Edgee Chat API

openapi: 3.2.0
info:
  title: Edgee Chat 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: Chat
  description: Chat completion endpoints (OpenAI format)
paths:
  /v1/chat/completions:
    post:
      operationId: createChatCompletion
      summary: Create chat completion
      description: Creates a completion for the chat message. Supports both streaming and non-streaming responses. The API is OpenAI-compatible and works with any model and provider.
      tags:
      - Chat
      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,chatbot,customer-support`'
      - 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. Tunes the compressor for the agentic style of the calling client.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChatCompletionRequest'
      responses:
        '200':
          description: Chat completion created successfully
          headers:
            X-Edgee-Provider:
              description: Name of the upstream provider actually used to fulfill the request (e.g. `openai`, `anthropic`, `google`).
              schema:
                type: string
            X-Edgee-Fallback-Used:
              description: Set to `1` when a fallback provider was used because the primary provider failed or was unavailable.
              schema:
                type: string
                enum:
                - '1'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ChatCompletionResponse'
              example:
                id: chatcmpl-123
                object: chat.completion
                created: 1677652288
                model: openai/gpt-5.2
                choices:
                - index: 0
                  message:
                    role: assistant
                    content: Hello! How can I assist you today?
                  finish_reason: stop
                usage:
                  prompt_tokens: 10
                  completion_tokens: 10
                  total_tokens: 20
                  input_tokens_details:
                    cached_tokens: 0
                  output_tokens_details:
                    reasoning_tokens: 0
                compression:
                  saved_tokens: 450
                  cost_savings: 27000
                  reduction: 48.99884991374353
                  time_ms: 12
            text/event-stream:
              schema:
                type: string
                format: binary
                description: 'Server-Sent Events stream. Each event is a JSON object prefixed with ''data: '' and followed by two newlines. The stream consists of multiple `ChatCompletionChunk` objects, and optionally a final chunk with usage statistics if `stream_options.include_usage` is true.'
              examples:
                contentChunk:
                  value: 'data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"openai/gpt-5.2","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}


                    '
                roleChunk:
                  value: 'data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"openai/gpt-5.2","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}


                    '
                finalChunk:
                  value: 'data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"openai/gpt-5.2","choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":10,"completion_tokens":10,"total_tokens":20,"input_tokens_details":{"cached_tokens":0},"output_tokens_details":{"reasoning_tokens":0}}}


                    '
        '400':
          description: Bad request - invalid input parameters
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              examples:
                badModelId:
                  value:
                    error:
                      code: bad_model_id
                      message: 'Invalid model ID: ''invalid-model'''
                modelNotFound:
                  value:
                    error:
                      code: model_not_found
                      message: Model 'openai/gpt-1' not found
                providerNotSupported:
                  value:
                    error:
                      code: provider_not_supported
                      message: Provider 'anthropic' is not supported for model 'openai/gpt-5.2'
        '401':
          description: Unauthorized - missing or invalid API key
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              example:
                error:
                  code: unauthorized
                  message: Missing Authorization header
        '403':
          description: Forbidden - API key is inactive, expired, or model not allowed
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              examples:
                inactiveKey:
                  value:
                    error:
                      code: forbidden
                      message: API key is inactive
                expiredKey:
                  value:
                    error:
                      code: forbidden
                      message: API key has expired
                modelNotAllowed:
                  value:
                    error:
                      code: forbidden
                      message: Model 'openai/gpt-5.2' is not allowed for this API key
        '429':
          description: Too many requests - usage limit exceeded
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              example:
                error:
                  code: usage_limit_exceeded
                  message: 'Usage limit exceeded: 1000.00 / 1000 tokens used'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
components:
  schemas:
    ToolCall:
      type: object
      required:
      - id
      - type
      - function
      properties:
        id:
          type: string
          description: The ID of the tool call.
        type:
          type: string
          enum:
          - function
          description: The type of the tool call.
        function:
          $ref: '#/components/schemas/FunctionCall'
    ToolChoiceTypedMode:
      type: object
      description: Typed-mode form of `tool_choice` — an object containing only a `type` field set to `auto` or `none`.
      required:
      - type
      properties:
        type:
          type: string
          enum:
          - auto
          - none
    Message:
      type: object
      required:
      - role
      properties:
        role:
          type: string
          enum:
          - system
          - user
          - assistant
          - tool
          - developer
          description: 'The role of the message author. Required properties vary by role:

            - `system`, `user`, `developer`: requires `content`

            - `assistant`: `content` is optional (can be empty if `tool_calls` is present)

            - `tool`: requires `content` and `tool_call_id`'
        content:
          type: string
          description: The contents of the message. Required for all roles except `assistant` (where it can be empty if `tool_calls` is present). For `assistant` role, defaults to empty string if not provided.
        name:
          type: string
          description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. Used for `system`, `user`, `assistant`, and `developer` roles.
        tool_call_id:
          type: string
          description: The ID of the tool call that this message is responding to. Required for `tool` role only.
        refusal:
          type: string
          description: The refusal message from the model, if any. Used for `assistant` role only.
        tool_calls:
          type: array
          description: The tool calls made by the assistant. Used for `assistant` role only.
          items:
            $ref: '#/components/schemas/ToolCall'
        cache_control:
          type: object
          description: Anthropic prompt-cache control passthrough. Applied when routing to an Anthropic-backed model. Used on `system`, `user`, and `assistant` roles only.
          additionalProperties: true
          example:
            type: ephemeral
    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.
    InputTokenDetails:
      type: object
      description: Additional details about input tokens.
      properties:
        cached_tokens:
          type: integer
          description: Number of cached tokens read from the prompt cache.
          minimum: 0
        cache_creation_tokens:
          type: integer
          description: Number of tokens written to the prompt cache (Anthropic-style cache creation).
          minimum: 0
    ToolChoiceSpecific:
      type: object
      required:
      - type
      - function
      properties:
        type:
          type: string
          enum:
          - function
          description: The type of the tool.
        function:
          $ref: '#/components/schemas/ToolChoiceFunction'
    Usage:
      type: object
      description: Usage statistics for the completion. In streaming responses, this is only present in the final chunk when `stream_options.include_usage` is true.
      required:
      - prompt_tokens
      - completion_tokens
      - total_tokens
      - input_tokens_details
      - output_tokens_details
      properties:
        prompt_tokens:
          type: integer
          description: Number of tokens in the prompt.
          minimum: 0
        completion_tokens:
          type: integer
          description: Number of tokens in the generated completion.
          minimum: 0
        total_tokens:
          type: integer
          description: Total number of tokens used in the request (prompt + completion).
          minimum: 0
        input_tokens_details:
          $ref: '#/components/schemas/InputTokenDetails'
        output_tokens_details:
          $ref: '#/components/schemas/OutputTokenDetails'
    EdgeeToolExecuted:
      type: object
      description: Summary of an Edge Tool that was executed inline by the gateway.
      required:
      - name
      - success
      properties:
        name:
          type: string
          description: Edge Tool identifier (e.g. `edgee_current_time`).
          example: edgee_current_time
        success:
          type: boolean
          description: Whether the tool returned successfully.
    FunctionCall:
      type: object
      required:
      - name
      - arguments
      properties:
        name:
          type: string
          description: The name of the function to call.
        arguments:
          type: string
          description: The arguments to call the function with, as JSON.
    CompressionInfo:
      type: object
      description: Token compression metrics. Present in the response when token compression was applied to the request. The `usage.prompt_tokens` field reflects the compressed token count actually billed by the provider.
      required:
      - saved_tokens
      - cost_savings
      - reduction
      - time_ms
      properties:
        saved_tokens:
          type: integer
          description: Number of input tokens saved by compression (original count minus compressed count).
          minimum: 0
          example: 450
        cost_savings:
          type: integer
          description: 'Estimated cost savings in micro-units. Divide by `1000000` to convert to USD. Example: `27000` = $0.027 saved.'
          minimum: 0
          example: 27000
        reduction:
          type: number
          description: Percentage reduction in input tokens. For example, `48` means the compressed prompt was 48% smaller than the original.
          minimum: 0
          maximum: 100
          example: 48.99884991374353
        time_ms:
          type: integer
          description: Time taken to perform compression, in milliseconds.
          minimum: 0
          example: 12
    FunctionDefinition:
      type: object
      required:
      - name
      properties:
        name:
          type: string
          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.
        description:
          type: string
          description: A description of what the function does, used by the model to choose when and how to call the function.
        parameters:
          type: object
          description: The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
          additionalProperties: true
    ChatCompletionResponse:
      type: object
      required:
      - id
      - object
      - created
      - model
      - choices
      - usage
      properties:
        id:
          type: string
          description: A unique identifier for the chat completion.
          example: chatcmpl-123
        object:
          type: string
          enum:
          - chat.completion
          description: The object type, which is always `chat.completion`.
        created:
          type: integer
          description: The Unix timestamp (in seconds) of when the chat completion was created.
          example: 1677652288
        model:
          type: string
          description: The model used for the chat completion.
          example: openai/gpt-5.2
        choices:
          type: array
          description: A list of chat completion choices. Can be more than one if n is greater than 1.
          items:
            $ref: '#/components/schemas/ChatCompletionChoice'
        usage:
          $ref: '#/components/schemas/Usage'
        compression:
          $ref: '#/components/schemas/CompressionInfo'
        edgee_pending_id:
          type: string
          description: Present when one or more Edge Tool calls were deferred. Pass this value back as `edgee_pending_id` in the next request to resume the conversation with the tool results filled in.
        edgee_tools_executed:
          type: array
          description: List of Edge Tools the gateway executed inline before returning. Empty or absent when no Edge Tools ran.
          items:
            $ref: '#/components/schemas/EdgeeToolExecuted'
    CompressionModel:
      type: string
      description: Selects the compression bundle to apply to the request. Equivalent to the `X-Edgee-Compression-Model` header.
      enum:
      - claude
      - opencode
      - codex
      - cursor
    ToolChoiceFunction:
      type: object
      required:
      - name
      properties:
        name:
          type: string
          description: The name of the function to call.
    Tool:
      type: object
      required:
      - type
      - function
      properties:
        type:
          type: string
          enum:
          - function
          description: The type of the tool. Currently, only `function` is supported.
        function:
          $ref: '#/components/schemas/FunctionDefinition'
    ChatCompletionRequest:
      type: object
      required:
      - model
      - messages
      properties:
        model:
          type: string
          description: 'ID of the model to use. Format: `{author_id}/{model_id}` (e.g. `openai/gpt-5.2`)'
          example: openai/gpt-5.2
        messages:
          type: array
          description: A list of messages comprising the conversation so far.
          items:
            $ref: '#/components/schemas/Message'
          minItems: 1
        max_tokens:
          type: integer
          description: The maximum number of tokens that can be generated in the chat completion.
          minimum: 1
        stream:
          type: boolean
          description: If set, partial message deltas will be sent, as in OpenAI. Streamed chunks are sent as Server-Sent Events (SSE).
          default: false
        stream_options:
          type: object
          description: Options for streaming response.
          properties:
            include_usage:
              type: boolean
              description: If set, an additional `[DONE]` message will be sent with usage statistics when the stream is finished.
        tools:
          type: array
          description: A list of tools the model may call. Currently, only `function` type is supported.
          items:
            $ref: '#/components/schemas/Tool'
        tool_choice:
          oneOf:
          - type: string
            enum:
            - none
            - auto
            description: Bare-string mode. `none` forbids tool calls; `auto` lets the model decide.
          - $ref: '#/components/schemas/ToolChoiceTypedMode'
          - $ref: '#/components/schemas/ToolChoiceSpecific'
          description: 'Controls which tool (if any) the model is allowed to call. Accepts a bare string (`none` / `auto`), a typed-mode object (`{ "type": "auto" | "none" }`), or a specific function reference.'
        edgee_tool_ids:
          type: array
          items:
            type: string
          description: List of Edge Tool IDs to inject (e.g. edgee_current_time, edgee_generate_uuid). Each ID must be activated for your API key. When omitted or empty, only tools with hydration enabled for your org or API key are auto-injected. Invalid or non-activated IDs return 400 with invalid_edgee_tool_ids.
          example:
          - edgee_current_time
          - edgee_generate_uuid
        edgee_pending_id:
          type: string
          description: Pending operation ID when continuing a conversation after Edge Tool execution (e.g. when mixing client-side and Edge Tools). The gateway injects stored Edge Tool results into the message history.
        tags:
          type: array
          items:
            type: string
          description: Optional tags to categorize and label the request. Useful for filtering and grouping requests in analytics and logs. Can also be sent via the `x-edgee-tags` header as a comma-separated string.
        enable_debug:
          type: boolean
          description: When `true`, the response includes additional debug information. Equivalent to the `X-Edgee-Debug` header.
        compression_model:
          $ref: '#/components/schemas/CompressionModel'
    OutputTokenDetails:
      type: object
      description: Additional details about output tokens.
      properties:
        reasoning_tokens:
          type: integer
          description: Number of reasoning tokens in the output.
          minimum: 0
    ChatCompletionChoice:
      type: object
      required:
      - index
      - message
      properties:
        index:
          type: integer
          description: The index of the choice in the list of choices.
          minimum: 0
        message:
          $ref: '#/components/schemas/Message'
        finish_reason:
          type: string
          enum:
          - stop
          - length
          - content_filter
          - tool_calls
          description: The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, or `tool_calls` if the model called a tool.
  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