plugin-redoc-0.yaml

openapi: 3.0.0
info:
  title: Mistral AI API
  description: >-
    Our Chat Completion and Embeddings APIs specification. Create your account
    on [La Plateforme](https://console.mistral.ai) to get access and read the
    [docs](https://docs.mistral.ai) to learn how to use it.
  version: 0.0.2
servers:
  - url: https://api.mistral.ai/v1
paths:
  /chat/completions:
    post:
      operationId: createChatCompletion
      summary: Create Chat Completions
      requestBody:
        required: true
        content:
          application/json:
            schema:
              anyOf:
                - $ref: '#/components/schemas/ChatCompletionRequest'
                - $ref: '#/components/schemas/ChatCompletionRequestFunctionCall'
                - $ref: '#/components/schemas/ChatCompletionRequestJSONMode'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                oneOf:
                  - $ref: '#/components/schemas/ChatCompletionResponse'
                  - $ref: '#/components/schemas/ChatCompletionResponseFunctionCall'
                  - $ref: '#/components/schemas/ChatCompletionResponseJSONMode'
  /embeddings:
    post:
      operationId: createEmbedding
      summary: Create Embeddings
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/EmbeddingRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EmbeddingResponse'
  /models:
    get:
      operationId: listModels
      summary: List Available Models
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModelList'
components:
  schemas:
    Error:
      type: object
      properties:
        type:
          type: string
          nullable: false
        message:
          type: string
          nullable: false
        param:
          type: string
          nullable: true
        code:
          type: string
          nullable: true
      required:
        - type
        - message
        - param
        - code
    ErrorResponse:
      type: object
      properties:
        error:
          $ref: '#/components/schemas/Error'
      required:
        - error
    ModelList:
      type: object
      properties:
        object:
          type: string
        data:
          type: array
          items:
            $ref: '#/components/schemas/Model'
      required:
        - object
        - data
    ChatCompletionRequest:
      type: object
      title: Regular
      properties:
        model:
          description: >
            ID of the model to use. You can use the [List Available
            Models](/api#operation/listModels) API to see all of your available
            models, or see our [Model overview](/models) for model descriptions.
          type: string
          example: mistral-small-latest
        messages:
          description: >
            The prompt(s) to generate completions for, encoded as a list of dict
            with role and content. The first prompt role should be `user` or
            `system`.
          type: array
          items:
            type: object
            properties:
              role:
                type: string
                enum:
                  - system
                  - user
                  - assistant
                  - tool
              content:
                type: string
            example:
              role: user
              content: Who is the best French painter? Answer in one short sentence.
        temperature:
          type: number
          minimum: 0
          maximum: 1
          default: 0.7
          nullable: true
          description: >
            What sampling temperature to use, between 0.0 and 1.0. Higher values
            like 0.8 will make the output more random, while lower values like
            0.2 will make it more focused and deterministic.


            We generally recommend altering this or `top_p` but not both.
        top_p:
          type: number
          minimum: 0
          maximum: 1
          default: 1
          nullable: true
          description: >
            Nucleus sampling, where the model considers the results of the
            tokens with `top_p` probability mass. So 0.1 means only the tokens
            comprising the top 10% probability mass are considered.


            We generally recommend altering this or `temperature` but not both.
        max_tokens:
          type: integer
          minimum: 0
          default: null
          nullable: true
          example: 512
          description: >
            The maximum number of tokens to generate in the completion.


            The token count of your prompt plus `max_tokens` cannot exceed the
            model's context length. 
        stream:
          type: boolean
          default: false
          nullable: true
          description: >
            Whether to stream back partial progress. If set, tokens will be sent
            as data-only server-sent events as they become available, with the
            stream terminated by a data: [DONE] message. Otherwise, the server
            will hold the request open until the timeout or until completion,
            with the response containing the full result as JSON.
        safe_prompt:
          type: boolean
          default: false
          description: |
            Whether to inject a safety prompt before all conversations.
        random_seed:
          type: integer
          default: null
          example: 1337
          description: >
            The seed to use for random sampling. If set, different calls will
            generate deterministic results.
      required:
        - model
        - messages
    ChatCompletionRequestJSONMode:
      type: object
      title: JSON mode
      properties:
        model:
          description: >
            ID of the model to use. You can use the [List Available
            Models](/api#operation/listModels) API to see all of your available
            models, or see our [Model overview](/models) for model descriptions.
          type: string
          example: mistral-small-latest
        messages:
          description: >
            The prompt(s) to generate completions for, encoded as a list of dict
            with role and content. The first prompt role should be `user` or
            `system`.
          type: array
          items:
            type: object
            properties:
              role:
                type: string
                enum:
                  - system
                  - user
                  - assistant
                  - tool
              content:
                type: string
            example:
              role: user
              content: Who is the best French painter? Answer in JSON.
        response_format:
          type: object
          description: >
            An object specifying the format that the model must output. Setting
            to `{ "type": "json_object" }` enables JSON mode, which guarantees
            the message the model generates is in JSON.

            When using JSON mode you MUST also instruct the model to produce
            JSON yourself with a system or a user message.
          properties:
            type:
              type: string
              example: json_object
        temperature:
          type: number
          minimum: 0
          maximum: 1
          default: 0.7
          nullable: true
          description: >
            What sampling temperature to use, between 0.0 and 1.0. Higher values
            like 0.8 will make the output more random, while lower values like
            0.2 will make it more focused and deterministic.


            We generally recommend altering this or `top_p` but not both.
        top_p:
          type: number
          minimum: 0
          maximum: 1
          default: 1
          nullable: true
          description: >
            Nucleus sampling, where the model considers the results of the
            tokens with `top_p` probability mass. So 0.1 means only the tokens
            comprising the top 10% probability mass are considered.


            We generally recommend altering this or `temperature` but not both.
        max_tokens:
          type: integer
          minimum: 0
          default: null
          nullable: true
          example: 512
          description: >
            The maximum number of tokens to generate in the completion.


            The token count of your prompt plus `max_tokens` cannot exceed the
            model's context length. 
        stream:
          type: boolean
          default: false
          nullable: true
          description: >
            Whether to stream back partial progress. If set, tokens will be sent
            as data-only server-sent events as they become available, with the
            stream terminated by a data: [DONE] message. Otherwise, the server
            will hold the request open until the timeout or until completion,
            with the response containing the full result as JSON.
        safe_prompt:
          type: boolean
          default: false
          description: |
            Whether to inject a safety prompt before all conversations.
        random_seed:
          type: integer
          default: null
          example: 1337
          description: >
            The seed to use for random sampling. If set, different calls will
            generate deterministic results.
      required:
        - model
        - messages
    ChatCompletionRequestFunctionCall:
      type: object
      title: Function calling
      properties:
        model:
          description: >
            ID of the model to use. You can use the [List Available
            Models](/api#operation/listModels) API to see all of your available
            models, or see our [Model overview](/models) for model descriptions.
          type: string
          example: mistral-small-latest
        messages:
          description: >
            The prompt(s) to generate completions for, encoded as a list of dict
            with role and content. The first prompt role should be `user` or
            `system`.

            When role is `tool`, the properties should contain `tool_call_id`
            (string or `null`).
          type: array
          items:
            type: object
            properties:
              role:
                type: string
                enum:
                  - system
                  - user
                  - assistant
                  - tool
              content:
                type: string
            example:
              role: user
              content: What is the weather like in Paris?
        temperature:
          type: number
          minimum: 0
          maximum: 1
          default: 0.7
          nullable: true
          description: >
            What sampling temperature to use, between 0.0 and 1.0. Higher values
            like 0.8 will make the output more random, while lower values like
            0.2 will make it more focused and deterministic.


            We generally recommend altering this or `top_p` but not both.
        top_p:
          type: number
          minimum: 0
          maximum: 1
          default: 1
          nullable: true
          description: >
            Nucleus sampling, where the model considers the results of the
            tokens with `top_p` probability mass. So 0.1 means only the tokens
            comprising the top 10% probability mass are considered.


            We generally recommend altering this or `temperature` but not both.
        max_tokens:
          type: integer
          minimum: 0
          default: null
          example: 64
          nullable: true
          description: >
            The maximum number of tokens to generate in the completion.


            The token count of your prompt plus `max_tokens` cannot exceed the
            model's context length. 
        stream:
          type: boolean
          default: false
          nullable: true
          description: >
            Whether to stream back partial progress. If set, tokens will be sent
            as data-only server-sent events as they become available, with the
            stream terminated by a data: [DONE] message. Otherwise, the server
            will hold the request open until the timeout or until completion,
            with the response containing the full result as JSON.
        safe_prompt:
          type: boolean
          default: false
          description: |
            Whether to inject a safety prompt before all conversations.
        tools:
          type: array
          description: >
            A list of available tools for the model. Use this to specify
            functions for which the model can generate JSON inputs.
          items:
            type: object
            required:
              - type
              - function
            properties:
              type:
                type: string
                description: |
                  The type of the tool. Currently, only `function` is supported.
                example: function
              function:
                type: object
                required:
                  - name
                description: |
                  The function properties.
                properties:
                  description:
                    type: string
                    description: >
                      The description of the function to help the model
                      determine when and how to invoke it.
                    example: Get the current weather in a given location.
                  name:
                    type: string
                    required: true
                    description: >
                      The name of the function to be called. Must be a-z,A-Z,0-9
                      or contain underscores and dashes, with a maximum length
                      of 64.
                    example: get_weather
                  parameters:
                    type: object
                    description: >
                      The function parameters, defined using a JSON Schema
                      object. If omitted, the function is considered to have an
                      empty parameter list.
                    example:
                      type: object
                      properties:
                        location:
                          type: string
                          description: The city and department, e.g. Marseille, 13
                        unit:
                          type: string
                          enum:
                            - celsius
                            - fahrenheit
                      required:
                        - location
        tool_choice:
          type: string
          default: auto
          description: >
            Specifies if/how functions are called. If set to `none` the model
            won't call a function and will generate a message instead. If set to
            `auto` the model can choose to either generate a message or call a
            function. If set to `any` the model is forced to call a function.
          example: auto
        random_seed:
          type: integer
          default: null
          example: 1337
          description: >
            The seed to use for random sampling. If set, different calls will
            generate deterministic results.
      required:
        - model
        - messages
    ChatCompletionResponse:
      type: object
      title: Regular
      properties:
        id:
          type: string
          example: cmpl-e5cc70bb28c444948073e77776eb30ef
        object:
          type: string
          example: chat.completion
        created:
          type: integer
          example: 1702256327
        model:
          type: string
          example: mistral-small-latest
        choices:
          type: array
          items:
            type: object
            required:
              - index
              - text
              - finish_reason
            properties:
              index:
                type: integer
                example: 0
              message:
                type: object
                properties:
                  role:
                    type: string
                    enum:
                      - user
                      - assistant
                    example: assistant
                  content:
                    type: string
                    example: >-
                      Claude Monet is often considered one of the best French
                      painters due to his significant role in the Impressionist
                      movement.
              finish_reason:
                type: string
                enum:
                  - stop
                  - length
                  - model_length
                  - error
                  - tool_calls
                example: stop
        usage:
          type: object
          properties:
            prompt_tokens:
              type: integer
              example: 16
            completion_tokens:
              type: integer
              example: 34
            total_tokens:
              type: integer
              example: 50
          required:
            - prompt_tokens
            - completion_tokens
            - total_tokens
    ChatCompletionResponseJSONMode:
      type: object
      title: JSON mode
      properties:
        id:
          type: string
          example: cmpl-e5cc70bb28c444948073e77776eb30ef
        object:
          type: string
          example: chat.completion
        created:
          type: integer
          example: 1702256327
        model:
          type: string
          example: mistral-small-latest
        choices:
          type: array
          items:
            type: object
            required:
              - index
              - text
              - finish_reason
            properties:
              index:
                type: integer
                example: 0
              message:
                type: object
                properties:
                  role:
                    type: string
                    enum:
                      - user
                      - assistant
                    example: assistant
                  content:
                    type: string
                    example: >-
                      {"name": "Claude Monet", "reason": "Claude Monet is often
                      considered one of the best French painters due to his
                      significant role in the development of Impressionism, a
                      major art movement that originated in France. His water
                      lily paintings are among the most famous works in the
                      history of art."}
              finish_reason:
                type: string
                enum:
                  - stop
                  - length
                  - model_length
                  - error
                  - tool_calls
                example: stop
        usage:
          type: object
          properties:
            prompt_tokens:
              type: integer
              example: 14
            completion_tokens:
              type: integer
              example: 83
            total_tokens:
              type: integer
              example: 69
          required:
            - prompt_tokens
            - completion_tokens
            - total_tokens
    ChatCompletionResponseFunctionCall:
      type: object
      title: Function calling
      properties:
        id:
          type: string
          example: cmpl-e5cc70bb28c444948073e77776eb30ef
        object:
          type: string
          example: chat.completion
        created:
          type: integer
          example: 1702256327
        model:
          type: string
          example: mistral-large-latest
        choices:
          type: array
          items:
            type: object
            required:
              - index
              - text
              - finish_reason
            properties:
              index:
                type: integer
                example: 0
              message:
                type: object
                properties:
                  role:
                    type: string
                    example: assistant
                  content:
                    type: string
                    example: ''
                  tool_calls:
                    type: array
                    items:
                      type: object
                      properties:
                        function:
                          type: object
                          properties:
                            name:
                              type: string
                            arguments:
                              type: str
                    example:
                      - function:
                          name: get_current_weather
                          arguments: '{"location": "Paris, 75"}'
              finish_reason:
                type: string
                enum:
                  - stop
                  - length
                  - model_length
                  - error
                  - tool_calls
                example: tool_calls
        usage:
          type: object
          properties:
            prompt_tokens:
              type: integer
              example: 118
            completion_tokens:
              type: integer
              example: 35
            total_tokens:
              type: integer
              example: 153
          required:
            - prompt_tokens
            - completion_tokens
            - total_tokens
    EmbeddingRequest:
      type: object
      properties:
        model:
          type: string
          example: mistral-embed
          description: |
            The ID of the model to use for this request.
        input:
          type: array
          items:
            type: string
          example:
            - Hello
            - world
          description: |
            The list of strings to embed.
        encoding_format:
          type: string
          enum:
            - float
          example: float
          description: |
            The format of the output data.
    EmbeddingResponse:
      type: object
      properties:
        id:
          type: string
          example: embd-aad6fc62b17349b192ef09225058bc45
        object:
          type: string
          example: list
        data:
          type: array
          items:
            type: object
            properties:
              object:
                type: string
                example: embedding
              embedding:
                type: array
                items:
                  type: number
                example:
                  - 0.1
                  - 0.2
                  - 0.3
              index:
                type: int
                example: 0
          example:
            - object: embedding
              embedding:
                - 0.1
                - 0.2
                - 0.3
              index: 0
            - object: embedding
              embedding:
                - 0.4
                - 0.5
                - 0.6
              index: 1
        model:
          type: string
        usage:
          type: object
          properties:
            prompt_tokens:
              type: integer
              example: 9
            total_tokens:
              type: integer
              example: 9
          required:
            - prompt_tokens
            - total_tokens
      required:
        - id
        - object
        - data
        - model
        - usage
    Model:
      title: Model
      properties:
        id:
          type: string
        object:
          type: string
        created:
          type: integer
        owned_by:
          type: string
      required:
        - id
        - object
        - created
        - owned_by