{ "openapi": "3.1.0", "info": { "title": "MiniMax Text API Anthropic", "description": "MiniMax text generation API with support for chat completion and streaming output.\n\n> ⚡ **`MiniMax-M3.1-Flash` highlights** — **1M long context**, **multimodal**, and **tunable thinking depth**.\n", "license": { "name": "MIT" }, "version": "1.0.0" }, "servers": [ { "url": "https://api.minimax.io" } ], "security": [ { "bearerAuth": [] }, { "apiKeyAuth": [] } ], "paths": { "/anthropic/v1/messages": { "post": { "summary": "Text Generation Anthropic", "operationId": "chatCompletionAnthropic", "tags": [ "Text Generation" ], "parameters": [ { "name": "Content-Type", "in": "header", "required": true, "description": "Media type of the request body, should be set to `application/json` to ensure JSON format", "schema": { "type": "string", "enum": [ "application/json" ], "default": "application/json" } } ], "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/CreateMessageReq" }, "examples": { "Deep Thinking": { "value": { "model": "MiniMax-M3.1-Flash", "thinking": { "type": "adaptive" }, "messages": [ { "role": "user", "content": "Which is bigger, 9.11 or 9.9?" } ], "max_tokens": 4096, "output_config": { "effort": "max" } } }, "Image Understanding": { "value": { "model": "MiniMax-M3.1-Flash", "thinking": { "type": "adaptive" }, "messages": [ { "role": "user", "content": [ { "type": "text", "text": "What does this image show?" }, { "type": "image", "source": { "type": "url", "url": "https://filecdn.minimax.chat/public/fe9d04da-f60e-444d-a2e0-18ae743add33.jpeg" } } ] } ], "max_tokens": 4096, "output_config": { "effort": "max" } } }, "Video Understanding": { "value": { "model": "MiniMax-M3.1-Flash", "thinking": { "type": "adaptive" }, "messages": [ { "role": "user", "content": [ { "type": "text", "text": "What is happening in this video?" }, { "type": "video", "source": { "type": "url", "url": "https://filecdn.minimax.chat/public/ee8c1648-21f1-41b7-8397-65022d22ffe5.mp4" } } ] } ], "max_tokens": 4096, "output_config": { "effort": "max" } } }, "Stream": { "value": { "model": "MiniMax-M3.1-Flash", "thinking": { "type": "adaptive" }, "messages": [ { "role": "user", "content": [ { "type": "text", "text": "What does this image show?" }, { "type": "image", "source": { "type": "url", "url": "https://filecdn.minimax.chat/public/fe9d04da-f60e-444d-a2e0-18ae743add33.jpeg" } } ] } ], "stream": true, "max_tokens": 4096, "output_config": { "effort": "max" } } }, "Tool Use": { "value": { "model": "MiniMax-M3.1-Flash", "messages": [ { "role": "user", "content": "How's the weather in San Francisco?" } ], "max_tokens": 4096, "tools": [ { "name": "get_weather", "description": "Get the current weather for a given location.", "input_schema": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state/country, e.g. San Francisco, US" } }, "required": [ "location" ] } } ], "tool_choice": { "type": "auto" }, "output_config": { "effort": "max" } } } } } }, "required": true }, "responses": { "200": { "description": "", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/CreateMessageResp" }, "examples": { "Deep Thinking": { "value": { "id": "066b367ba949a58a9d6829b4bf8cbcd4", "type": "message", "role": "assistant", "model": "MiniMax-M3.1-Flash", "content": [ { "thinking": "The user is asking which is bigger, 9.11 or 9.9.\n\n9.11 vs 9.9\n\n9.9 is greater than 9.11.\n\nTo compare: 9.11 = 9.11 and 9.9 = 9.90\n\n9.90 > 9.11, so 9.9 is bigger.", "signature": "6d0315c818f9664ff185dabaa22cd89f2bf28a3a52122095bce23d905471ec5f", "type": "thinking" }, { "text": "**9.9 is bigger than 9.11.**\n\nTo compare decimals, it helps to write them with the same number of decimal places:\n- 9.11 = 9.11\n- 9.9 = 9.90\n\nSince 9.90 > 9.11, **9.9 is larger**.", "type": "text" } ], "usage": { "input_tokens": 13, "output_tokens": 149, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 159 }, "stop_reason": "end_turn" } }, "Image Understanding": { "value": { "id": "066a3730f92943410551c4b4978ddad1", "type": "message", "role": "assistant", "model": "MiniMax-M3.1-Flash", "content": [ { "thinking": "The user is asking what the image shows. I can describe this image of a young child.", "signature": "db8ecae1e5a63cabebd69d2625983499bb498bfd329dde5c3cede76f12896336", "type": "thinking" }, { "text": "This image shows a young girl, probably around 4-5 years old, photographed in a close-up portrait style. She has:\n\n- **Wavy, tousled light brown hair** with bangs that fall across her forehead, with some strands appearing slightly messy or windblown\n- **Large, expressive hazel-green eyes** that are looking directly at the camera\n- **A soft, subtle smile** giving her a warm, gentle expression\n- **Fair skin** with rosy cheeks, illuminated by warm, soft lighting\n\nShe's wearing what appears to be a **cream or off-white dress** with delicate lace or ruffled detailing around the neckline and shoulders.\n\nThe photograph has a **professional portrait quality**, with a softly blurred, neutral grayish-beige background and warm directional lighting that creates a classic, painterly aesthetic. The composition and styling suggest this could be a formal portrait or an AI-generated image with a vintage/realistic photographic style.", "type": "text" } ], "usage": { "input_tokens": 1209, "output_tokens": 214, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 157 }, "stop_reason": "end_turn" } }, "Video Understanding": { "value": { "id": "066b458956dd2902de31eae19cf15c6e", "type": "message", "role": "assistant", "model": "MiniMax-M3.1-Flash", "content": [ { "thinking": "The user wants to know what is happening in the video.\n\n1. **Analyze the video:**\n * The video is a meme/edited clip.\n * It starts with a cat (specifically a Bengal cat, looks like a Savannah cat or similar breed) walking on a diving board at the Olympics (London 2012).\n * The cat is edited into the scene, replacing a human diver.\n * The cat walks to the end of the board.\n * The cat then jumps off the diving board into the pool.\n * The people in the background are real, reacting (or rather, just sitting there, as it's a static crowd image or very slow movement).\n * The text \"MINIMAX | Hailuo AI\" is visible, indicating it's an AI-generated video.\n\n2. **Describe the action:**\n * A cat walks on a diving board.\n * The cat jumps off the diving board.\n * The setting is an Olympic-sized pool.\n\n3. **Synthesize the description:**\n * Start with the main subject: a cat.\n * Describe the location: a diving board at a swimming pool.\n * Describe the action: walking, then jumping off.\n * Combine into a concise sentence: \"A cat is seen walking on a diving board and then jumping off into a swimming pool.\"\n\n4. **Review against the video:**\n * Does the video show a cat? Yes.\n * Does it show a diving board? Yes.\n * Does the cat jump off? Yes.\n * Is there a swimming pool below? Yes.\n * The description is accurate and covers the key events in the short clip.\n\n5. **Final Output Generation:** Present the synthesized description clearly.", "signature": "4849e0d596e25f03504dbb4eee7316fc48714dc86b93c9b7dd63adef7f4aa9b2", "type": "thinking" }, { "text": "A cat is seen walking on a diving board and then jumping off into a swimming pool.", "type": "text" } ], "usage": { "input_tokens": 349, "output_tokens": 393, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 1896 }, "stop_reason": "end_turn" } }, "Stream": { "value": [ { "type": "message_start", "message": { "id": "066a3766d21ce23c8afc5e85a427036c", "type": "message", "role": "assistant", "content": [], "model": "MiniMax-M3.1-Flash", "stop_reason": null, "stop_sequence": null, "usage": { "input_tokens": 0, "output_tokens": 0, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 1366 }, "service_tier": "standard" } }, { "type": "ping" }, { "type": "content_block_start", "index": 0, "content_block": { "type": "thinking", "thinking": "" } }, { "type": "content_block_delta", "index": 0, "delta": { "type": "thinking_delta", "thinking": "The user" } }, { "type": "content_block_delta", "index": 0, "delta": { "type": "thinking_delta", "thinking": " is asking me to describe what an image shows. I should describe the image objectively, focusing on" } }, { "type": "content_block_delta", "index": 0, "delta": { "type": "thinking_delta", "thinking": " visible features without identifying the person." } }, { "type": "content_block_delta", "index": 0, "delta": { "type": "signature_delta", "signature": "69b031ac42358c4e99f8f80f5ea48ff9cec06ca68500428ee1145e16a8020843" } }, { "type": "content_block_stop", "index": 0 }, { "type": "content_block_start", "index": 1, "content_block": { "type": "text", "text": "" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": "The image shows a close-up portrait of a young girl" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": ", probably around 3-5 years old. She has the following features:\n\n- **Hair" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": "**: Wavy, light brown/auburn hair with bangs across her forehead, with some" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": " strands appearing to be pulled up\n- **Eyes**: Large, expressive brown/amber eyes looking" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": " directly at the camera\n- **Expression**: A subtle, closed-mouth smile that gives her a gentle" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": ", slightly mischievous look\n- **Clothing**: She's wearing a white or cream-colored top with delicate" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": " lace or ruffled trim around the neckline and sleeves\n- **Lighting**: The photo uses" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": " warm, soft lighting that creates a gentle glow on her face\n- **Background**: A muted, neutral" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": " brownish-gray backdrop that keeps the focus entirely on her\n\nThe overall aesthetic has" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": " a professional, portrait-photography quality with a warm, vintage feel to the color tones" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": "." } }, { "type": "content_block_stop", "index": 1 }, { "type": "message_delta", "delta": { "stop_reason": "end_turn" }, "usage": { "input_tokens": 1252, "output_tokens": 213, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 114 } }, { "type": "message_stop" } ] }, "Tool Use": { "value": { "id": "066b133406cd8cfd88eb3b2b893a5daa", "type": "message", "role": "assistant", "model": "MiniMax-M3.1-Flash", "content": [ { "thinking": "The user is asking about the weather in San Francisco. I have access to a get_weather tool that can provide this information. I need to format the location parameter appropriately - the example shows \"San Francisco, US\" as the format.", "signature": "fa86efec7c27d4aa23eac60ba7a1f4e5f0f37a18d6ec4944fe495aebb6bd0930", "type": "thinking" }, { "text": "I'll check the current weather in San Francisco for you.", "type": "text" }, { "type": "tool_use", "id": "call_function_9pjh8jjdebck_1", "name": "get_weather", "input": { "location": "San Francisco, US" } } ], "usage": { "input_tokens": 14, "output_tokens": 91, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 404 }, "stop_reason": "tool_use" } } } }, "text/event-stream": { "schema": { "$ref": "#/components/schemas/StreamEvent" }, "examples": { "Stream": { "value": [ { "type": "message_start", "message": { "id": "066a3766d21ce23c8afc5e85a427036c", "type": "message", "role": "assistant", "content": [], "model": "MiniMax-M3.1-Flash", "stop_reason": null, "stop_sequence": null, "usage": { "input_tokens": 0, "output_tokens": 0, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 1366 }, "service_tier": "standard" } }, { "type": "ping" }, { "type": "content_block_start", "index": 0, "content_block": { "type": "thinking", "thinking": "" } }, { "type": "content_block_delta", "index": 0, "delta": { "type": "thinking_delta", "thinking": "The user" } }, { "type": "content_block_delta", "index": 0, "delta": { "type": "thinking_delta", "thinking": " is asking me to describe what an image shows. I should describe the image objectively, focusing on" } }, { "type": "content_block_delta", "index": 0, "delta": { "type": "thinking_delta", "thinking": " visible features without identifying the person." } }, { "type": "content_block_delta", "index": 0, "delta": { "type": "signature_delta", "signature": "69b031ac42358c4e99f8f80f5ea48ff9cec06ca68500428ee1145e16a8020843" } }, { "type": "content_block_stop", "index": 0 }, { "type": "content_block_start", "index": 1, "content_block": { "type": "text", "text": "" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": "The image shows a close-up portrait of a young girl" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": ", probably around 3-5 years old. She has the following features:\n\n- **Hair" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": "**: Wavy, light brown/auburn hair with bangs across her forehead, with some" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": " strands appearing to be pulled up\n- **Eyes**: Large, expressive brown/amber eyes looking" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": " directly at the camera\n- **Expression**: A subtle, closed-mouth smile that gives her a gentle" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": ", slightly mischievous look\n- **Clothing**: She's wearing a white or cream-colored top with delicate" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": " lace or ruffled trim around the neckline and sleeves\n- **Lighting**: The photo uses" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": " warm, soft lighting that creates a gentle glow on her face\n- **Background**: A muted, neutral" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": " brownish-gray backdrop that keeps the focus entirely on her\n\nThe overall aesthetic has" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": " a professional, portrait-photography quality with a warm, vintage feel to the color tones" } }, { "type": "content_block_delta", "index": 1, "delta": { "type": "text_delta", "text": "." } }, { "type": "content_block_stop", "index": 1 }, { "type": "message_delta", "delta": { "stop_reason": "end_turn" }, "usage": { "input_tokens": 1252, "output_tokens": 213, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 114 } }, { "type": "message_stop" } ] } } } } }, "400": { "description": "Invalid request parameters (missing required fields, type not in the whitelist, tool_use.input not a JSON object, etc.).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "type": "error", "request_id": "req_xxxxxxxx", "error": { "type": "invalid_request_error", "message": "messages.0.content.1: unsupported content type 'foo'" } } } } }, "401": { "description": "API key missing or invalid.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "type": "error", "request_id": "req_xxxxxxxx", "error": { "type": "authentication_error", "message": "API key missing or invalid." } } } } }, "403": { "description": "No permission to access this model or path.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "type": "error", "request_id": "req_xxxxxxxx", "error": { "type": "permission_error", "message": "No permission to access this model or path." } } } } }, "404": { "description": "Model does not exist.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "type": "error", "request_id": "req_xxxxxxxx", "error": { "type": "not_found_error", "message": "Model does not exist." } } } } }, "413": { "description": "Request body exceeds 64 MB, or a multimodal file exceeds the size limit.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "type": "error", "request_id": "req_xxxxxxxx", "error": { "type": "request_too_large", "message": "Request body exceeds 64 MB, or a multimodal file exceeds the size limit." } } } } }, "429": { "description": "RPM / TPM / connection-count or other rate limit triggered.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "type": "error", "request_id": "req_xxxxxxxx", "error": { "type": "rate_limit_error", "message": "RPM / TPM / connection-count or other rate limit triggered." } } } } }, "500": { "description": "Internal server error.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "type": "error", "request_id": "req_xxxxxxxx", "error": { "type": "api_error", "message": "Internal server error." } } } } }, "529": { "description": "Upstream model overloaded; retryable.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "type": "error", "request_id": "req_xxxxxxxx", "error": { "type": "overloaded_error", "message": "Upstream model overloaded; retryable." } } } } } } } }, "/anthropic/v1/messages/count_tokens": { "post": { "summary": "Count Tokens Anthropic", "operationId": "countTokensAnthropic", "tags": [ "Text Generation" ], "parameters": [ { "name": "Content-Type", "in": "header", "required": true, "description": "Media type of the request body, should be set to `application/json` to ensure JSON format", "schema": { "type": "string", "enum": [ "application/json" ], "default": "application/json" } } ], "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/CreateMessageReq" }, "examples": { "Request": { "value": { "model": "MiniMax-M3.1-Flash", "messages": [ { "role": "user", "content": "Hello" } ] } } } } }, "required": true }, "responses": { "200": { "description": "Returns input token usage for the request without generating model output.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/CountTokensResp" }, "examples": { "Request": { "value": { "usage": { "input_tokens": 3, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0 } } } } } } } } } } }, "components": { "schemas": { "CreateMessageReq": { "type": "object", "required": [ "model", "messages" ], "properties": { "model": { "type": "string", "description": "Model ID. `MiniMax-M3.1-Flash` and `MiniMax-M3` are multimodal models with native support for text, image, and video input, alongside tool use and thinking content blocks. `MiniMax-M3.1-Flash` additionally always thinks and supports tunable thinking depth via `output_config.effort`.", "enum": [ "MiniMax-M3.1-Flash", "MiniMax-M3" ] }, "service_tier": { "type": "string", "description": "Service tier for request admission. Supported values are `standard` and `priority`. If omitted, the request uses the `standard` tier. The `priority` [price](https://platform.minimax.io/docs/pricing/overview#models/text) is 1.5 times the `standard` price and ensures priority admission so the request is processed ahead of other requests, leading to faster responses and fewer failures. `MiniMax-M3.1-Flash` does not support this field.", "enum": [ "standard", "priority" ], "default": "standard" }, "system": { "description": "Set the role and behavior of the model.", "oneOf": [ { "type": "string", "description": "Plain text system prompt" }, { "type": "array", "description": "System prompt in content block array format. Text blocks can include cache_control (not supported by MiniMax-M3 or MiniMax-M3.1-Flash).", "items": { "type": "object", "properties": { "type": { "type": "string", "enum": [ "text" ], "description": "Content block type" }, "text": { "type": "string", "description": "Text content" }, "cache_control": { "$ref": "#/components/schemas/CacheControl" } }, "required": [ "type", "text" ] } } ] }, "messages": { "type": "array", "description": "Conversation history. `MiniMax-M3.1-Flash` and `MiniMax-M3` support text, image, video, tool use, tool result, and thinking content blocks. The M2.7, M2.5, M2.1, and M2 series support text and tool-call content blocks only; they do not support image or video input.", "items": { "$ref": "#/components/schemas/Message" } }, "stream": { "type": "boolean", "description": "Whether to use streaming output, defaults to `false`. When set to `true`, the response will be returned in chunks", "default": false }, "max_tokens": { "type": "integer", "format": "int64", "description": "Specifies the upper limit for generated content length (in tokens). For MiniMax-M3.1-Flash and MiniMax-M3 the recommended value is 131072 (128K) and the maximum is 524288 (512K); for other models the recommended value is 65536 (64K) and the maximum is 204800 (200K). Content exceeding the limit will be truncated. If generation stops due to `length`, try increasing this value", "minimum": 1 }, "temperature": { "type": "number", "format": "double", "description": "Temperature coefficient, affects output randomness. Range [0, 2], default 1. Higher values produce more random output; lower values produce more deterministic output.", "minimum": 0, "maximum": 2, "default": 1 }, "top_p": { "type": "number", "format": "double", "description": "Nucleus sampling parameter. Range [0, 1]. Default is 0.95 for MiniMax-M3.1-Flash and MiniMax-M3, and 0.9 for M2.x models.", "minimum": 0, "maximum": 1, "default": 0.95 }, "tools": { "type": "array", "description": "Tool definitions for Anthropic-compatible tool use.", "items": { "$ref": "#/components/schemas/Tool" } }, "tool_choice": { "$ref": "#/components/schemas/ToolChoice" }, "thinking": { "type": "object", "description": "Controls thinking behavior. The default depends on the model, so no schema-level default is declared.\n- `MiniMax-M3.1-Flash`: always thinks. If `type` is sent it must be `adaptive`; `disabled` returns HTTP 400. Use `output_config.effort` to tune thinking depth.\n- `MiniMax-M3`: thinking is off when `thinking` is omitted; send `adaptive` to enable it and return thinking blocks.\n- M2.x models: thinking cannot be disabled; `disabled` is accepted but ignored.", "properties": { "type": { "type": "string", "enum": [ "disabled", "adaptive" ], "description": "Thinking control type.\n- `disabled`: turns off thinking output for `MiniMax-M3`. Rejected with HTTP 400 by `MiniMax-M3.1-Flash`; accepted but ignored by M2.x models.\n- `adaptive`: enables thinking output and returns thinking blocks. The only value accepted by `MiniMax-M3.1-Flash`." } }, "required": [] }, "output_config": { "type": "object", "description": "Output configuration. Use `effort` to tune thinking depth for `MiniMax-M3.1-Flash`.", "properties": { "effort": { "type": "string", "description": "Thinking depth for `MiniMax-M3.1-Flash`. Accepts `low`, `medium`, `high`, `xhigh`, or `max`; defaults to `max` when omitted. Other models ignore this field. `none` is not supported for `MiniMax-M3.1-Flash` and returns HTTP 400.", "enum": [ "low", "medium", "high", "xhigh", "max" ] } }, "required": [] }, "metadata": { "type": "object", "description": "Request metadata. user_id is recommended for end-user-level aggregation, rate limiting, and billing analysis.", "properties": { "user_id": { "type": "string", "description": "End-user ID." } } } } }, "CreateMessageResp": { "type": "object", "properties": { "id": { "type": "string", "description": "Unique ID of this response" }, "type": { "type": "string", "description": "Object type, fixed as `message`", "enum": [ "message" ] }, "role": { "type": "string", "description": "Role, fixed as `assistant`", "enum": [ "assistant" ] }, "model": { "type": "string", "description": "Model ID used for this request" }, "content": { "type": "array", "description": "List of response content blocks", "items": { "$ref": "#/components/schemas/ResponseContentBlock" } }, "stop_reason": { "type": "string", "description": "Reason for stopping generation:\n- end_turn: Model ended naturally\n- max_tokens: Reached max_tokens limit\n- tool_use: Model requested tool use", "enum": [ "end_turn", "max_tokens", "tool_use" ] }, "usage": { "$ref": "#/components/schemas/Usage" } } }, "Message": { "type": "object", "required": [ "role", "content" ], "properties": { "role": { "type": "string", "enum": [ "user", "assistant", "user_system", "group", "sample_message_user", "sample_message_ai" ], "description": "Role of the message sender. `MiniMax-M3.1-Flash` and `MiniMax-M3` use alternating user / assistant messages." }, "content": { "description": "Message content. `MiniMax-M3.1-Flash` and `MiniMax-M3` support text, image, video, tool use, tool result, and thinking content blocks.", "oneOf": [ { "type": "string", "description": "Plain text message" }, { "type": "array", "description": "Message content. `MiniMax-M3.1-Flash` and `MiniMax-M3` support text, image, video, tool use, tool result, and thinking content blocks.", "items": { "$ref": "#/components/schemas/RequestContentBlock" } } ] } } }, "RequestContentBlock": { "type": "object", "description": "Content block accepted in request messages. text and tool blocks are supported by all models; image and video blocks are supported by `MiniMax-M3.1-Flash` and `MiniMax-M3` only. thinking is only used when echoing a prior assistant turn back to the model.", "required": [ "type" ], "properties": { "type": { "type": "string", "description": "Content block type:\n- text: Text content\n- image: Image input, `MiniMax-M3.1-Flash` and `MiniMax-M3` only\n- video: Video input, `MiniMax-M3.1-Flash` and `MiniMax-M3` only\n- tool_use: Echoed assistant tool call from a previous turn\n- tool_result: Tool execution result\n- thinking: Echoed assistant thinking from a previous turn\n- mid_conv_system: System instructions inserted mid-conversation", "enum": [ "text", "image", "video", "tool_use", "tool_result", "thinking", "mid_conv_system" ] }, "text": { "type": "string", "description": "Text content when type=text." }, "source": { "$ref": "#/components/schemas/MediaSource", "description": "Image or video source when type=image or type=video. `MiniMax-M3.1-Flash` and `MiniMax-M3` only." }, "id": { "type": "string", "description": "Tool call ID when echoing type=tool_use." }, "name": { "type": "string", "description": "Tool name when echoing type=tool_use." }, "input": { "type": "object", "description": "Tool input when echoing type=tool_use." }, "tool_use_id": { "type": "string", "description": "ID of the matching tool_use block when type=tool_result." }, "content": { "oneOf": [ { "type": "string" }, { "type": "array", "items": { "$ref": "#/components/schemas/RequestContentBlock" } } ], "description": "Tool execution result, either a string or an array of text/image content blocks." }, "thinking": { "type": "string", "description": "Echoed assistant thinking content when type=thinking." }, "signature": { "type": "string", "description": "Signature for echoed thinking content. Return unchanged in later turns." }, "cache_control": { "$ref": "#/components/schemas/CacheControl" } } }, "ResponseContentBlock": { "type": "object", "description": "Content block returned in response messages. The model emits text, tool_use (when calling tools), and thinking (when extended thinking is active). Responses never contain image, video, tool_result, or mid_conv_system blocks.", "required": [ "type" ], "properties": { "type": { "type": "string", "description": "Content block type:\n- text: Text content\n- tool_use: Model tool call\n- thinking: Model thinking content", "enum": [ "text", "tool_use", "thinking" ] }, "text": { "type": "string", "description": "Text content when type=text." }, "id": { "type": "string", "description": "Tool call ID returned when type=tool_use." }, "name": { "type": "string", "description": "Tool name returned when type=tool_use." }, "input": { "type": "object", "description": "Tool input returned when type=tool_use." }, "thinking": { "type": "string", "description": "Model thinking content when type=thinking." }, "signature": { "type": "string", "description": "Signature for thinking content. Return unchanged in later turns." } } }, "Usage": { "type": "object", "description": "Token usage for this request, including prompt cache usage when applicable.", "properties": { "input_tokens": { "type": "integer", "description": "Number of tokens consumed by input" }, "output_tokens": { "type": "integer", "description": "Number of tokens consumed by output" }, "cache_creation_input_tokens": { "type": "integer", "description": "Number of input tokens used to create prompt cache entries." }, "cache_read_input_tokens": { "type": "integer", "description": "Number of input tokens read from prompt cache." } } }, "StreamEvent": { "type": "object", "description": "", "required": [ "type" ], "properties": { "type": { "type": "string", "description": "Event type:\n- `message_start`: Message start, contains complete message metadata\n- `ping`: Heartbeat event\n- `content_block_start`: Content block start\n- `content_block_delta`: Content block incremental update\n- `content_block_stop`: Content block end\n- `message_delta`: Message-level incremental update (e.g., stop_reason)\n- `message_stop`: Message end", "enum": [ "message_start", "ping", "content_block_start", "content_block_delta", "content_block_stop", "message_delta", "message_stop" ] }, "message": { "type": "object", "description": "Message object (returned when `type` is `message_start`)", "properties": { "id": { "type": "string", "description": "Unique ID of the message" }, "type": { "type": "string", "enum": [ "message" ] }, "role": { "type": "string", "enum": [ "assistant" ] }, "content": { "type": "array", "description": "Content block list, initially an empty array", "items": { "$ref": "#/components/schemas/ResponseContentBlock" } }, "model": { "type": "string", "description": "Model ID" }, "stop_reason": { "type": "string", "nullable": true, "description": "Stop reason, null at the start of streaming" }, "stop_sequence": { "type": "string", "nullable": true, "description": "Stop sequence, null at the start of streaming" }, "usage": { "$ref": "#/components/schemas/Usage" } } }, "index": { "type": "integer", "description": "Index of the content block (returned for `content_block_start`, `content_block_delta`, `content_block_stop`)" }, "content_block": { "$ref": "#/components/schemas/ResponseContentBlock", "description": "Content block object (returned when `type` is `content_block_start`)" }, "delta": { "type": "object", "description": "Incremental update content (returned for `content_block_delta` or `message_delta`)", "properties": { "type": { "type": "string", "description": "Delta type, for example text_delta, thinking_delta, or signature_delta.", "enum": [ "text_delta", "thinking_delta", "signature_delta" ] }, "text": { "type": "string", "description": "Incremental text content" }, "stop_reason": { "type": "string", "description": "Reason for stopping generation.", "enum": [ "end_turn", "max_tokens", "tool_use" ] } } }, "usage": { "$ref": "#/components/schemas/Usage", "description": "Token usage (returned for `message_delta`)" } } }, "CacheControl": { "type": "object", "description": "Prompt cache marker. Not supported by MiniMax-M3 or MiniMax-M3.1-Flash.", "properties": { "type": { "type": "string", "enum": [ "ephemeral" ], "description": "Prompt cache marker." } }, "required": [ "type" ] }, "MediaSource": { "type": "object", "description": "Media source for image or video blocks.\n\n**Supported image formats**\n\n| Format | Common extensions | MIME Type |\n| :-- | :-- | :-- |\n| JPEG | .jpg, .jpeg | image/jpeg |\n| PNG | .png | image/png |\n| GIF | .gif | image/gif |\n| WEBP | .webp | image/webp |\n\n**Supported video formats**\n\n| Format | Common extensions | MIME Type |\n| :-- | :-- | :-- |\n| MP4 | .mp4 | video/mp4 |\n| AVI | .avi | video/avi or video/x-msvideo |\n| MOV | .mov | URL input: set the object storage Content-Type to video/quicktime; base64 input: use video/mov, i.e. data:video/mov;base64, |\n| MKV | .mkv | video/x-matroska |\n\n**File size and request limits**\n- URL or Base64 input: video file ≤ 50 MB, image file ≤ 10 MB, request body ≤ 64 MB.\n- Files API upload: referenced as `mm_file://{file_id}`, with a single video up to 512 MB.", "properties": { "type": { "type": "string", "enum": [ "base64", "url" ], "description": "Media source type." }, "media_type": { "type": "string", "description": "Required for base64 input, for example image/png or video/mp4." }, "data": { "type": "string", "description": "Base64-encoded media bytes." }, "url": { "type": "string", "description": "Public URL. Videos can also use a Files API reference in the form `mm_file://{file_id}`. To obtain a `file_id`, first upload the video via the [Upload File](/api-reference/file-management-upload) API." }, "detail": { "type": "string", "enum": [ "low", "default", "high" ], "default": "default", "description": "Understanding detail level. Defaults to default.\n\nFor image input, rough single-image token usage heuristic:\n\n| detail | Rough token usage |\n| :-- | :-- |\n| low | Usually a few hundred tokens, up to ~600 |\n| default | Often ~1k-3k tokens, up to ~5k |\n| high | Often several thousand tokens, up to ~15k+ |\n\nActual usage depends on image size and content; use `POST /anthropic/v1/messages/count_tokens` or response usage for exact usage." }, "fps": { "type": "number", "minimum": 0.2, "maximum": 5, "default": 1, "description": "Video frame sampling rate. Defaults to 1. Range [0.2, 5].\n- Higher values: more sensitive to scene changes, but higher token cost and slower response.\n- Lower values: lower token cost and faster response, but less sensitive to scene changes." }, "max_long_side_pixel": { "type": "integer", "minimum": 1, "description": "Longest-side pixel limit for the image or video frames." } }, "required": [ "type" ] }, "Tool": { "type": "object", "description": "Tool definitions for Anthropic-compatible tool use.", "properties": { "name": { "type": "string", "description": "Tool name." }, "description": { "type": "string", "description": "Tool description." }, "input_schema": { "type": "object", "description": "Tool input parameters JSON Schema." }, "cache_control": { "$ref": "#/components/schemas/CacheControl" } }, "required": [ "name", "input_schema" ] }, "ToolChoice": { "type": "object", "description": "Tool selection strategy. Only `auto` is supported; the model decides whether to call tools.", "properties": { "type": { "type": "string", "enum": [ "auto" ], "description": "Tool choice type." } }, "required": [ "type" ] }, "CountTokensResp": { "type": "object", "description": "Returns input token usage for the request without generating model output.", "properties": { "usage": { "$ref": "#/components/schemas/Usage" } } }, "ErrorResponse": { "type": "object", "description": "Error response. Uses an HTTP status code plus a JSON body. When an error occurs during streaming, it is delivered as an `event: error` SSE event with the same body structure; clients should stop reading and clean up the session state after receiving an error.", "properties": { "type": { "type": "string", "enum": [ "error" ], "description": "Always `error`." }, "request_id": { "type": "string", "description": "Unique identifier of the request, useful for troubleshooting." }, "error": { "type": "object", "properties": { "type": { "type": "string", "description": "Error type.", "enum": [ "invalid_request_error", "authentication_error", "permission_error", "not_found_error", "request_too_large", "rate_limit_error", "api_error", "overloaded_error" ] }, "message": { "type": "string", "description": "Error details." } } } } } }, "securitySchemes": { "bearerAuth": { "type": "http", "scheme": "bearer", "description": "Bearer API Key auth. Send Authorization: Bearer . If Authorization and x-api-key are both present, Authorization takes precedence." }, "apiKeyAuth": { "type": "apiKey", "in": "header", "name": "x-api-key", "description": "Anthropic-compatible API Key auth. Send x-api-key: . Authorization: Bearer is recommended." } } } }