> ## Documentation Index > Fetch the complete documentation index at: https://powower.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # miniMax-M3.1-Flash > Call the MiniMax-M3.1-Flash OpenAI-compatible chat model via the baze platform. The model supports a 1,000,000-token context window with text, image, and video inputs. Thinking is always on; tune its depth with `reasoning_effort`. The same model is also available through `POST /v1/messages` and `POST /v1/responses`. ## OpenAPI ````yaml api-reference/en/zmodelChat/minimax/miniMax-M3.1-Flash.json POST /v1/chat/completions openapi: 3.0.1 info: title: MiniMax-M3.1-Flash version: 1.0.0 description: >- MiniMax (`type=35`) channel Chat Completions capability documentation. The unified API endpoint is `/v1/chat/completions`. The platform gateway forwards requests to the upstream provider `POST /v1/text/chatcompletion_v2`, using an OpenAI Chat Completions-compatible request and response structure. `MiniMax-M3.1-Flash` supports a 1,000,000-token context window with text, image, and video inputs. Thinking is always on and cannot be disabled; tune its depth with `reasoning_effort`. The same model is also available through `POST /v1/messages` (Anthropic Messages-compatible) and native `POST /v1/responses` (OpenAI Responses-compatible); see the Responses API page for how `reasoning.effort` maps to the same setting. This document describes only the field subset that the platform gateway reliably passes through: `model`, `messages`, `temperature`, `top_p`, `max_tokens`, `reasoning_effort`, `stream`. servers: - url: https://baze-api.powerbuyin.top description: Baze API server endpoint security: [] tags: - name: MiniMax Chat description: MiniMax OpenAI-compatible Chat Completions capability paths: /v1/chat/completions: post: tags: - MiniMax Chat summary: MiniMax-M3.1-Flash description: >- Call the MiniMax-M3.1-Flash OpenAI-compatible chat model via the baze platform. The model supports a 1,000,000-token context window with text, image, and video inputs. Thinking is always on; tune its depth with `reasoning_effort`. The same model is also available through `POST /v1/messages` and `POST /v1/responses`. operationId: minimaxChatCompletions requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ChatCompletionRequest' examples: basic: summary: Non-streaming chat value: model: MiniMax-M3.1-Flash messages: - role: system content: You are a concise assistant. - role: user content: Describe Paris in one sentence. temperature: 0.3 stream: summary: Streaming chat value: model: MiniMax-M3.1-Flash messages: - role: user content: Count from one to five. stream: true reasoning_effort: summary: Tune thinking depth value: model: MiniMax-M3.1-Flash messages: - role: user content: >- Analyze the time complexity of this code and suggest optimizations. reasoning_effort: medium image_input: summary: Image input value: model: MiniMax-M3.1-Flash messages: - role: user content: - type: text text: What is wrong with the layout in this screenshot? - type: image_url image_url: url: https://example.com/layout-bug.png detail: default responses: '200': description: >- Success. Non-streaming returns OpenAI-compatible JSON; streaming returns an OpenAI-compatible SSE event stream. content: application/json: schema: $ref: '#/components/schemas/ChatCompletionResponse' text/event-stream: schema: type: string description: >- SSE data stream. Each `data:` event can be parsed as an OpenAI Chat Completions Chunk; the stream typically ends with `data: [DONE]`. '400': description: Invalid request parameters. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' security: - BearerAuth: [] components: schemas: ChatCompletionRequest: type: object required: - model - messages properties: model: type: string enum: - MiniMax-M3.1-Flash messages: type: array items: $ref: '#/components/schemas/ChatMessage' temperature: type: number minimum: 0 maximum: 1 default: 0.7 description: Sampling temperature. Higher values make output more random. top_p: type: number minimum: 0 maximum: 1 default: 0.95 description: >- Nucleus sampling threshold. Avoid tuning `temperature` and `top_p` at the same time. max_tokens: type: integer minimum: 1 description: >- Maximum number of output tokens per reply. The model context window is 1,000,000 tokens, covering both input and output. reasoning_effort: type: string enum: - low - medium - high - xhigh - max default: max description: >- Thinking depth level. `MiniMax-M3.1-Flash` always thinks and cannot disable it, so this field is the only way to control depth. Higher values produce more output tokens and longer waits. Defaults to `max` when omitted. On the Responses path, express the same setting with `reasoning.effort`. stream: type: boolean description: Whether to return results as an SSE event stream. ChatCompletionResponse: type: object properties: id: type: string object: type: string created: type: integer model: type: string choices: type: array items: type: object usage: type: object ErrorResponse: type: object required: - error properties: error: $ref: '#/components/schemas/ErrorObject' ChatMessage: type: object required: - role - content properties: role: type: string enum: - system - user - assistant - user_system - group - sample_message_user - sample_message_ai description: |- Role of the message sender system: Set the model's role and behavior user: User input assistant: Model's historical replies user_system: Set the user's role and persona group: Name of the conversation sample_message_user: Example user input sample_message_ai: Example model output content: oneOf: - type: string - type: array description: >- Multimodal content blocks. MiniMax-M3.1-Flash supports text, image, and video inputs. items: type: object required: - type description: >- A multimodal content block. Use the `type` field to declare the block type, and populate only the field that matches that type. properties: type: type: string enum: - text - image_url - video_url description: |- Content block type: - `text`: Text block - `image_url`: Image input - `video_url`: Video input text: type: string description: Text content (when `type` is `text`). image_url: type: object description: >- Image input (when `type` is `image_url`). Maximum 10 MB per image. Supported formats: JPEG, PNG, GIF, WEBP. required: - url properties: url: type: string description: Image URL or Base64 data URL. detail: type: string enum: - low - default - high default: default description: >- Controls image parsing resolution. Defaults to `default`. Higher values consume more tokens. video_url: type: object description: >- Video input (when `type` is `video_url`). Supported formats: MP4, AVI, MOV, MKV. required: - url properties: url: type: string description: >- Video URL, Base64 data URL, or a Files API reference in the form `mm_file://{file_id}`. URL/Base64 videos: max 50 MB; Files API videos: max 512 MB. detail: type: string enum: - low - default - high default: default description: >- Controls video frame extraction resolution. Defaults to `default`. fps: type: number minimum: 0.2 maximum: 5 default: 1 description: >- Video frame extraction rate. Defaults to 1, range [0.2, 5]. Higher values are more sensitive to visual changes but cost more tokens; lower values cost fewer tokens but may miss visual changes. description: >- Message content. MiniMax-M3.1-Flash supports text, image, and video content blocks. ErrorObject: type: object required: - message - type - param - code properties: message: type: string type: type: string param: type: string code: type: string securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: API Token description: 'Pass `Authorization: Bearer ` in the request header.' ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.