Edgee Tokens API

openapi: 3.2.0
info:
  title: Edgee Tokens 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: Tokens
  description: Token estimation endpoints
paths:
  /v1/messages/count_tokens:
    post:
      operationId: countTokensMessages
      summary: Count tokens (Anthropic format)
      description: 'Estimates the number of input tokens for a request shaped like the Anthropic [Messages API](#tag/Messages). Always forwards to the Anthropic provider''s tokenizer. Returns an `input_tokens` count compatible with `/v1/count_tokens`.


        **Note:** `max_tokens` is accepted but ignored by this endpoint.'
      tags:
      - Tokens
      security:
      - bearerAuth: []
      - apiKeyAuth: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateMessageRequest'
            example:
              model: claude-sonnet-4.5
              max_tokens: 1024
              messages:
              - role: user
                content: What is the capital of France?
      responses:
        '200':
          description: Token count estimated successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CountTokensResponse'
              example:
                input_tokens: 14
        '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'
  /v1/count_tokens:
    post:
      operationId: countTokens
      summary: Count tokens
      description: 'Estimates the number of input tokens for a set of messages without making an LLM call. Accepts both OpenAI chat format and Anthropic Messages format, the format is auto-detected from the message structure. Useful for pre-flight cost estimation, rate-limit planning, and prompt optimization.


        **Note:** Token counts are approximate and may differ from provider-native tokenizers (e.g. OpenAI tiktoken, Anthropic''s tokenizer).'
      tags:
      - Tokens
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CountTokensRequest'
            example:
              model: openai/gpt-5.2
              messages:
              - role: system
                content: You are a helpful assistant.
              - role: user
                content: What is the capital of France?
      responses:
        '200':
          description: Token count estimated successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CountTokensResponse'
              example:
                input_tokens: 42
        '400':
          description: Bad request - invalid input parameters
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Unauthorized - missing or invalid API key
          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'
    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
    CountTokensResponse:
      type: object
      required:
      - input_tokens
      properties:
        input_tokens:
          type: integer
          description: Estimated number of input tokens for the provided messages. This is an approximation, counts may differ from provider-native tokenizers. Use for estimation and budgeting, not exact billing.
          minimum: 0
          example: 42
    CountTokensRequest:
      type: object
      required:
      - model
      properties:
        model:
          type: string
          description: 'ID of the target model. Format: `{author_id}/{model_id}`. The gateway uses this to pick the appropriate tokenizer when `tokenizer` is not provided.'
          example: openai/gpt-5.2
        messages:
          type: array
          description: Optional array of message objects to count tokens for. Accepts both OpenAI chat format (with `system`, `user`, `assistant` roles) and Anthropic Messages format; the format is auto-detected from the message structure. Defaults to an empty array.
          items:
            type: object
            required:
            - role
            - content
            properties:
              role:
                type: string
                description: The role of the message author.
              content:
                description: The message content. Can be a plain string or an array of content blocks.
                oneOf:
                - type: string
                - type: array
                  items:
                    type: object
            additionalProperties: true
        system:
          description: Optional system prompt. Accepts a plain string or an array of Anthropic content blocks. Used when counting tokens for an Anthropic-style request.
          oneOf:
          - type: string
          - type: array
            items:
              type: object
        tokenizer:
          type: string
          enum:
          - cl100k_base
          - o200k_base
          description: Explicit tokenizer override. When omitted, the gateway picks one based on `model`.
  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