Mistral AI Chat API

openapi: 3.2.0
info:
  title: Mistral AI Chat API
  description: Chat completion API for conversational AI using Mistral's language models. Supports streaming, function calling, JSON mode, vision inputs, and multi-turn conversations with system, user, assistant, and tool messages.
  version: '1.0'
  contact:
    name: Mistral AI Support
    url: https://docs.mistral.ai/
    email: support@mistral.ai
  termsOfService: https://mistral.ai/terms/
servers:
- url: https://api.mistral.ai/v1
  description: Mistral AI Production
security:
- bearerAuth: []
tags:
- name: Chat
  description: Chat completion operations
paths:
  /chat/completions:
    post:
      operationId: createChatCompletion
      summary: Mistral AI Create a chat completion
      description: Generate a model response for the given chat conversation. Supports multi-turn conversations, streaming, function calling, JSON mode, and vision inputs depending on the model.
      tags:
      - Chat
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChatCompletionRequest'
      responses:
        '200':
          description: Chat completion response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ChatCompletionResponse'
            text/event-stream:
              schema:
                $ref: '#/components/schemas/ChatCompletionStreamResponse'
        '400':
          description: Bad request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Unauthorized - invalid or missing API key
        '429':
          description: Rate limit exceeded
        '500':
          description: Internal server error
components:
  schemas:
    Error:
      type: object
      properties:
        type:
          type: string
        message:
          type: string
        param:
          type:
          - string
          - 'null'
        code:
          type:
          - string
          - 'null'
    ChatCompletionResponse:
      type: object
      properties:
        id:
          type: string
          description: Unique identifier for the completion
        object:
          type: string
          enum:
          - chat.completion
        created:
          type: integer
          description: Unix timestamp of when the completion was created
        model:
          type: string
          description: The model used for the completion
        choices:
          type: array
          items:
            $ref: '#/components/schemas/Choice'
        usage:
          $ref: '#/components/schemas/Usage'
    Usage:
      type: object
      properties:
        prompt_tokens:
          type: integer
          description: Number of tokens in the prompt
        completion_tokens:
          type: integer
          description: Number of tokens in the completion
        total_tokens:
          type: integer
          description: Total tokens used
    Tool:
      type: object
      required:
      - type
      - function
      properties:
        type:
          type: string
          enum:
          - function
        function:
          $ref: '#/components/schemas/FunctionDefinition'
    ToolCall:
      type: object
      properties:
        id:
          type: string
          description: Unique identifier for the tool call
        type:
          type: string
          enum:
          - function
        function:
          type: object
          properties:
            name:
              type: string
              description: The function name
            arguments:
              type: string
              description: JSON string of the function arguments
    FunctionDefinition:
      type: object
      required:
      - name
      properties:
        name:
          type: string
          description: The name of the function
        description:
          type: string
          description: Description of what the function does
        parameters:
          type: object
          description: JSON Schema describing the function parameters
    Message:
      type: object
      required:
      - role
      - content
      properties:
        role:
          type: string
          enum:
          - system
          - user
          - assistant
          - tool
          description: The role of the message author
        content:
          oneOf:
          - type: string
          - type: array
            items:
              $ref: '#/components/schemas/ContentPart'
          description: The content of the message
        name:
          type: string
          description: Optional name for the participant
        tool_calls:
          type: array
          items:
            $ref: '#/components/schemas/ToolCall'
          description: Tool calls generated by the model
        tool_call_id:
          type: string
          description: ID of the tool call this message is a response to
    Choice:
      type: object
      properties:
        index:
          type: integer
        message:
          $ref: '#/components/schemas/Message'
        finish_reason:
          type: string
          enum:
          - stop
          - length
          - tool_calls
          - model_length
          description: Reason the model stopped generating
    ChatCompletionRequest:
      type: object
      required:
      - model
      - messages
      properties:
        model:
          type: string
          description: ID of the model to use
          examples:
          - mistral-large-latest
          - mistral-small-latest
          - open-mistral-nemo
        messages:
          type: array
          description: List of messages comprising the conversation
          items:
            $ref: '#/components/schemas/Message'
        temperature:
          type: number
          minimum: 0
          maximum: 2
          default: 0.7
          description: Sampling temperature between 0 and 2
        top_p:
          type: number
          minimum: 0
          maximum: 1
          default: 1
          description: Nucleus sampling parameter
        max_tokens:
          type: integer
          minimum: 1
          description: Maximum number of tokens to generate
        stream:
          type: boolean
          default: false
          description: Whether to stream partial message deltas
        stop:
          oneOf:
          - type: string
          - type: array
            items:
              type: string
          description: Stop sequences where the model will stop generating
        random_seed:
          type: integer
          description: Random seed for deterministic generation
        response_format:
          type: object
          properties:
            type:
              type: string
              enum:
              - text
              - json_object
          description: Output format specification
        tools:
          type: array
          items:
            $ref: '#/components/schemas/Tool'
          description: List of tools the model may call
        tool_choice:
          type: string
          enum:
          - auto
          - none
          - any
          default: auto
          description: Controls how the model uses tools
        safe_prompt:
          type: boolean
          default: false
          description: Whether to prepend a safety system prompt
    ChatCompletionStreamResponse:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          enum:
          - chat.completion.chunk
        created:
          type: integer
        model:
          type: string
        choices:
          type: array
          items:
            $ref: '#/components/schemas/StreamChoice'
    StreamChoice:
      type: object
      properties:
        index:
          type: integer
        delta:
          $ref: '#/components/schemas/Message'
        finish_reason:
          type:
          - string
          - 'null'
          enum:
          - stop
          - length
          - tool_calls
          - model_length
          - null
    ContentPart:
      type: object
      required:
      - type
      properties:
        type:
          type: string
          enum:
          - text
          - image_url
        text:
          type: string
          description: Text content
        image_url:
          type: object
          properties:
            url:
              type: string
              format: uri
              description: URL or base64 data URI of the image
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: Mistral AI API key passed as a Bearer token
externalDocs:
  description: Mistral AI Chat API Documentation
  url: https://docs.mistral.ai/api/