":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":"Video generation resolution. Options are model-specific and sourced from the catalog.","required":false,"metadata":{},"default":"720p","options":["480p","720p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio (1:1, 16:9, 9:16, 4:3, 3:2, etc.).","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.","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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"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"}],"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- Pair with Seedream 5.0 Lite for the reference image first when targeting lifelike-face cohesion across multiple inputs.\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- Pair with Seedream 5.0 Lite for the reference image first when targeting lifelike-face cohesion across multiple inputs.\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","display_name":"Seedance 2.0 Pro","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"],"structured_output":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":"Video generation resolution. 4K is available on Seedance 2.0 Pro.","required":false,"metadata":{},"default":"720p","options":["480p","720p","1080p","4k"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"adaptive: derive from input image.","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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"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"}],"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- Pair with Seedream 5.0 Lite for the reference image first when targeting lifelike-face cohesion across multiple inputs.\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- Pair with Seedream 5.0 Lite for the reference image first when targeting lifelike-face cohesion across multiple inputs.\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","display_name":"Seedream 5.0 Lite","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"],"structured_output":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.","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 [2.56MP, 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 [2.56MP, 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.","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're 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"}],"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-5-0-pro","object":"model","display_name":"Seedream 5.0 Pro","provider":"bytedance","description":"Premium Seedream image model for detailed text-to-image, single-image edits, and multi-reference fusion with 1K and 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_reference","text_rendering"],"structured_output":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":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 Pro supports up to 10 reference images.","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":"quality","label":"Quality","type":"enum","description":"Seedream Pro resolution tier. Defaults to 2K.","required":false,"metadata":{"ui":{"control":"segmented","section":"Settings"}},"default":"2K","options":["1K","2K"]},{"name":"size","label":"Size","type":"string","description":"Resolution tier or explicit pixel size such as 1K, 2K, or 2048x2048. Explicit pixels override aspect_ratio and quality.","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.","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, 4.19MP], aspect must be in [1:16, 16:1], and dimensions must be multiples of 16.","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":16,"max":8192},{"name":"custom_height","label":"Custom Height","type":"number","description":"Custom output height in pixels. Total area must be in [0.92MP, 4.19MP], aspect must be in [1:16, 16:1], and dimensions must be multiples of 16.","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":16,"max":8192},{"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.","required":false,"metadata":{"ui":{"control":"segmented","section":"Output"}},"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":{"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 2.36MP","value":"$0.075"},{"spec":"per image","label":"Output above 2.36MP","value":"$0.150"},{"spec":"per input image after the first","label":"Extra input image","value":"$0.005"}],"limits":{"note":"**Modes**\n\n- Text to image\n- Single or multi-image to image\n\n**Limits**\n\n- One output image per request\n- Up to 10 reference images\n- 1K and 2K resolution tiers\n- PNG or JPEG output\n- No grouped-output, streaming, or web-search mode\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\n**Limits**\n\n- One output image per request\n- Up to 10 reference images\n- 1K and 2K resolution tiers\n- PNG or JPEG output\n- No grouped-output, streaming, or web-search mode\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":"soulx-podcast","object":"model","display_name":"SoulX Podcast","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"],"structured_output":null,"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. Speaker must say the consent phrase aloud.","required":false,"metadata":{}},{"name":"voice_s2_audio_url","label":"Voice S2 Audio Url","type":"string","description":"Reference audio URL for [S2] custom-voice cloning.","required":false,"metadata":{}},{"name":"voice_s3_audio_url","label":"Voice S3 Audio Url","type":"string","description":"Reference audio URL for [S3] custom-voice cloning.","required":false,"metadata":{}},{"name":"voice_s4_audio_url","label":"Voice S4 Audio Url","type":"string","description":"Reference audio URL for [S4] custom-voice cloning.","required":false,"metadata":{}},{"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":"Reproducibility seed (string per upstream).","required":false,"metadata":{},"default":"42"},{"name":"output_format","label":"Output Format","type":"enum","description":"Output media file format (mp3, wav, mp4, png, jpg, etc., depending on the endpoint).","required":false,"metadata":{},"default":"mp3","options":["mp3","wav"]},{"name":"language","label":"Language","type":"string","description":"Forwarded to upstream (passthrough) so the podcast model can pick the right voice/dialect tier.","required":false,"metadata":{},"default":""}],"supported_endpoints":["POST /v1/audio/speech"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 1k characters","label":"Base","value":"$0.015"},{"spec":"per 1k characters","label":"Dialect","value":"$0.015"}],"limits":{"note":"Open-source voice model for long-form, multi-speaker podcast dialogue with paralinguistic control and zero-shot voice cloning."},"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","display_name":"Stable Audio 2.0","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"],"structured_output":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":"Output media file format (mp3, wav, mp4, png, jpg, etc., depending on the endpoint).","required":false,"metadata":{},"default":"mp3","options":["mp3","wav"]},{"name":"duration","label":"Duration","type":"number","description":"Seconds. Stability Audio 2.0 generates 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. Only used when random_seed=false.","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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per generation","label":"Base Cost","value":"$0.58"},{"spec":"per step","label":"Per Step Cost","value":"$0.00"}],"limits":{"note":"Generates up to 3 minutes 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","display_name":"Stable Audio 2.5","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"],"structured_output":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":"Output media file format (mp3, wav, mp4, png, jpg, etc., depending on the endpoint).","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":0.5,"min":0.01,"max":1},{"name":"mask_start","label":"Mask Start","type":"number","description":"Inpaint window start (seconds). Required for audio-inpaint.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"audio-inpaint"},"clear_when_hidden":true},"min":0,"max":190},{"name":"mask_end","label":"Mask End","type":"number","description":"Inpaint window end (seconds). Required for audio-inpaint.","required":false,"metadata":{"visible_when":{"op":"eq","field":"mode","value":"audio-inpaint"},"clear_when_hidden":true},"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. Only used when random_seed=false.","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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per generation","label":"Generation","value":"$0.68"}],"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","display_name":"SVI 2.0 Pro","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"],"structured_output":null,"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.","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 pipeline tier. 'quality' uses the Wan 2.2 plus reference image model for higher fidelity; 'fast' uses the flash model for cheaper, quicker generations. Only applies in text-to-video mode (image-to-video skips this step).","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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"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"}],"limits":{"note":"Theoretically infinite-length video with consistent character ID. 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","display_name":"Tavily Research","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"],"structured_output":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":"How citations are formatted in the answer (inline | footnote | bibliography).","required":false,"metadata":{},"default":"numbered","options":["numbered","mla","apa","chicago"]},{"name":"include_answer","label":"Include answer","type":"boolean","description":"When true, Tavily returns a synthesized answer alongside the source list.","required":false,"metadata":{},"default":true},{"name":"max_results","label":"Max results","type":"number","description":"Cap on the number of source documents Tavily returns.","required":false,"metadata":{},"default":5,"min":1,"max":20},{"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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"average per task","label":"Mini","value":"~$1.19"},{"spec":"average per task","label":"Pro","value":"~$2.75"}],"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","display_name":"Tavily Search","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"],"structured_output":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 | extract | crawl | map. Determines which Tavily endpoint runs.","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"]},{"name":"search_chunks_per_source","label":"Search Chunks Per Source","type":"number","description":"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":true},{"name":"include_raw_content","label":"Include Raw Content","type":"boolean","description":"Include the raw HTML content alongside cleaned text.","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.","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.","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.","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 (1-50).","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":10,"min":1,"max":500},{"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 | text | html).","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":false},{"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":60,"min":5,"max":300},{"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 | text | html).","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.","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":false},{"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":60,"min":5,"max":300},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Skip the EmpirioLabs Markdown formatting (Sources / Results / Code blocks added by the renderer). The raw upstream Tavily JSON is returned for power users / agents.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/search"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"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"}],"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","display_name":"Text Embedding v4","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"],"structured_output":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 texts to embed (max 10 entries, 8192 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 caller identifier (passed through to upstream).","required":false,"metadata":{}}],"supported_endpoints":["POST /v1/embeddings"],"pricing":{"prompt":"0.00000007","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.07"}],"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**Batch**\n\n- Up to 10 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","display_name":"Tongyi Embedding Vision Flash","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"],"structured_output":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":"Either 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"},"pricing_rows":[{"spec":"per 1M tokens","label":"Text input","value":"$0.09"},{"spec":"per 1M tokens","label":"Image / video input","value":"$0.03"}],"limits":{"note":"**Output**\n\n- Fixed 768-dim vector per input\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","display_name":"Tongyi Embedding Vision Plus","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"],"structured_output":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":"Either 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"},"pricing_rows":[{"spec":"per 1M tokens","label":"Text input","value":"$0.09"},{"spec":"per 1M tokens","label":"Image / video input","value":"$0.09"}],"limits":{"note":"**Output**\n\n- Fixed 1152-dim vector per input (no fusion across modalities)\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","display_name":"Wan 2.6","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"],"structured_output":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":"t2v: text-to-video. i2v: animate the attached image. r2v: reference-to-video — generate from a reference image.","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.","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 (1:1, 16:9, 9:16, 4:3, 3:2, etc.).","required":false,"metadata":{"ui":{"control":"segmented"}},"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.","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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"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)"}],"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\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**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\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**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","display_name":"Wan 2.7","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"],"structured_output":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.","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 audio from the reference video (videoedit/r2v 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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per second","label":"All Modes 720P","value":"$0.10"},{"spec":"per second","label":"All Modes 1080P","value":"$0.150"}],"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; 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; 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","display_name":"Wan2.7 Image","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"],"structured_output":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":"When true, a small Alibaba/Wan provenance watermark is stamped on each generated image. EmpirioLabs does not add any watermark of its own.","required":false,"metadata":{},"default":false},{"name":"response_format","label":"Response Format","type":"enum","description":"url (default) returns a signed URL; b64_json returns inline base64.","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"}],"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","display_name":"Whisper Large v3 Turbo","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"],"structured_output":null,"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 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":"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":"Strip per-segment timestamps from the response.","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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per minute of audio","label":"Controlled transcription","value":"$0.005 (was $0.006)"}],"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","display_name":"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"],"structured_output":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":"task_mode","label":"Task Mode","type":"enum","description":"Operating mode for the agent (default | research | coding | etc.).","required":false,"metadata":{},"default":"adaptive","options":["adaptive"]},{"name":"agent_profile","label":"Agent Profile","type":"enum","description":"Pre-built agent profile (e.g. analyst, researcher, coder) that tunes the system prompt and tools.","required":false,"metadata":{},"default":"manus-1.6","options":["manus-1.6","manus-1.6-lite","manus-1.6-max"]},{"name":"disable_formatting","label":"Disable Formatting","type":"boolean","description":"Skip the EmpirioLabs Markdown formatting around the Manus agent run. The raw upstream agent output is returned.","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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per task","label":"Adaptive - Manus 1.6 Lite","value":"$1.44 - $2.63"},{"spec":"per task","label":"Adaptive - Manus 1.6","value":"$2.89 - $5.25"},{"spec":"per task","label":"Adaptive - Manus 1.6 Max","value":"$5.25 - $9.19"}],"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-flash:variant1","object":"model","display_name":"DeepSeek V4 Flash (Variant 1)","provider":"deepseek","description":"Lightweight MoE model with 284B total / 13B active parameters and native 1M context, tuned for low-latency, cost-effective high-concurrency use.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","web_search"],"structured_output":"json_schema","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":true,"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.","required":false,"metadata":{},"default":4096,"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":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for the reasoning process. Up to 393216.","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":"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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable live web search. Adds a $0.02 surcharge 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-flash:variant1:generateContent"],"pricing":{"prompt":"0.0000002","completion":"0.0000004","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.20"},{"spec":"per 1M generated tokens","label":"Output","value":"$0.40"},{"spec":"per request when enabled","label":"Web search","value":"$0.02"}],"limits":null,"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=deepseek-v4-flash:variant1","api_url":"https://docs.empiriolabs.ai/models/deepseek-v4-flash#variant1","logo":"https://media.empiriolabs.ai/model-logos/deepseek.png","status":"available"},{"id":"deepseek-v4-pro:variant1","object":"model","display_name":"DeepSeek V4 Pro (Variant 1)","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"],"structured_output":"json_schema","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":true,"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.","required":false,"metadata":{},"default":4096,"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":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for the reasoning process. Up to 393216.","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":"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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Enable live web search. Adds a $0.02 surcharge 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"},"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"}],"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","display_name":"Grok Imagine Video 1.5","provider":"xai","description":"Image-to-video model that animates a source image with prompt-guided motion, up to 15 seconds at 480p or 720p across seven aspect ratios.","modality":"video","type":"generation","category":"video","category_label":null,"modality_label":null,"modalities":["video","text","image"],"input_modalities":["text","image"],"output_modalities":["video"],"features":["image_to_video","video_generation"],"structured_output":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":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":"Describe the motion and action to animate from the source image.","required":true,"metadata":{"ui":{"control":"textarea","section":"Input"}}},{"name":"image","label":"Image","type":"string","description":"Source image to animate. Public image URL, data URI, or uploaded image.","required":true,"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 faster, 720p is higher definition.","required":false,"metadata":{"ui":{"control":"segmented","section":"Generation"}},"default":"720p","options":["480p","720p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio. Defaults to the source image aspect ratio when omitted.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Generation"}},"options":["1:1","16:9","9:16","4:3","3:4","3:2","2:3"]}],"supported_endpoints":["POST /v1/videos/generations"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per image","label":"Image input","value":"$0.05"},{"spec":"per second","label":"480p","value":"$0.096"},{"spec":"per second","label":"720p","value":"$0.168"}],"limits":{"note":"Image-to-video model. Provide a source image and a prompt describing the motion to animate.\n\n**Defaults**\n\n- 10 second duration (1 to 15 seconds supported)\n- 720p output (480p or 720p)\n- Aspect ratio follows the source image unless set\n\n**Controls**\n\nSupports a source image (URL or upload), prompt, duration, resolution, and aspect ratio.\n\n**Billing**\n\n- Charged per second of generated video at the selected resolution (720p costs more per second than 480p), plus a per-source-image fee for the image you animate.\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":"Image-to-video model. Provide a source image and a prompt describing the motion to animate.\n\n**Defaults**\n\n- 10 second duration (1 to 15 seconds supported)\n- 720p output (480p or 720p)\n- Aspect ratio follows the source image unless set\n\n**Controls**\n\nSupports a source image (URL or upload), prompt, duration, resolution, and aspect ratio.\n\n**Billing**\n\n- Charged per second of generated video at the selected resolution (720p costs more per second than 480p), plus a per-source-image fee for the image you animate.\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":"mimo-v2-5-pro","object":"model","display_name":"MiMo V2.5 Pro","provider":"xiaomi","description":"Top-tier model for agentic workflows, complex software engineering, and long-horizon tasks, sustaining work across 1000+ tool calls on 1M context.","modality":"text","type":"chat","category":"text","category_label":null,"modality_label":null,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"features":["reasoning","agentic"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":128000,"model_released_at":"2026-04-27","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":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable extended thinking mode. Slower but improves reasoning-heavy tasks.","required":false,"metadata":{},"default":true},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Allow the model to perform web searches when needed.","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 keywords the model can use across web searches.","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 searches the model can perform per request.","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, 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 tokens in the response.","required":false,"metadata":{},"default":4096,"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":"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":"Skip the EmpirioLabs Markdown formatting (citation [[N]](url) rewriting + References block when web search was used). The raw upstream answer with plain [N] citations is returned.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/mimo-v2-5-pro:generateContent"],"pricing":{"prompt":"0.000002175","completion":"0.00000435","image":"0","request":"0","input_cache_read":"0.000000018"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$2.175"},{"spec":"per 1M generated tokens","label":"Output","value":"$4.35"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.018"},{"spec":"per request when enabled","label":"Web search","value":"$0.015"}],"limits":{"note":"Web search ($0.015/call) is charged only when invoked. Cached input tokens are billed at a steep discount. 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-v2-5-pro","api_url":"https://docs.empiriolabs.ai/models/mimo-v2-5-pro","logo":"https://media.empiriolabs.ai/model-logos/mimo-v2-5-pro.png","status":"available"},{"id":"mimo-v2-5","object":"model","display_name":"MiMo V2.5","provider":"xiaomi","description":"Multimodal model with native visual and audio understanding on a 1M context, designed to reason and act across modalities in agentic workflows.","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":["vision","audio_in"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":128000,"model_released_at":"2026-04-22","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":"enable_thinking","label":"Enable Thinking","type":"boolean","description":"Enable extended thinking mode. Slower but improves reasoning-heavy tasks.","required":false,"metadata":{},"default":true},{"name":"tool_web_search","label":"Web Search","type":"boolean","description":"Allow the model to perform web searches when needed.","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 keywords the model can use across web searches.","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 searches the model can perform per request.","required":false,"metadata":{"visible_when":{"op":"eq","field":"tool_web_search","value":true},"clear_when_hidden":true},"default":5,"min":1,"max":10},{"name":"video_fps","label":"Video Fps","type":"number","description":"Frames-per-second sampled from input video for analysis.","required":false,"metadata":{},"default":2,"min":0.1,"max":10},{"name":"video_resolution","label":"Video Resolution","type":"enum","description":"Resolution at which input video is sampled (e.g. 360p, 480p, 720p).","required":false,"metadata":{},"default":"default","options":["default","max"]},{"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 tokens in the response.","required":false,"metadata":{},"default":4096,"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":"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":"Skip the EmpirioLabs Markdown formatting (citation [[N]](url) rewriting + References block when web search was used). The raw upstream answer with plain [N] citations is returned.","required":false,"metadata":{},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/mimo-v2-5:generateContent"],"pricing":{"prompt":"0.0000007","completion":"0.0000014","image":"0","request":"0","input_cache_read":"0.000000014"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$0.70"},{"spec":"per 1M generated tokens","label":"Output","value":"$1.40"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.014"},{"spec":"per request when enabled","label":"Web search","value":"$0.015"}],"limits":{"note":"Omnimodal input (text, image, video, audio) with text output. Web search ($0.015/call) is charged only when invoked. Cached input tokens are billed at a steep discount.","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-v2-5","api_url":"https://docs.empiriolabs.ai/models/mimo-v2-5","logo":"https://media.empiriolabs.ai/model-logos/mimo-v2-5.png","status":"available"},{"id":"glm-5-2:variant1","object":"model","display_name":"GLM 5.2 (Variant 1)","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"],"structured_output":"json_schema","batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":131072,"model_released_at":"2026-06-16","is_new":true,"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, 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.","required":false,"metadata":{},"default":4096,"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":"thinking_budget","label":"Thinking Budget","type":"number","description":"Maximum tokens reserved for the reasoning process. Up to 131072.","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":131072},{"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. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service.","required":false,"metadata":{"ui":{"control":"segmented","section":"Model"},"translate_effort_to_budget":true},"default":"medium","options":["none","low","medium","high","max"]},{"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}],"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 request when enabled","label":"Web search","value":"$0.013"}],"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","display_name":"Kimi K2.7 Code (Variant 1)","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"],"structured_output":"none","batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"max_output_tokens":16384,"model_released_at":"2026-06-16","is_new":true,"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}],"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 request when enabled","label":"Web search","value":"$0.013"}],"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","display_name":"HappyHorse 1.1","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"],"structured_output":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":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":"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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per second","label":"720p","value":"$0.14"},{"spec":"per second","label":"1080p","value":"$0.18"}],"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","display_name":"Seedance 2.0 Mini","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"],"structured_output":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":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.","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":"Video generation resolution. Options are model-specific and sourced from the catalog.","required":false,"metadata":{},"default":"720p","options":["480p","720p"]},{"name":"aspect_ratio","label":"Aspect Ratio","type":"enum","description":"Output aspect ratio (1:1, 16:9, 9:16, 4:3, 3:2, etc.).","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.","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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"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"}],"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- Pair with Seedream 5.0 Lite for the reference image first when targeting lifelike-face cohesion across multiple inputs.\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- Pair with Seedream 5.0 Lite for the reference image first when targeting lifelike-face cohesion across multiple inputs.\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","display_name":"MiniMax M3 (Priority)","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":1000000,"context_length":1000000,"max_output_tokens":524288,"model_released_at":"2026-06-01","is_new":true,"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":"temperature","label":"Temperature","type":"number","description":"Controls randomness. Lower values are more deterministic; higher values are more exploratory.","required":false,"metadata":{"step":0.01,"control":"slider"},"default":1,"min":0,"max":2},{"name":"top_p","label":"Top P","type":"number","description":"Controls nucleus sampling by limiting generation to the most likely token mass.","required":false,"metadata":{"step":0.01,"control":"slider"},"default":0.95,"min":0,"max":1},{"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":"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":"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":{"ui":{"control":"toggle","section":"Tools"},"aliases":["web_search","linkup_web_search","tool_web_search_linkup"],"billing":{"source":"linkup_injector","price_per_search":0.013,"price_per_request":0.013},"powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"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":"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/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":"0.0000000675","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 (Linkup)","value":"$0.013"}],"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. Linkup web search is available through web_search_linkup and adds $0.013 per successful search."},"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","display_name":"Step 3.7 Flash","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"max_output_tokens":131072,"model_released_at":"2026-05-28","is_new":true,"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,"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":0,"max":1},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort for Step 3.7 Flash.","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":"Reasoning trace format returned by StepFun.","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":{"ui":{"control":"toggle","section":"Tools"},"group":"tools","aliases":["web_search","linkup_web_search","tool_web_search_linkup"],"powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"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"}],"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","display_name":"Step 3.5 Flash","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"],"structured_output":null,"batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"max_output_tokens":131072,"model_released_at":"2026-02-12","is_new":true,"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,"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":0,"max":1},{"name":"reasoning_format","label":"Reasoning Format","type":"enum","description":"Reasoning trace format returned by StepFun.","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":{"ui":{"control":"toggle","section":"Tools"},"group":"tools","aliases":["web_search","linkup_web_search","tool_web_search_linkup"],"powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"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"}],"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","display_name":"Step 3.5 Flash 2603","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"],"structured_output":null,"batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"max_output_tokens":131072,"model_released_at":"2026-04-02","is_new":true,"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,"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":0,"max":1},{"name":"reasoning_effort","label":"Reasoning Effort","type":"enum","description":"Reasoning effort for the agent-optimized Step 3.5 Flash 2603 route.","required":false,"metadata":{"ui":{"control":"segmented","section":"Reasoning"}},"default":"low","options":["low","high"]},{"name":"reasoning_format","label":"Reasoning Format","type":"enum","description":"Reasoning trace format returned by StepFun.","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":{"ui":{"control":"toggle","section":"Tools"},"group":"tools","aliases":["web_search","linkup_web_search","tool_web_search_linkup"],"powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"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"}],"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","display_name":"StepAudio 2.5 Chat","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"],"structured_output":"json_object","batch_supported":null,"batch_discount_pct":null,"context_window":256000,"context_length":256000,"max_output_tokens":131072,"model_released_at":null,"is_new":true,"is_featured":false,"discount":null,"capabilities":{"streaming":false,"system_prompt":false,"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,"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":0,"max":1},{"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":"Reasoning trace format returned by StepFun.","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":{"ui":{"control":"toggle","section":"Tools"},"group":"tools","aliases":["web_search","linkup_web_search","tool_web_search_linkup"],"powered_by":"linkup","addon_cost_usd":0.013,"gateway_injected":true},"default":false}],"supported_endpoints":["POST /v1/chat/completions","POST /v1/responses","POST /v1/messages","POST /v1beta/models/stepaudio-2-5-chat:generateContent"],"pricing":{"prompt":"0.00000143","completion":"0.00000357","image":"0","request":"0","input_cache_read":"0.00000029"},"pricing_rows":[{"spec":"per 1M prompt tokens","label":"Input","value":"$1.43"},{"spec":"per 1M generated tokens","label":"Output","value":"$3.57"},{"spec":"per 1M cached input tokens","label":"Implicit cache read","value":"$0.29"},{"spec":"per call when invoked","label":"Web Search (Linkup)","value":"$0.013"}],"limits":{"note":"Accepts text or base64 audio input and returns text. Linkup web search is available for text prompts. Public USD pricing is converted from StepFun official CNY pricing at 7 CNY per USD, matching the conversion basis used by StepFun English pricing rows."},"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":"step-image-edit-2","object":"model","display_name":"Step Image Edit 2","provider":"stepfun","description":"StepFun image generation and image editing model for text-to-image and single-image edits.","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"],"structured_output":null,"batch_supported":null,"batch_discount_pct":null,"context_window":null,"context_length":null,"max_output_tokens":null,"model_released_at":"2026-04-29","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":"prompt","label":"Prompt","type":"string","description":"Prompt or edit instruction. Maximum 512 characters.","required":true,"metadata":{"ui":{"control":"prompt","section":"Input"}},"max":512},{"name":"image","label":"Image","type":"string","description":"Reference image URL, data URI, or uploaded image. When present, image editing mode is used.","required":false,"metadata":{"ui":{"accept":"image/*","control":"file","section":"Input"}}},{"name":"images","label":"Images","type":"string","description":"Alias for image. StepFun Image Edit 2 currently uses one input image.","required":false,"metadata":{"ui":{"hidden":true}}},{"name":"size","label":"Size","type":"enum","description":"Output size.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Image"}},"default":"1024x1024","options":["1024x1024","768x1360","896x1184","1360x768","1184x896"]},{"name":"n","label":"Number of Images","type":"number","description":"Accepted for API compatibility. StepFun currently returns one image.","required":false,"metadata":{"ui":{"hidden":true}},"default":1,"min":1,"max":1},{"name":"response_format","label":"Response Format","type":"enum","description":"Return signed image URLs by default or include base64 image data.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Output"}},"default":"url","options":["url","b64_json"]},{"name":"seed","label":"Seed","type":"number","description":"Random seed for reproducible generation.","required":false,"metadata":{"ui":{"control":"number","section":"Advanced"}},"min":0,"max":2147483647},{"name":"steps","label":"Steps","type":"number","description":"Sampling steps.","required":false,"metadata":{"ui":{"step":1,"control":"slider","section":"Advanced"}},"default":8,"min":1,"max":50},{"name":"cfg_scale","label":"CFG Scale","type":"number","description":"Classifier-free guidance scale.","required":false,"metadata":{"ui":{"step":0.1,"control":"slider","section":"Advanced"}},"default":1,"min":1,"max":10},{"name":"negative_prompt","label":"Negative Prompt","type":"string","description":"Negative prompt. Maximum 512 characters.","required":false,"metadata":{"ui":{"control":"textarea","section":"Advanced"}},"max":512},{"name":"text_mode","label":"Text Mode","type":"boolean","description":"Enable text-focused rendering mode.","required":false,"metadata":{"ui":{"control":"toggle","section":"Advanced"}},"default":false}],"supported_endpoints":["POST /v1/images/generations","POST /v1/images/edits"],"pricing":{"prompt":"0","completion":"0","image":"0.003","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per generated image","label":"Output image","value":"$0.003"}],"limits":{"note":"Supports text-to-image and single-image editing. Prompt and negative_prompt are limited to 512 characters. Supported sizes are 1024x1024, 768x1360, 896x1184, 1360x768, and 1184x896. n is currently limited to 1.\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":"**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=step-image-edit-2","api_url":"https://docs.empiriolabs.ai/models/step-image-edit-2","logo":"https://media.empiriolabs.ai/model-logos/step-image-edit-2.png","status":"available"},{"id":"stepaudio-2-5-tts","object":"model","display_name":"StepAudio 2.5 TTS","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"],"structured_output":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":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. Maximum 1,000 characters.","required":true,"metadata":{"ui":{"control":"textarea","section":"Input"}},"max":1000},{"name":"voice","label":"Voice","type":"string","description":"Official voice ID or custom cloned voice ID.","required":false,"metadata":{"ui":{"control":"text_field","section":"Voice","placeholder":"lively-girl"}},"default":"lively-girl"},{"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","48000"]},{"name":"instruction","label":"Instruction","type":"string","description":"Global emotion or style guidance. Only supported by StepAudio 2.5 TTS.","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":"Filter markdown syntax before synthesis.","required":false,"metadata":{"ui":{"control":"toggle","section":"Advanced"}},"default":false}],"supported_endpoints":["POST /v1/audio/speech"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 10,000 characters","label":"Synthesis","value":"$0.85"}],"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":"step-tts-2","object":"model","display_name":"Step TTS 2","provider":"stepfun","description":"StepFun text-to-speech model with official voices, custom cloned voices, and voice tag controls.","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","voice_tags","multilingual"],"structured_output":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","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":"string","description":"Official voice ID or custom cloned voice ID.","required":false,"metadata":{"ui":{"control":"text_field","section":"Voice","placeholder":"lively-girl"}},"default":"lively-girl"},{"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","48000"]},{"name":"voice_label","label":"Voice Label","type":"string","description":"Emotion and speaking-style tags for step-tts-2.","required":false,"metadata":{"ui":{"control":"json","section":"Voice"}}},{"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":"Filter markdown syntax before synthesis.","required":false,"metadata":{"ui":{"control":"toggle","section":"Advanced"}},"default":false}],"supported_endpoints":["POST /v1/audio/speech"],"pricing":{"prompt":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per 10,000 characters","label":"Synthesis","value":"$0.40"}],"limits":{"note":"Maximum input is 1,000 characters. Supports official voice IDs, custom cloned voices, voice_label emotion tags, and voice_label style tags. The instruction parameter is only for stepaudio-2.5-tts."},"notes":null,"chat_url":"https://platform.empiriolabs.ai/dashboard/playground?model=step-tts-2","api_url":"https://docs.empiriolabs.ai/models/step-tts-2","logo":"https://media.empiriolabs.ai/model-logos/step-tts-2.png","status":"available"},{"id":"stepaudio-2-5-asr","object":"model","display_name":"StepAudio 2.5 ASR","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"],"structured_output":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":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":"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.","required":false,"metadata":{"ui":{"control":"toggle","section":"Recognition"}},"default":true},{"name":"enable_timestamp","label":"Enable Timestamps","type":"boolean","description":"Return timestamp fields from StepFun SSE events when available.","required":false,"metadata":{"ui":{"control":"toggle","section":"Recognition"}},"default":false},{"name":"format","label":"Format","type":"enum","description":"Audio container format.","required":false,"metadata":{"ui":{"control":"drop_down","section":"Format"}},"default":"wav","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":"0","completion":"0","image":"0","request":"0","input_cache_read":"0"},"pricing_rows":[{"spec":"per hour of audio","label":"Transcription","value":"$0.022"}],"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"}],"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"}],"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}],"catalog_version":"2.10.65","catalog_updated_at":"2026-07-09"}