Edgee Messages API

openapi: 3.2.0
info:
  title: Edgee Messages API
  version: 1.0.0
  description: Edgee is an edge-native AI Gateway with private model hosting, automatic model selection, cost audits/alerts, and edge tools. This API is OpenAI-compatible, providing one API for any model and any provider.
servers:
- url: https://edgee.io
  description: Edgee AI Gateway
security:
- bearerAuth: []
tags:
- name: Messages
  description: Messages endpoints (Anthropic format)
paths:
  /v1/messages:
    post:
      operationId: createMessage
      summary: Create message (Anthropic format)
      description: Creates a message using Anthropic's native Messages API format. Only works with Anthropic provider.
      tags:
      - Messages
      parameters:
      - name: X-Edgee-Tags
        in: header
        required: false
        schema:
          type: string
        description: 'Comma-separated list of tags for categorizing and filtering requests in analytics and logs. Example: `production,agent,codex`'
      - name: X-Edgee-Debug
        in: header
        required: false
        schema:
          type: boolean
        description: Enable debug mode to include additional debugging information in the response.
      - name: X-Edgee-Compression-Model
        in: header
        required: false
        schema:
          type: string
          enum:
          - claude
          - opencode
          - cursor
          - codex
        description: Compression bundle to apply.
      - name: x-edgee-api-key
        in: header
        required: false
        schema:
          type: string
        description: Claude CLI passthrough authentication. When set, the gateway uses this key instead of `x-api-key` / `Authorization` to authenticate the request. Used by the Claude Code CLI when proxying requests through Edgee.
      - name: x-edgee-session-id
        in: header
        required: false
        schema:
          type: string
        description: Claude CLI session identifier. Used to group all messages from a single CLI session in analytics.
      security:
      - bearerAuth: []
      - apiKeyAuth: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateMessageRequest'
      responses:
        '200':
          description: Message created successfully
          headers:
            X-Edgee-Provider:
              description: Name of the upstream provider actually used (always `anthropic` for this endpoint).
              schema:
                type: string
            X-Edgee-Fallback-Used:
              description: Set to `1` when a fallback provider was used.
              schema:
                type: string
                enum:
                - '1'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateMessageResponse'
            text/event-stream:
              schema:
                type: string
                format: binary
                description: Server-Sent Events stream for streaming responses
        '400':
          description: Bad request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '403':
          description: Forbidden
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
components:
  schemas:
    ToolChoice:
      type: object
      required:
      - type
      discriminator:
        propertyName: type
      oneOf:
      - type: object
        required:
        - type
        properties:
          type:
            type: string
            enum:
            - auto
            description: Model decides whether to use tools
      - type: object
        required:
        - type
        properties:
          type:
            type: string
            enum:
            - any
            description: Model must use one of the provided tools
      - type: object
        required:
        - type
        - name
        properties:
          type:
            type: string
            enum:
            - tool
          name:
            type: string
            description: Name of the specific tool to use
    ErrorResponse:
      type: object
      required:
      - error
      description: Error response. The `error` object follows OpenAI's error envelope shape; the gateway additionally populates `type` (Anthropic-style category) and `param` when applicable.
      properties:
        error:
          type: object
          required:
          - message
          properties:
            message:
              type: string
              description: A human-readable error message.
            type:
              type: string
              enum:
              - invalid_request_error
              - authentication_error
              - permission_error
              - not_found_error
              - rate_limit_error
              - server_error
              - provider_error
              description: Anthropic-style high-level error category. Always present.
            code:
              type:
              - string
              - 'null'
              description: 'A machine-readable error code. Currently emitted values: `unauthorized`, `forbidden`, `invalid_json`, `bad_model_id`, `model_not_found`, `provider_not_supported`, `invalid_tokenizer`, `invalid_request`, `usage_limit_exceeded`, `provider_error`, `internal_error`.'
              example: bad_model_id
            param:
              type:
              - string
              - 'null'
              description: Name of the request parameter that caused the error, when applicable.
    CreateMessageRequest:
      type: object
      required:
      - model
      - max_tokens
      - messages
      properties:
        model:
          type: string
          description: The model ID to use (Anthropic format, without provider prefix)
          example: claude-sonnet-4.5
        max_tokens:
          type: integer
          description: Maximum number of tokens to generate
          minimum: 1
          example: 1024
        messages:
          type: array
          description: Array of message objects
          items:
            $ref: '#/components/schemas/MessageParam'
          minItems: 1
        system:
          oneOf:
          - type: string
            description: System prompt as a string
          - type: array
            description: System prompt as content blocks
            items:
              $ref: '#/components/schemas/ContentBlock'
        stream:
          type: boolean
          description: Enable streaming responses
          default: false
        tools:
          type: array
          description: Tool definitions
          items:
            $ref: '#/components/schemas/AnthropicTool'
        tool_choice:
          $ref: '#/components/schemas/ToolChoice'
    MessageParam:
      type: object
      required:
      - role
      - content
      properties:
        role:
          type: string
          enum:
          - user
          - assistant
          description: The role of the message
        content:
          oneOf:
          - type: string
            description: Simple text content
          - type: array
            description: Array of content blocks
            items:
              $ref: '#/components/schemas/ContentBlock'
    CreateMessageResponse:
      type: object
      required:
      - id
      - model
      - content
      - usage
      properties:
        id:
          type: string
          description: Unique identifier for this message
        model:
          type: string
          description: The model that generated the response
        content:
          type: array
          description: Array of content blocks
          items:
            $ref: '#/components/schemas/ContentBlock'
        usage:
          $ref: '#/components/schemas/AnthropicUsage'
        stop_reason:
          type: string
          enum:
          - end_turn
          - max_tokens
          - tool_use
          description: Why the model stopped generating
    AnthropicTool:
      type: object
      required:
      - name
      - input_schema
      properties:
        name:
          type: string
          description: The name of the tool
        description:
          type: string
          description: Description of what the tool does
        input_schema:
          type: object
          description: JSON Schema describing the tool's input parameters
    ContentBlock:
      type: object
      required:
      - type
      discriminator:
        propertyName: type
      oneOf:
      - type: object
        required:
        - type
        - text
        properties:
          type:
            type: string
            enum:
            - text
          text:
            type: string
      - type: object
        required:
        - type
        - id
        - name
        - input
        properties:
          type:
            type: string
            enum:
            - tool_use
          id:
            type: string
          name:
            type: string
          input:
            type: object
      - type: object
        required:
        - type
        - tool_use_id
        - content
        properties:
          type:
            type: string
            enum:
            - tool_result
          tool_use_id:
            type: string
          content:
            type: string
          is_error:
            type: boolean
            default: false
    AnthropicUsage:
      type: object
      required:
      - input_tokens
      - output_tokens
      properties:
        input_tokens:
          type: integer
          description: Number of input tokens.
          minimum: 0
        output_tokens:
          type: integer
          description: Number of output tokens.
          minimum: 0
        cache_read_input_tokens:
          type: integer
          description: Number of input tokens read from the prompt cache.
          minimum: 0
        cache_creation_input_tokens:
          type: integer
          description: Number of input tokens written to the prompt cache.
          minimum: 0
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: Bearer authentication header of the form `Bearer <token>`, where `<token>` is your API key. More info [here](/docs/api-reference/authentication)
    apiKeyAuth:
      type: apiKey
      in: header
      name: x-api-key
      description: Anthropic-style API key authentication using the x-api-key header