--- title: "Create Response" method: POST path: "/v1/responses" tags: ["Responses"] --- # Create Response `POST /v1/responses` ## Request - Base URL: `https://api.minimax.io` - URL: `https://api.minimax.io/v1/responses` - Auth: HTTP bearer - TypeScript: (a function with typed inputs; its response is checked against the schema) ## Headers - `Content-Type` 'application/json', required ## Request body - CreateResponseReq - `model` string, required: Model name to invoke, e.g. `MiniMax-M3.1-Flash` - `service_tier` 'standard' | 'priority': 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. - `input` union, required: Conversation content. Supports either a simple text or a full conversation history array - string: Simple text input - InputItem[]: Full conversation history - `type` 'message' | 'function_call' | 'function_call_output' | 'reasoning': Item type - `role` 'user' | 'assistant' | 'system' | 'developer' | 'tool': Message role (only when `type` is `message`) - `content` union: Message content; string or multimodal parts array (only when `type` is `message`) - string - ContentPart[] - `type` 'input_text' | 'output_text' | 'input_image' | 'input_video', required: Content part type: - `input_text` / `output_text`: Text part - `input_image`: Image input - `input_video`: Video input - `text` string: Text content (when `type` is `input_text` / `output_text`) - `image_url` union: Image input (when `type` is `input_image`). Supported formats: JPEG, PNG, GIF, WEBP - string - object - … - `video_url` union: Video input (when `type` is `input_video`). Supported formats: MP4, AVI, MOV, MKV - string - object - … - `call_id` string: Tool call ID (only when `type` is `function_call` or `function_call_output`) - `name` string: Function name (only when `type` is `function_call`) - `arguments` string: Function arguments as a JSON string (only when `type` is `function_call`) - `output` union: Tool return result (only when `type` is `function_call_output`) - string - ContentPart[] - `type` 'input_text' | 'output_text' | 'input_image' | 'input_video', required: Content part type: - `input_text` / `output_text`: Text part - `input_image`: Image input - `input_video`: Video input - `text` string: Text content (when `type` is `input_text` / `output_text`) - `image_url` union: Image input (when `type` is `input_image`). Supported formats: JPEG, PNG, GIF, WEBP - string - object - … - `video_url` union: Video input (when `type` is `input_video`). Supported formats: MP4, AVI, MOV, MKV - string - object - … - `summary` object[]: Reasoning segment array (only when `type` is `reasoning`) - `type` 'summary_text' - `text` string: Reasoning text - `instructions` string: System instructions - `max_output_tokens` integer: Maximum output token count. Reasoning tokens count toward it too, so a value that is too small yields `status: "incomplete"` with no `message` item in `output`. - `temperature` number, float: Not supported yet; any value passed has no effect. `MiniMax-M3.1-Flash` and `MiniMax-M3` always use 1. - `top_p` number, float: Not supported yet; any value passed has no effect. `MiniMax-M3.1-Flash` and `MiniMax-M3` always use 0.95. If passed, the value must be within (0, 1]. - `stream` boolean: Set to `true` to enable SSE streaming response - `tools` Tool[]: Tool list - `type` 'function', required: Tool type - `name` string, required: Function name - `description` string: Function description, helps the model decide when to call it - `parameters` object: Function parameter definition in JSON Schema format - `tool_choice` 'auto': Tool selection strategy: `auto` lets the model decide whether to call tools - `metadata` object: Request metadata. Both keys and values are strings - `prompt_cache_key` string: Prompt cache routing identifier - `text` object: Output format control - `format` object - `type` 'text': Output format type - `reasoning` object: Reasoning control. The default depends on the model, so no schema-level default is declared. - `MiniMax-M3.1-Flash`: reasoning is always on, including when `reasoning` is omitted. `effort` accepts `low`, `medium`, `high`, `xhigh` or `max`, and does tune reasoning depth. When omitted, it defaults to `max`. `effort: "none"` returns HTTP 400. - `MiniMax-M3`: reasoning is off unless `effort` is set to a non-`none` value, which turns reasoning on but does not tune its depth. - `effort` 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | 'max' | 'none' ## Response `200` Successful response - CreateResponseResp - `id` string: Response ID - `object` 'response': Object type, always `response` - `created_at` integer: Response creation time (Unix seconds) - `model` string: Actual model that processed the request - `status` 'completed' | 'incomplete' | 'failed': Response status - `output` OutputItem[]: Model output list - union - object - `id` string: `_msg` format - `type` 'message' - `status` 'completed' - `role` 'assistant' - `content` object[] - `type` 'output_text' - `text` string: Text generated by the model - `annotations` unknown[]: Reference annotations - unknown - object: Reasoning output (only returned when reasoning is enabled) - `id` string: `_rs` format - `type` 'reasoning' - `status` 'completed' - `summary` unknown[]: Reasoning summary - unknown - `content` object[] - `type` 'reasoning_text' - `text` string: Reasoning text - object: Function call - `id` string: `_fc_` format - `type` 'function_call' - `status` 'completed' - `call_id` string: Tool call ID, used to correlate with `function_call_output` - `name` string: Function name - `arguments` string: Function arguments as a JSON string - `output_text` string, nullable: Convenience field: concatenates all text outputs - `usage` Usage - `input_tokens` integer: Input token count - `input_tokens_details` object - `cached_tokens` integer: Prompt cache hit tokens - `output_tokens` integer: Output token count - `output_tokens_details` object - `reasoning_tokens` integer: Tokens consumed by reasoning (only counted when reasoning is enabled) - `total_tokens` integer: Total token count - `error` object, nullable: Error info, only returned when `status=failed` - `code` string: Error code - `message` string: Human-readable error description - `incomplete_details` object, nullable: Reason for incompletion, only returned when `status=incomplete` - `reason` 'max_output_tokens' | 'content_filter' - `parallel_tool_calls` boolean: This parameter is not supported in requests. If passed, it will be ignored, and the response always returns **`true`**. - `store` boolean: This parameter is not supported in requests. If passed, it will be ignored, and the response always returns **`false`**. - `truncation` 'disabled': This parameter is not supported in requests. If passed, it will be ignored, and the response always returns **`disabled`**. - `previous_response_id` string, nullable: This parameter is not supported in requests. If passed, it will be ignored, and the response always returns **`null`**. - `conversation` object, nullable: This parameter is not supported in requests. If passed, it will be ignored, and the response always returns **`null`**. - `service_tier` string, nullable: The service tier actually applied to this request: `standard` or `priority`. `MiniMax-M3.1-Flash` does not support this field, so the response returns **`null`**. - `safety_identifier` string, nullable: This parameter is not supported in requests. If passed, it will be ignored, and the response always returns **`null`**. ## Changes - **2026-11-07** `caf5377783c4`: 1 warning - the `top_p` request property's exclusiveMinimum was set to `0.00` - **2026-11-06** `a8c51922e453`: 7 breaking, 9 info - removed the enum value `none` of the request property `tool_choice` - the response property `created_at` became optional for the status `200` - the response property `id` became optional for the status `200` - the response property `model` became optional for the status `200` - …12 more [Operation history](https://skmtc.dev/minimax/apis/minimax-responses-api/changes/v1/responses/post.md) --- [API](https://skmtc.dev/minimax/apis/minimax-responses-api.md) - [All operations](https://skmtc.dev/minimax/apis/minimax-responses-api/llms.txt) - [OpenAPI document](https://skmtc.dev/minimax/apis/minimax-responses-api/revisions/caf5377783c4?raw)