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

# EvoLink Auto - Claude Format

> Intelligent routing using Anthropic Messages API format

## Smart Model Routing

Call EvoLink Auto intelligent model routing using Anthropic Messages API format.

### Key Features

* **Claude Native Format**: Fully compatible with Anthropic Messages API
* **Intelligent Routing**: Automatically selects a suitable model
* **Transparent Response**: Response includes the actual model name used

<Note>
  Set the `model` parameter to `evolink/auto` and use the `/v1/messages` endpoint.
</Note>

<Note>
  **BaseURL**: The default BaseURL is `https://direct.evolink.ai`, which has better support for text models and long-lived connections. `https://api.evolink.ai` is the primary endpoint for multimodal services and serves as a fallback address for text models.
</Note>


## OpenAPI

````yaml /en/api-manual/language-series/evolink-auto/evolink-auto-claude.json POST /v1/messages
openapi: 3.1.0
info:
  title: EvoLink Auto - Claude Format
  description: Intelligent model routing using Anthropic Messages API format
  license:
    name: MIT
  version: 1.0.0
servers:
  - url: https://direct.evolink.ai
    description: Standard API
security:
  - bearerAuth: []
paths:
  /v1/messages:
    post:
      tags:
        - Intelligent Routing
      summary: Intelligent Model Routing (Claude Format)
      description: Intelligent routing using Anthropic Messages API format
      operationId: createMessagesAuto
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ClaudeAutoRequest'
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ClaudeResponse'
components:
  schemas:
    ClaudeAutoRequest:
      type: object
      required:
        - model
        - messages
        - max_tokens
      properties:
        model:
          type: string
          description: Use intelligent routing
          enum:
            - evolink/auto
          example: evolink/auto
        messages:
          type: array
          description: Conversation messages
          items:
            $ref: '#/components/schemas/MessageInput'
          minItems: 1
          example:
            - role: user
              content: Introduce the history of artificial intelligence
        max_tokens:
          type: integer
          description: Maximum tokens to generate
          minimum: 1
          example: 1024
        temperature:
          type: number
          description: Sampling temperature
          minimum: 0
          maximum: 2
          example: 0.7
        top_p:
          type: number
          description: Nucleus sampling parameter
          minimum: 0
          maximum: 1
          example: 0.9
        top_k:
          type: integer
          description: Top-K sampling
          minimum: 1
          example: 40
        stream:
          type: boolean
          description: Enable streaming
          default: false
    ClaudeResponse:
      type: object
      properties:
        id:
          type: string
          description: Response unique identifier
        model:
          type: string
          description: Actual model name used
          example: claude-opus-4-7
        type:
          type: string
          enum:
            - message
        role:
          type: string
          enum:
            - assistant
        content:
          type: array
          items:
            type: object
            properties:
              type:
                type: string
                enum:
                  - text
              text:
                type: string
        usage:
          type: object
          properties:
            input_tokens:
              type: integer
            output_tokens:
              type: integer
      example:
        id: msg_01XFDUDYJgAACyzWYzeHhsX7
        model: gpt-5.4
        type: message
        role: assistant
        content:
          - type: text
            text: The history of artificial intelligence dates back to the 1950s...
        usage:
          input_tokens: 15
          output_tokens: 156
    MessageInput:
      type: object
      required:
        - role
        - content
      properties:
        role:
          type: string
          enum:
            - user
            - assistant
        content:
          type: string
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: >-
        ##All APIs require Bearer Token authentication##


        **Get API Key:**


        Visit [API Key Management](https://evolink.ai/dashboard/keys) to get
        your API Key


        **Add to request header:**

        ```

        Authorization: Bearer YOUR_API_KEY

        ```
      bearerFormat: sk-evo-xxxxxxxxxx

````