{ "openapi": "3.1.0", "info": { "title": "MiniMax Responses API", "description": "MiniMax OpenAI Responses API 兼容接口，支持对话生成和 Token 估算", "license": { "name": "MIT" }, "version": "1.0.0" }, "servers": [ { "url": "https://api.minimax.cn" } ], "security": [ { "bearerAuth": [] } ], "paths": { "/v1/responses": { "post": { "summary": "对话生成", "operationId": "createResponse", "tags": [ "Responses" ], "parameters": [ { "name": "Content-Type", "in": "header", "required": true, "description": "请求体的媒介类型，请设置为 `application/json`，确保请求数据的格式为 JSON", "schema": { "type": "string", "enum": [ "application/json" ], "default": "application/json" } } ], "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/CreateResponseReq" }, "examples": { "深度思考": { "value": { "model": "MiniMax-M3.1-Flash", "reasoning": { "effort": "max" }, "input": "9.11 和 9.9 哪个更大？" } }, "图片理解": { "value": { "model": "MiniMax-M3.1-Flash", "reasoning": { "effort": "max" }, "input": [ { "role": "user", "content": [ { "type": "input_text", "text": "这张图片的内容是什么？" }, { "type": "input_image", "image_url": "https://filecdn.minimax.chat/public/fe9d04da-f60e-444d-a2e0-18ae743add33.jpeg" } ] } ] } }, "视频理解": { "value": { "model": "MiniMax-M3.1-Flash", "reasoning": { "effort": "max" }, "input": [ { "role": "user", "content": [ { "type": "input_text", "text": "这个视频里发生了什么？" }, { "type": "input_video", "video_url": "https://filecdn.minimax.chat/public/ee8c1648-21f1-41b7-8397-65022d22ffe5.mp4" } ] } ] } }, "流式": { "value": { "model": "MiniMax-M3.1-Flash", "reasoning": { "effort": "max" }, "input": [ { "role": "user", "content": [ { "type": "input_text", "text": "这张图片的内容是什么？" }, { "type": "input_image", "image_url": "https://filecdn.minimax.chat/public/fe9d04da-f60e-444d-a2e0-18ae743add33.jpeg" } ] } ], "stream": true } }, "工具调用": { "value": { "model": "MiniMax-M3.1-Flash", "reasoning": { "effort": "max" }, "input": "旧金山现在天气怎么样？", "tools": [ { "type": "function", "name": "get_weather", "description": "Get the current weather for a given location.", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state/country, e.g. San Francisco, US" } }, "required": [ "location" ] } } ] } } } } }, "required": true }, "responses": { "200": { "description": "成功响应", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/CreateResponseResp" }, "examples": { "深度思考": { "value": { "id": "07229fa4ff19f5b74ad4581cad3af46c", "object": "response", "created_at": 1792240804, "model": "MiniMax-M3.1-Flash", "status": "completed", "output": [ { "id": "07229fa4ff19f5b74ad4581cad3af46c_rs", "type": "reasoning", "status": "completed", "summary": [], "content": [ { "type": "reasoning_text", "text": "We need answer Chinese. Need determine 9.11 vs 9.9. Decimal comparison: 9.9 = 9.90 > 9.11. User asks which larger. Need concise maybe explain. Ensure not date ambiguity? They ask 9.11 and 9.9 likely decimals. Answer 9.9 larger. Chinese." } ] }, { "id": "07229fa4ff19f5b74ad4581cad3af46c_msg", "type": "message", "status": "completed", "role": "assistant", "content": [ { "type": "output_text", "text": "9.9 更大。\n\n因为把小数位补齐：9.9 = 9.90，而 9.90 > 9.11。", "annotations": [] } ] } ], "output_text": "9.9 更大。\n\n因为把小数位补齐：9.9 = 9.90，而 9.90 > 9.11。", "usage": { "input_tokens": 216, "output_tokens": 107, "total_tokens": 323, "input_tokens_details": { "cached_tokens": 189 }, "output_tokens_details": { "reasoning_tokens": 75 } }, "error": null, "incomplete_details": null, "instructions": null, "metadata": {}, "tools": null, "tool_choice": "auto", "temperature": 1, "top_p": 0.95, "text": { "format": { "type": "text" } }, "reasoning": { "effort": "max", "summary": null }, "max_output_tokens": null, "parallel_tool_calls": true, "previous_response_id": null, "conversation": null, "store": false, "service_tier": null, "safety_identifier": null, "truncation": "disabled" } }, "图片理解": { "value": { "id": "07229fa4f4b7aa2578eef43416353b1e", "object": "response", "created_at": 1792240804, "model": "MiniMax-M3.1-Flash", "status": "completed", "output": [ { "id": "07229fa4f4b7aa2578eef43416353b1e_rs", "type": "reasoning", "status": "completed", "summary": [], "content": [ { "type": "reasoning_text", "text": "We need answer Chinese. Need describe image. We can identify generic child, no sensitive. Need maybe mention close-up portrait of young girl smiling, curly brown hair bangs, green/hazel eyes, white lace dress, warm soft lighting, blurred brown-gray background. Since user asks content. Need concise. Ensure not infer identity. Let's craft." } ] }, { "id": "07229fa4f4b7aa2578eef43416353b1e_msg", "type": "message", "status": "completed", "role": "assistant", "content": [ { "type": "output_text", "text": "这是一张小女孩的暖调人像特写。她留着棕色卷发和齐刘海，睁着绿色或棕绿色的眼睛，面带微笑，身穿带蕾丝领口和肩部装饰的白色连衣裙。背景呈柔和的棕灰色虚化，光线温暖自然。", "annotations": [] } ] } ], "output_text": "这是一张小女孩的暖调人像特写。她留着棕色卷发和齐刘海，睁着绿色或棕绿色的眼睛，面带微笑，身穿带蕾丝领口和肩部装饰的白色连衣裙。背景呈柔和的棕灰色虚化，光线温暖自然。", "usage": { "input_tokens": 1407, "output_tokens": 127, "total_tokens": 1534, "input_tokens_details": { "cached_tokens": 1405 }, "output_tokens_details": { "reasoning_tokens": 70 } }, "error": null, "incomplete_details": null, "instructions": null, "metadata": {}, "tools": null, "tool_choice": "auto", "temperature": 1, "top_p": 0.95, "text": { "format": { "type": "text" } }, "reasoning": { "effort": "max", "summary": null }, "max_output_tokens": null, "parallel_tool_calls": true, "previous_response_id": null, "conversation": null, "store": false, "service_tier": null, "safety_identifier": null, "truncation": "disabled" } }, "视频理解": { "value": { "id": "07229fa44741487d6937e3789ea56819", "object": "response", "created_at": 1792240804, "model": "MiniMax-M3.1-Flash", "status": "completed", "output": [ { "id": "07229fa44741487d6937e3789ea56819_rs", "type": "reasoning", "status": "completed", "summary": [], "content": [ { "type": "reasoning_text", "text": "We need answer in Chinese likely describe video. Need inspect sequence. We have frames 0-5.5 sec. It's a generated/edited video perhaps cat in Olympic diving venue, running along diving board/platform, leaps into pool, splash. Need accurately state. Let's parse details.\n\nAt 0: cat (Asian? wildcat-looking domestic cat, spotted/striped) walking on narrow turquoise diving board/beam over pool in Olympic stadium. Background Olympic rings, crowds, purple signage \"Lausanne 2024\" perhaps. Camera tracks as cat runs. At ~2.5 sec cat leaps, paws extended, flying over diving platform, rotates/dives headfirst into pool around 4 sec, splash at 4.5, ripples. Need mention no visible injury perhaps. User asks \"这个视频里发生了什么？\" likely concise Chinese description. We should avoid overclaiming exact venue/competition or whether real. Say video depicts a cat walking/running along diving platform in an Olympic-themed swimming/diving arena, then jumps and dives into pool causing splash, ending with ripples. Maybe note it appears AI-generated due image/video artifacts/watermarks MiniMax/Hailuo AI. Should we mention? Could be useful but not needed. Need answer natural.\n\nLet's formulate: \"视频中，一只带斑纹的猫在类似奥运会跳水馆的跳板/池边窄台上向前奔跑，背景有奥运五环和观众。跑到尽头后纵身跃起，身体在空中翻转，随后头朝下扎入泳池，激起大片水花；最后水面只剩涟漪和逐渐消散的水花。\" Maybe if question wants event summary. Include duration ~5.5 sec. Need perhaps mention cat lands in diving pool, not necessarily headfirst? Frame 3.5 body vertical head down, yes.\n\nLet's answer Chinese." } ] }, { "id": "07229fa44741487d6937e3789ea56819_msg", "type": "message", "status": "completed", "role": "assistant", "content": [ { "type": "output_text", "text": "视频里，一只带斑纹的猫沿着奥运跳水馆池边的窄平台向前奔跑，背景有奥运五环和观众。跑到尽头后，它纵身跃起，在空中翻转后头朝下跳入泳池，激起一大片水花，最后水面只剩下逐渐扩散的涟漪。", "annotations": [] } ] } ], "output_text": "视频里，一只带斑纹的猫沿着奥运跳水馆池边的窄平台向前奔跑，背景有奥运五环和观众。跑到尽头后，它纵身跃起，在空中翻转后头朝下跳入泳池，激起一大片水花，最后水面只剩下逐渐扩散的涟漪。", "usage": { "input_tokens": 2285, "output_tokens": 430, "total_tokens": 2715, "input_tokens_details": { "cached_tokens": 2283 }, "output_tokens_details": { "reasoning_tokens": 369 } }, "error": null, "incomplete_details": null, "instructions": null, "metadata": {}, "tools": null, "tool_choice": "auto", "temperature": 1, "top_p": 0.95, "text": { "format": { "type": "text" } }, "reasoning": { "effort": "max", "summary": null }, "max_output_tokens": null, "parallel_tool_calls": true, "previous_response_id": null, "conversation": null, "store": false, "service_tier": null, "safety_identifier": null, "truncation": "disabled" } }, "流式": { "value": [ { "type": "response.created", "sequence_number": 0, "response": { "id": "07229fa479c585e3683008175f57bd8f", "object": "response", "created_at": 1792240804, "model": "MiniMax-M3.1-Flash", "status": "in_progress", "output": [], "output_text": null, "usage": null, "error": null, "incomplete_details": null, "instructions": null, "metadata": {}, "tools": null, "tool_choice": "auto", "temperature": 1, "top_p": 0.95, "text": { "format": { "type": "text" } }, "reasoning": { "effort": "max", "summary": null }, "max_output_tokens": null, "parallel_tool_calls": true, "previous_response_id": null, "conversation": null, "store": false, "service_tier": null, "safety_identifier": null, "truncation": "disabled" } }, { "type": "response.in_progress", "sequence_number": 1, "response": { "id": "07229fa479c585e3683008175f57bd8f", "object": "response", "created_at": 1792240804, "model": "MiniMax-M3.1-Flash", "status": "in_progress", "output": [], "output_text": null, "usage": null, "error": null, "incomplete_details": null, "instructions": null, "metadata": {}, "tools": null, "tool_choice": "auto", "temperature": 1, "top_p": 0.95, "text": { "format": { "type": "text" } }, "reasoning": { "effort": "max", "summary": null }, "max_output_tokens": null, "parallel_tool_calls": true, "previous_response_id": null, "conversation": null, "store": false, "service_tier": null, "safety_identifier": null, "truncation": "disabled" } }, { "type": "response.output_item.added", "sequence_number": 2, "item": { "id": "07229fa479c585e3683008175f57bd8f_rs", "type": "reasoning", "status": "in_progress", "summary": [], "content": [] }, "output_index": 0 }, { "type": "response.content_part.added", "sequence_number": 3, "part": { "type": "reasoning_text", "text": "" }, "output_index": 0, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_rs" }, { "type": "response.reasoning_text.delta", "sequence_number": 4, "output_index": 0, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_rs", "delta": "We need answer" }, { "type": "response.reasoning_text.delta", "sequence_number": 5, "output_index": 0, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_rs", "delta": " Chinese describe image. Need be careful child, identity unknown. Need content: close-up portrait of young girl, brown" }, { "type": "response.reasoning_text.delta", "sequence_number": 6, "output_index": 0, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_rs", "delta": " wavy hair bangs, looking camera slight smile, cream lace dress, warm golden light, neutral blurred" }, { "type": "response.reasoning_text.delta", "sequence_number": 7, "output_index": 0, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_rs", "delta": " background. We should not infer ethnicity perhaps. concise. Maybe mention eyes green/hazel. Need answer in" }, { "type": "response.reasoning_text.delta", "sequence_number": 8, "output_index": 0, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_rs", "delta": " Chinese." }, { "type": "response.reasoning_text.done", "sequence_number": 9, "output_index": 0, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_rs", "text": "We need answer Chinese describe image. Need be careful child, identity unknown. Need content: close-up portrait of young girl, brown wavy hair bangs, looking camera slight smile, cream lace dress, warm golden light, neutral blurred background. We should not infer ethnicity perhaps. concise. Maybe mention eyes green/hazel. Need answer in Chinese." }, { "type": "response.content_part.done", "sequence_number": 10, "part": { "type": "reasoning_text", "text": "We need answer Chinese describe image. Need be careful child, identity unknown. Need content: close-up portrait of young girl, brown wavy hair bangs, looking camera slight smile, cream lace dress, warm golden light, neutral blurred background. We should not infer ethnicity perhaps. concise. Maybe mention eyes green/hazel. Need answer in Chinese." }, "output_index": 0, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_rs" }, { "type": "response.output_item.done", "sequence_number": 11, "item": { "id": "07229fa479c585e3683008175f57bd8f_rs", "type": "reasoning", "status": "completed", "summary": [], "content": [ { "type": "reasoning_text", "text": "We need answer Chinese describe image. Need be careful child, identity unknown. Need content: close-up portrait of young girl, brown wavy hair bangs, looking camera slight smile, cream lace dress, warm golden light, neutral blurred background. We should not infer ethnicity perhaps. concise. Maybe mention eyes green/hazel. Need answer in Chinese." } ] }, "output_index": 0 }, { "type": "response.output_item.added", "sequence_number": 12, "item": { "type": "message", "status": "in_progress", "role": "assistant", "content": [], "id": "07229fa479c585e3683008175f57bd8f_msg_1" }, "output_index": 1 }, { "type": "response.content_part.added", "sequence_number": 13, "part": { "type": "output_text", "text": "", "annotations": [] }, "output_index": 1, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_msg_1" }, { "type": "response.output_text.delta", "sequence_number": 14, "output_index": 1, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_msg_1", "delta": "这是一张小女孩的暖色调肖像特写。她留着棕色卷发" }, { "type": "response.output_text.delta", "sequence_number": 15, "output_index": 1, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_msg_1", "delta": "和齐刘海，穿着带蕾丝边的米白色连衣裙，微微笑着看向镜头。画面" }, { "type": "response.output_text.delta", "sequence_number": 16, "output_index": 1, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_msg_1", "delta": "采用柔和的侧光与浅景深，背景呈棕灰色虚化，整体温馨" }, { "type": "response.output_text.delta", "sequence_number": 17, "output_index": 1, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_msg_1", "delta": "自然。" }, { "type": "response.output_text.done", "sequence_number": 18, "output_index": 1, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_msg_1", "text": "这是一张小女孩的暖色调肖像特写。她留着棕色卷发和齐刘海，穿着带蕾丝边的米白色连衣裙，微微笑着看向镜头。画面采用柔和的侧光与浅景深，背景呈棕灰色虚化，整体温馨自然。" }, { "type": "response.content_part.done", "sequence_number": 19, "part": { "type": "output_text", "text": "这是一张小女孩的暖色调肖像特写。她留着棕色卷发和齐刘海，穿着带蕾丝边的米白色连衣裙，微微笑着看向镜头。画面采用柔和的侧光与浅景深，背景呈棕灰色虚化，整体温馨自然。", "annotations": [] }, "output_index": 1, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_msg_1" }, { "type": "response.output_item.done", "sequence_number": 20, "item": { "id": "07229fa479c585e3683008175f57bd8f_msg_1", "type": "message", "status": "completed", "role": "assistant", "content": [ { "type": "output_text", "text": "这是一张小女孩的暖色调肖像特写。她留着棕色卷发和齐刘海，穿着带蕾丝边的米白色连衣裙，微微笑着看向镜头。画面采用柔和的侧光与浅景深，背景呈棕灰色虚化，整体温馨自然。", "annotations": [] } ] }, "output_index": 1 }, { "type": "response.completed", "sequence_number": 21, "response": { "id": "07229fa479c585e3683008175f57bd8f", "object": "response", "created_at": 1792240804, "model": "MiniMax-M3.1-Flash", "status": "completed", "output": [ { "id": "07229fa479c585e3683008175f57bd8f_rs", "type": "reasoning", "status": "completed", "summary": [], "content": [ { "type": "reasoning_text", "text": "We need answer Chinese describe image. Need be careful child, identity unknown. Need content: close-up portrait of young girl, brown wavy hair bangs, looking camera slight smile, cream lace dress, warm golden light, neutral blurred background. We should not infer ethnicity perhaps. concise. Maybe mention eyes green/hazel. Need answer in Chinese." } ] }, { "id": "07229fa479c585e3683008175f57bd8f_msg_1", "type": "message", "status": "completed", "role": "assistant", "content": [ { "type": "output_text", "text": "这是一张小女孩的暖色调肖像特写。她留着棕色卷发和齐刘海，穿着带蕾丝边的米白色连衣裙，微微笑着看向镜头。画面采用柔和的侧光与浅景深，背景呈棕灰色虚化，整体温馨自然。", "annotations": [] } ] } ], "output_text": "这是一张小女孩的暖色调肖像特写。她留着棕色卷发和齐刘海，穿着带蕾丝边的米白色连衣裙，微微笑着看向镜头。画面采用柔和的侧光与浅景深，背景呈棕灰色虚化，整体温馨自然。", "usage": { "input_tokens": 1407, "output_tokens": 121, "total_tokens": 1528, "input_tokens_details": { "cached_tokens": 1405 }, "output_tokens_details": { "reasoning_tokens": 70 } }, "error": null, "incomplete_details": null, "instructions": null, "metadata": {}, "tools": null, "tool_choice": "auto", "temperature": 1, "top_p": 0.95, "text": { "format": { "type": "text" } }, "reasoning": { "effort": "max", "summary": null }, "max_output_tokens": null, "parallel_tool_calls": true, "previous_response_id": null, "conversation": null, "store": false, "service_tier": null, "safety_identifier": null, "truncation": "disabled" } } ] }, "工具调用": { "value": { "id": "07229fa434e87bfb6278664eb2616841", "object": "response", "created_at": 1792240804, "model": "MiniMax-M3.1-Flash", "status": "completed", "output": [ { "id": "07229fa434e87bfb6278664eb2616841_rs", "type": "reasoning", "status": "completed", "summary": [], "content": [ { "type": "reasoning_text", "text": "The user asks in Chinese: \"What's the current weather in San Francisco?\" I should call the weather tool." } ] }, { "id": "07229fa434e87bfb6278664eb2616841_fc_0", "type": "function_call", "status": "completed", "call_id": "call_function_f5xolsmpgj3i_1", "name": "get_weather", "arguments": "{\"location\": \"San Francisco, US\"}" } ], "output_text": null, "usage": { "input_tokens": 463, "output_tokens": 54, "total_tokens": 517, "input_tokens_details": { "cached_tokens": 229 }, "output_tokens_details": { "reasoning_tokens": 24 } }, "error": null, "incomplete_details": null, "instructions": null, "metadata": {}, "tools": [ { "type": "function", "name": "get_weather", "description": "Get the current weather for a given location.", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state/country, e.g. San Francisco, US" } }, "required": [ "location" ] } } ], "tool_choice": "auto", "temperature": 1, "top_p": 0.95, "text": { "format": { "type": "text" } }, "reasoning": { "effort": "max", "summary": null }, "max_output_tokens": null, "parallel_tool_calls": true, "previous_response_id": null, "conversation": null, "store": false, "service_tier": null, "safety_identifier": null, "truncation": "disabled" } } } }, "text/event-stream": { "schema": { "type": "object", "description": "流式响应（SSE）。每个事件的 `data` 为 JSON，`type` 字段标识事件类型。" }, "examples": { "流式": { "value": [ { "type": "response.created", "sequence_number": 0, "response": { "id": "07229fa479c585e3683008175f57bd8f", "object": "response", "created_at": 1792240804, "model": "MiniMax-M3.1-Flash", "status": "in_progress", "output": [], "output_text": null, "usage": null, "error": null, "incomplete_details": null, "instructions": null, "metadata": {}, "tools": null, "tool_choice": "auto", "temperature": 1, "top_p": 0.95, "text": { "format": { "type": "text" } }, "reasoning": { "effort": "max", "summary": null }, "max_output_tokens": null, "parallel_tool_calls": true, "previous_response_id": null, "conversation": null, "store": false, "service_tier": null, "safety_identifier": null, "truncation": "disabled" } }, { "type": "response.in_progress", "sequence_number": 1, "response": { "id": "07229fa479c585e3683008175f57bd8f", "object": "response", "created_at": 1792240804, "model": "MiniMax-M3.1-Flash", "status": "in_progress", "output": [], "output_text": null, "usage": null, "error": null, "incomplete_details": null, "instructions": null, "metadata": {}, "tools": null, "tool_choice": "auto", "temperature": 1, "top_p": 0.95, "text": { "format": { "type": "text" } }, "reasoning": { "effort": "max", "summary": null }, "max_output_tokens": null, "parallel_tool_calls": true, "previous_response_id": null, "conversation": null, "store": false, "service_tier": null, "safety_identifier": null, "truncation": "disabled" } }, { "type": "response.output_item.added", "sequence_number": 2, "item": { "id": "07229fa479c585e3683008175f57bd8f_rs", "type": "reasoning", "status": "in_progress", "summary": [], "content": [] }, "output_index": 0 }, { "type": "response.content_part.added", "sequence_number": 3, "part": { "type": "reasoning_text", "text": "" }, "output_index": 0, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_rs" }, { "type": "response.reasoning_text.delta", "sequence_number": 4, "output_index": 0, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_rs", "delta": "We need answer" }, { "type": "response.reasoning_text.delta", "sequence_number": 5, "output_index": 0, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_rs", "delta": " Chinese describe image. Need be careful child, identity unknown. Need content: close-up portrait of young girl, brown" }, { "type": "response.reasoning_text.delta", "sequence_number": 6, "output_index": 0, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_rs", "delta": " wavy hair bangs, looking camera slight smile, cream lace dress, warm golden light, neutral blurred" }, { "type": "response.reasoning_text.delta", "sequence_number": 7, "output_index": 0, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_rs", "delta": " background. We should not infer ethnicity perhaps. concise. Maybe mention eyes green/hazel. Need answer in" }, { "type": "response.reasoning_text.delta", "sequence_number": 8, "output_index": 0, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_rs", "delta": " Chinese." }, { "type": "response.reasoning_text.done", "sequence_number": 9, "output_index": 0, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_rs", "text": "We need answer Chinese describe image. Need be careful child, identity unknown. Need content: close-up portrait of young girl, brown wavy hair bangs, looking camera slight smile, cream lace dress, warm golden light, neutral blurred background. We should not infer ethnicity perhaps. concise. Maybe mention eyes green/hazel. Need answer in Chinese." }, { "type": "response.content_part.done", "sequence_number": 10, "part": { "type": "reasoning_text", "text": "We need answer Chinese describe image. Need be careful child, identity unknown. Need content: close-up portrait of young girl, brown wavy hair bangs, looking camera slight smile, cream lace dress, warm golden light, neutral blurred background. We should not infer ethnicity perhaps. concise. Maybe mention eyes green/hazel. Need answer in Chinese." }, "output_index": 0, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_rs" }, { "type": "response.output_item.done", "sequence_number": 11, "item": { "id": "07229fa479c585e3683008175f57bd8f_rs", "type": "reasoning", "status": "completed", "summary": [], "content": [ { "type": "reasoning_text", "text": "We need answer Chinese describe image. Need be careful child, identity unknown. Need content: close-up portrait of young girl, brown wavy hair bangs, looking camera slight smile, cream lace dress, warm golden light, neutral blurred background. We should not infer ethnicity perhaps. concise. Maybe mention eyes green/hazel. Need answer in Chinese." } ] }, "output_index": 0 }, { "type": "response.output_item.added", "sequence_number": 12, "item": { "type": "message", "status": "in_progress", "role": "assistant", "content": [], "id": "07229fa479c585e3683008175f57bd8f_msg_1" }, "output_index": 1 }, { "type": "response.content_part.added", "sequence_number": 13, "part": { "type": "output_text", "text": "", "annotations": [] }, "output_index": 1, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_msg_1" }, { "type": "response.output_text.delta", "sequence_number": 14, "output_index": 1, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_msg_1", "delta": "这是一张小女孩的暖色调肖像特写。她留着棕色卷发" }, { "type": "response.output_text.delta", "sequence_number": 15, "output_index": 1, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_msg_1", "delta": "和齐刘海，穿着带蕾丝边的米白色连衣裙，微微笑着看向镜头。画面" }, { "type": "response.output_text.delta", "sequence_number": 16, "output_index": 1, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_msg_1", "delta": "采用柔和的侧光与浅景深，背景呈棕灰色虚化，整体温馨" }, { "type": "response.output_text.delta", "sequence_number": 17, "output_index": 1, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_msg_1", "delta": "自然。" }, { "type": "response.output_text.done", "sequence_number": 18, "output_index": 1, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_msg_1", "text": "这是一张小女孩的暖色调肖像特写。她留着棕色卷发和齐刘海，穿着带蕾丝边的米白色连衣裙，微微笑着看向镜头。画面采用柔和的侧光与浅景深，背景呈棕灰色虚化，整体温馨自然。" }, { "type": "response.content_part.done", "sequence_number": 19, "part": { "type": "output_text", "text": "这是一张小女孩的暖色调肖像特写。她留着棕色卷发和齐刘海，穿着带蕾丝边的米白色连衣裙，微微笑着看向镜头。画面采用柔和的侧光与浅景深，背景呈棕灰色虚化，整体温馨自然。", "annotations": [] }, "output_index": 1, "content_index": 0, "item_id": "07229fa479c585e3683008175f57bd8f_msg_1" }, { "type": "response.output_item.done", "sequence_number": 20, "item": { "id": "07229fa479c585e3683008175f57bd8f_msg_1", "type": "message", "status": "completed", "role": "assistant", "content": [ { "type": "output_text", "text": "这是一张小女孩的暖色调肖像特写。她留着棕色卷发和齐刘海，穿着带蕾丝边的米白色连衣裙，微微笑着看向镜头。画面采用柔和的侧光与浅景深，背景呈棕灰色虚化，整体温馨自然。", "annotations": [] } ] }, "output_index": 1 }, { "type": "response.completed", "sequence_number": 21, "response": { "id": "07229fa479c585e3683008175f57bd8f", "object": "response", "created_at": 1792240804, "model": "MiniMax-M3.1-Flash", "status": "completed", "output": [ { "id": "07229fa479c585e3683008175f57bd8f_rs", "type": "reasoning", "status": "completed", "summary": [], "content": [ { "type": "reasoning_text", "text": "We need answer Chinese describe image. Need be careful child, identity unknown. Need content: close-up portrait of young girl, brown wavy hair bangs, looking camera slight smile, cream lace dress, warm golden light, neutral blurred background. We should not infer ethnicity perhaps. concise. Maybe mention eyes green/hazel. Need answer in Chinese." } ] }, { "id": "07229fa479c585e3683008175f57bd8f_msg_1", "type": "message", "status": "completed", "role": "assistant", "content": [ { "type": "output_text", "text": "这是一张小女孩的暖色调肖像特写。她留着棕色卷发和齐刘海，穿着带蕾丝边的米白色连衣裙，微微笑着看向镜头。画面采用柔和的侧光与浅景深，背景呈棕灰色虚化，整体温馨自然。", "annotations": [] } ] } ], "output_text": "这是一张小女孩的暖色调肖像特写。她留着棕色卷发和齐刘海，穿着带蕾丝边的米白色连衣裙，微微笑着看向镜头。画面采用柔和的侧光与浅景深，背景呈棕灰色虚化，整体温馨自然。", "usage": { "input_tokens": 1407, "output_tokens": 121, "total_tokens": 1528, "input_tokens_details": { "cached_tokens": 1405 }, "output_tokens_details": { "reasoning_tokens": 70 } }, "error": null, "incomplete_details": null, "instructions": null, "metadata": {}, "tools": null, "tool_choice": "auto", "temperature": 1, "top_p": 0.95, "text": { "format": { "type": "text" } }, "reasoning": { "effort": "max", "summary": null }, "max_output_tokens": null, "parallel_tool_calls": true, "previous_response_id": null, "conversation": null, "store": false, "service_tier": null, "safety_identifier": null, "truncation": "disabled" } } ] } } } } } } } }, "/v1/responses/input_tokens": { "post": { "summary": "Token 估算", "operationId": "estimateInputTokens", "tags": [ "Responses" ], "parameters": [ { "name": "Content-Type", "in": "header", "required": true, "description": "请求体的媒介类型，请设置为 `application/json`，确保请求数据的格式为 JSON", "schema": { "type": "string", "enum": [ "application/json" ], "default": "application/json" } } ], "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/EstimateInputTokensReq" }, "examples": { "Request": { "value": { "model": "MiniMax-M3.1-Flash", "input": "请帮我写一封邮件，邀请团队成员参加下周三下午 3 点的项目复盘会议，说明会议议程，并提醒大家提前准备各自负责模块的进展总结和遇到的问题。" } } } } }, "required": true }, "responses": { "200": { "description": "成功响应", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/EstimateInputTokensResp" }, "examples": { "Response": { "value": { "object": "response.input_tokens", "input_tokens": 235 } } } } } } } } } }, "components": { "schemas": { "CreateResponseReq": { "type": "object", "required": ["model", "input"], "properties": { "model": { "type": "string", "description": "调用的模型名称，如 `MiniMax-M3.1-Flash`", "example": "MiniMax-M3.1-Flash" }, "service_tier": { "type": "string", "description": "请求准入服务层级。支持的取值为 `standard` 和 `priority`。省略时默认使用 `standard`。`priority` 的[价格](https://platform.minimax.cn/docs/pricing/overview#models/text)为 `standard` 的 1.5 倍，并会确保请求获得优先准入，使其排在其他请求之前处理，从而带来更快响应并减少失败。`MiniMax-M3.1-Flash` 不支持该字段。", "enum": [ "standard", "priority" ], "default": "standard" }, "input": { "description": "对话内容，支持简单文本或完整对话历史数组", "oneOf": [ { "type": "string", "description": "简单文本输入" }, { "type": "array", "description": "完整对话历史", "items": { "$ref": "#/components/schemas/InputItem" } } ] }, "instructions": { "type": "string", "description": "系统指令" }, "max_output_tokens": { "type": "integer", "description": "最大输出 token 数。推理 token 也计入此上限，设置过小会导致 `status` 为 `incomplete` 且 `output` 中没有 `message` 项。" }, "temperature": { "type": "number", "format": "float", "description": "暂不支持指定，传入的值不会生效。`MiniMax-M3.1-Flash` 和 `MiniMax-M3` 固定使用 1。", "default": 1 }, "top_p": { "type": "number", "format": "float", "description": "暂不支持指定，传入的值不会生效。`MiniMax-M3.1-Flash` 和 `MiniMax-M3` 固定使用 0.95。若传入，取值需在 (0, 1] 范围内。", "default": 0.95, "minimum": 0, "maximum": 1 }, "stream": { "type": "boolean", "description": "设置为 `true` 启用 SSE 流式响应", "default": false }, "tools": { "type": "array", "description": "工具列表", "items": { "$ref": "#/components/schemas/Tool" } }, "tool_choice": { "type": "string", "enum": ["auto"], "description": "工具选择策略：`auto` 表示由模型自动判断是否调用工具" }, "metadata": { "type": "object", "description": "请求元数据，key-value 均为字符串", "additionalProperties": { "type": "string" } }, "prompt_cache_key": { "type": "string", "description": "Prompt 缓存路由标识" }, "text": { "type": "object", "description": "输出格式控制", "properties": { "format": { "type": "object", "properties": { "type": { "type": "string", "enum": ["text"], "default": "text", "description": "输出格式类型" } } } } }, "reasoning": { "type": "object", "description": "推理控制。默认值随模型不同，因此未在 schema 层声明统一默认值。\n- `MiniMax-M3.1-Flash`：推理始终开启，省略 `reasoning` 时也会推理。`effort` 可取 `low`、`medium`、`high`、`xhigh` 或 `max`，并且确实会调节推理深度；省略时默认使用 `max` 档位。传入 `effort: \"none\"` 会返回 HTTP 400。\n- `MiniMax-M3`：默认关闭推理；将 `effort` 设为非 `none` 值可开启推理，但不会调节推理深度。\n- M2.x 模型：推理无法关闭，传入 `effort: \"none\"` 会被接收但不生效。", "properties": { "effort": { "type": "string", "enum": ["minimal", "low", "medium", "high", "xhigh", "max", "none"] } }, "required": [] } } }, "InputItem": { "type": "object", "description": "对话历史条目。`type` 字段决定具体形态：`message`（默认）/ `function_call` / `function_call_output` / `reasoning`", "properties": { "type": { "type": "string", "enum": ["message", "function_call", "function_call_output", "reasoning"], "default": "message", "description": "条目类型" }, "role": { "type": "string", "enum": ["user", "assistant", "system", "developer", "tool"], "description": "消息角色（仅当 `type` 为 `message` 时使用）" }, "content": { "description": "消息内容，可以是字符串或多模态片段数组（仅当 `type` 为 `message` 时使用）", "oneOf": [ {"type": "string"}, {"type": "array", "items": {"$ref": "#/components/schemas/ContentPart"}} ] }, "call_id": { "type": "string", "description": "工具调用 ID（仅当 `type` 为 `function_call` 或 `function_call_output` 时使用）" }, "name": { "type": "string", "description": "函数名（仅当 `type` 为 `function_call` 时使用）" }, "arguments": { "type": "string", "description": "函数参数的 JSON 字符串（仅当 `type` 为 `function_call` 时使用）" }, "output": { "description": "工具返回结果（仅当 `type` 为 `function_call_output` 时使用）", "oneOf": [ {"type": "string"}, {"type": "array", "items": {"$ref": "#/components/schemas/ContentPart"}} ] }, "summary": { "type": "array", "description": "思维链段落数组（仅当 `type` 为 `reasoning` 时使用）", "items": { "type": "object", "properties": { "type": { "type": "string", "enum": ["summary_text"] }, "text": { "type": "string", "description": "思维链文本" } } } } } }, "ContentPart": { "type": "object", "required": ["type"], "description": "消息内容片段", "properties": { "type": { "type": "string", "enum": ["input_text", "output_text", "input_image", "input_video"], "description": "内容片段类型：\n- `input_text` / `output_text`: 文本片段\n- `input_image`: 图片输入\n- `input_video`: 视频输入" }, "text": { "type": "string", "description": "文本内容（当 `type` 为 `input_text` / `output_text` 时）" }, "image_url": { "description": "图片输入（当 `type` 为 `input_image` 时）。支持的格式：JPEG、PNG、GIF、WEBP", "oneOf": [ {"type": "string"}, { "type": "object", "required": ["url"], "properties": { "url": { "type": "string", "description": "图片链接或 Base64 编码" }, "detail": { "type": "string", "enum": ["low", "default", "high"], "default": "default", "description": "图片理解的精细度档位" } } } ] }, "video_url": { "description": "视频输入（当 `type` 为 `input_video` 时）。支持的格式：MP4、AVI、MOV、MKV", "oneOf": [ {"type": "string"}, { "type": "object", "required": ["url"], "properties": { "url": { "type": "string", "description": "视频链接或 Base64 编码，大文件建议使用 File API 上传" }, "fps": { "type": "number", "format": "float", "default": 1, "minimum": 0.2, "maximum": 5, "description": "抽帧频率" }, "detail": { "type": "string", "enum": ["low", "default", "high"], "default": "default", "description": "视频理解的精细度档位" }, "max_long_side_pixel": { "type": "integer", "description": "视频帧最长边的像素约束" } } } ] } } }, "Tool": { "type": "object", "required": ["type", "name"], "properties": { "type": { "type": "string", "enum": ["function"], "description": "工具类型" }, "name": { "type": "string", "description": "函数名称" }, "description": { "type": "string", "description": "函数说明，用于模型判断何时调用" }, "parameters": { "type": "object", "description": "函数参数定义，使用 JSON Schema 格式" } } }, "CreateResponseResp": { "type": "object", "properties": { "id": { "type": "string", "description": "响应 ID", "example": "abc123" }, "object": { "type": "string", "enum": ["response"], "description": "对象类型，固定为 `response`" }, "created_at": { "type": "integer", "description": "响应创建时间（Unix 秒）" }, "model": { "type": "string", "description": "实际处理请求的模型名称", "example": "MiniMax-M3.1-Flash" }, "status": { "type": "string", "enum": ["completed", "incomplete", "failed"], "description": "响应状态" }, "output": { "type": "array", "description": "模型输出列表", "items": { "$ref": "#/components/schemas/OutputItem" } }, "output_text": { "type": "string", "nullable": true, "description": "便捷字段：所有文本输出拼接后的结果" }, "usage": { "$ref": "#/components/schemas/Usage" }, "error": { "type": "object", "nullable": true, "description": "错误信息，仅在 `status=failed` 时返回", "properties": { "code": { "type": "string", "description": "错误码" }, "message": { "type": "string", "description": "人类可读的错误描述" } } }, "incomplete_details": { "type": "object", "nullable": true, "description": "未完成原因，仅在 `status=incomplete` 时返回", "properties": { "reason": { "type": "string", "enum": ["max_output_tokens", "content_filter"] } } }, "parallel_tool_calls": { "type": "boolean", "description": "请求中暂不支持该参数，传入后将被忽略，响应中固定返回 **`true`**。" }, "store": { "type": "boolean", "description": "请求中暂不支持该参数，传入后将被忽略，响应中固定返回 **`false`**。" }, "truncation": { "type": "string", "enum": ["disabled"], "description": "请求中暂不支持该参数，传入后将被忽略，响应中固定返回 **`disabled`**。" }, "previous_response_id": { "type": "string", "nullable": true, "description": "请求中暂不支持该参数，传入后将被忽略，响应中固定返回 **`null`**。" }, "conversation": { "type": "object", "nullable": true, "description": "请求中暂不支持该参数，传入后将被忽略，响应中固定返回 **`null`**。" }, "service_tier": { "type": "string", "nullable": true, "description": "本次请求实际生效的服务层级，取值为 `standard` 或 `priority`。`MiniMax-M3.1-Flash` 不支持该字段，响应中返回 **`null`**。" }, "safety_identifier": { "type": "string", "nullable": true, "description": "请求中暂不支持该参数，传入后将被忽略，响应中固定返回 **`null`**。" } } }, "OutputItem": { "oneOf": [ { "title": "Message", "type": "object", "properties": { "id": { "type": "string", "description": "`_msg` 格式" }, "type": { "type": "string", "enum": ["message"] }, "status": { "type": "string", "enum": ["completed"] }, "role": { "type": "string", "enum": ["assistant"] }, "content": { "type": "array", "items": { "type": "object", "properties": { "type": { "type": "string", "enum": ["output_text"] }, "text": { "type": "string", "description": "模型生成的文本" }, "annotations": { "type": "array", "description": "引用标注" } } } } } }, { "title": "Reasoning", "type": "object", "description": "思维链输出（仅开启推理时返回）", "properties": { "id": { "type": "string", "description": "`_rs` 格式" }, "type": { "type": "string", "enum": ["reasoning"] }, "status": { "type": "string", "enum": ["completed"] }, "summary": { "type": "array", "description": "思维链摘要" }, "content": { "type": "array", "items": { "type": "object", "properties": { "type": { "type": "string", "enum": ["reasoning_text"] }, "text": { "type": "string", "description": "思维链文本" } } } } } }, { "title": "Function Call", "type": "object", "description": "工具调用", "properties": { "id": { "type": "string", "description": "`_fc_` 格式" }, "type": { "type": "string", "enum": ["function_call"] }, "status": { "type": "string", "enum": ["completed"] }, "call_id": { "type": "string", "description": "工具调用 ID，用于关联 `function_call_output`" }, "name": { "type": "string", "description": "函数名称" }, "arguments": { "type": "string", "description": "函数参数的 JSON 字符串" } } } ] }, "Usage": { "type": "object", "properties": { "input_tokens": { "type": "integer", "description": "输入 token 数" }, "input_tokens_details": { "type": "object", "properties": { "cached_tokens": { "type": "integer", "description": "Prompt 缓存命中的 token 数" } } }, "output_tokens": { "type": "integer", "description": "输出 token 数" }, "output_tokens_details": { "type": "object", "properties": { "reasoning_tokens": { "type": "integer", "description": "思维链消耗的 token 数（仅开启推理时计入）" } } }, "total_tokens": { "type": "integer", "description": "总 token 数" } } }, "EstimateInputTokensReq": { "type": "object", "required": ["model", "input"], "properties": { "model": { "type": "string", "description": "调用的模型名称，如 `MiniMax-M3.1-Flash`", "example": "MiniMax-M3.1-Flash" }, "input": { "description": "对话内容，支持简单文本或完整对话历史数组", "oneOf": [ { "type": "string", "description": "简单文本输入" }, { "type": "array", "description": "完整对话历史", "items": { "$ref": "#/components/schemas/InputItem" } } ] }, "instructions": { "type": "string", "description": "系统指令" }, "tools": { "type": "array", "description": "工具列表", "items": { "$ref": "#/components/schemas/Tool" } }, "tool_choice": { "type": "string", "enum": ["auto"], "description": "工具选择策略：`auto` 表示由模型自动判断是否调用工具" }, "text": { "type": "object", "description": "输出格式控制", "properties": { "format": { "type": "object", "properties": { "type": { "type": "string", "enum": ["text"], "default": "text", "description": "输出格式类型" } } } } }, "reasoning": { "type": "object", "description": "推理控制。默认值随模型不同，因此未在 schema 层声明统一默认值。\n- `MiniMax-M3.1-Flash`：推理始终开启，省略 `reasoning` 时也会推理。`effort` 可取 `low`、`medium`、`high`、`xhigh` 或 `max`，并且确实会调节推理深度；省略时默认使用 `max` 档位。传入 `effort: \"none\"` 会返回 HTTP 400。\n- `MiniMax-M3`：默认关闭推理；将 `effort` 设为非 `none` 值可开启推理，但不会调节推理深度。\n- M2.x 模型：推理无法关闭，传入 `effort: \"none\"` 会被接收但不生效。", "properties": { "effort": { "type": "string", "enum": ["minimal", "low", "medium", "high", "xhigh", "max", "none"] } }, "required": [] } } }, "EstimateInputTokensResp": { "type": "object", "required": ["object", "input_tokens"], "properties": { "object": { "type": "string", "enum": ["response.input_tokens"], "description": "对象类型，固定为 `response.input_tokens`" }, "input_tokens": { "type": "integer", "description": "估算的输入 token 数" } } } }, "securitySchemes": { "bearerAuth": { "type": "http", "scheme": "bearer", "bearerFormat": "JWT", "description": "`HTTP: Bearer Auth`\n - Security Scheme Type: http\n - HTTP Authorization Scheme: Bearer API_key，用于验证账户信息，可在 [账户管理>接口密钥](https://platform.minimax.cn/user-center/basic-information/interface-key) 中查看" } } } }