> ## Documentation Index
> Fetch the complete documentation index at: https://docs.capriole.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Messages

> Create Anthropic Messages-compatible output with Capriole AI Claude models.

Use this endpoint when your application, SDK, or agent expects the Anthropic Messages request and response format.

Send a standard Messages payload with `model`, `messages`, and `max_tokens`. Capriole AI resolves latest aliases to the selected upstream Claude model before upstream dispatch, forwards compatible fields such as `system`, `tools`, `thinking`, and `stream`, and returns the upstream JSON or SSE stream unchanged.

`POST /v1/messages` accepts `claude-latest`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, and `claude-sonnet-4-6`. Use `claude-latest` to let Capriole AI choose our recommended flagship Claude Messages model.

`POST /v1/messages/count_tokens` accepts the same Claude model IDs for Anthropic-compatible token-count checks. It returns the selected upstream's token-count response or error.

For simple Capriole-native text generation, use `POST /v1/chat`. Use `POST /v1/messages` when Anthropic Messages wire behavior is required.


## OpenAPI

````yaml api-reference/openapi.json POST /v1/messages
openapi: 3.1.0
info:
  title: Capriole AI API
  description: >-
    Public API for model discovery, text chat, and protocol-compatible model
    endpoints.
  version: 1.0.0
servers:
  - url: https://api.caprioletech.com
security: []
paths:
  /v1/messages:
    post:
      summary: Create message
      description: Creates an Anthropic Messages-compatible response for Claude models.
      operationId: createMessage
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/MessagesRequest'
            examples:
              text:
                value:
                  model: claude-latest
                  max_tokens: 1024
                  messages:
                    - role: user
                      content: Hello World!
              streaming:
                value:
                  model: claude-opus-4-7
                  max_tokens: 1024
                  messages:
                    - role: user
                      content: Write a short Python function.
                  stream: true
      responses:
        '200':
          description: Anthropic Messages-compatible JSON response or SSE stream
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/MessagesResponse'
            text/event-stream:
              schema:
                type: string
                description: Anthropic Messages-compatible SSE chunks.
        '400':
          $ref: '#/components/responses/ValidationOrDetailErrorResponse'
        '401':
          $ref: '#/components/responses/DetailErrorResponse'
        '403':
          $ref: '#/components/responses/DetailErrorResponse'
        '429':
          $ref: '#/components/responses/RateLimitErrorResponse'
        '500':
          $ref: '#/components/responses/InternalServerErrorResponse'
        '502':
          $ref: '#/components/responses/DetailErrorResponse'
      security:
        - bearerAuth: []
components:
  schemas:
    MessagesRequest:
      type: object
      additionalProperties: true
      required:
        - model
        - messages
        - max_tokens
      properties:
        model:
          type: string
          description: Public Anthropic Messages model identifier or Claude latest alias
          enum:
            - claude-latest
            - claude-opus-4-8
            - claude-opus-4-7
            - claude-opus-4-6
            - claude-sonnet-4-6
        messages:
          type: array
          description: Anthropic-compatible conversation messages.
          items:
            $ref: '#/components/schemas/MessagesMessage'
        max_tokens:
          type: integer
          exclusiveMinimum: 0
          description: Maximum number of output tokens.
        system:
          description: Optional Anthropic-compatible system prompt.
          oneOf:
            - type: string
            - type: array
              items:
                $ref: '#/components/schemas/MessagesContentBlock'
        tools:
          type: array
          description: Anthropic-compatible tool definitions.
          items:
            type: object
            additionalProperties: true
        thinking:
          type: object
          description: Anthropic-compatible thinking options.
          additionalProperties: true
        stream:
          type: boolean
          default: false
          description: Stream the response as Anthropic-compatible server-sent events.
    MessagesResponse:
      type: object
      description: Anthropic Messages-compatible response body.
      additionalProperties: true
    MessagesMessage:
      type: object
      additionalProperties: true
      required:
        - role
        - content
      properties:
        role:
          type: string
          description: Message role such as user or assistant.
        content:
          description: Anthropic-compatible message content.
          oneOf:
            - type: string
            - type: array
              items:
                $ref: '#/components/schemas/MessagesContentBlock'
    MessagesContentBlock:
      type: object
      additionalProperties: true
      properties:
        type:
          type: string
          description: Anthropic content block type.
        text:
          type: string
    ValidationError:
      type: object
      required:
        - detail
        - errors
      properties:
        detail:
          type: string
          description: Validation summary
        errors:
          type: array
          items:
            type: string
          description: Per-field validation errors
    DetailError:
      type: object
      required:
        - detail
      properties:
        detail:
          type: string
          description: Error detail from the API
  responses:
    ValidationOrDetailErrorResponse:
      description: Validation error or request-level error response
      content:
        application/json:
          schema:
            oneOf:
              - $ref: '#/components/schemas/ValidationError'
              - $ref: '#/components/schemas/DetailError'
          examples:
            invalidPayload:
              value:
                detail: Invalid input parameters received.
                errors:
                  - >-
                    Field 'body -> input': String should have at least 1
                    character
    DetailErrorResponse:
      description: Error response with a detail message
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/DetailError'
          examples:
            missingBearerToken:
              value:
                detail: Missing Bearer token
            invalidApiKey:
              value:
                detail: Invalid API key
            usageMetadataUnavailable:
              value:
                detail: Missing usage metadata
    RateLimitErrorResponse:
      description: Rate limit error response
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/DetailError'
          examples:
            rateLimitExceeded:
              value:
                detail: 'Rate limit exceeded: 100 per 1 minute'
    InternalServerErrorResponse:
      description: Internal server error response
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/DetailError'
          examples:
            internalServerError:
              value:
                detail: An internal server error occurred. Please try again later.
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: >-
        Use an API key created in the Capriole AI page. Send it as
        `Authorization: Bearer sk-...`.

````