Infer by Flow7 Chat Completions API

openapi: 3.2.0
info:
  title: Infer by Flow7 Public Chat API
  summary: Authenticated Responses, Chat Completions, and Anthropic Messages inference plus public catalog/status metadata.
  description: 'This description covers Infer''s public paid integration surface: authenticated Responses, OpenAI Chat Completions, Anthropic Messages, the authenticated model/receipt APIs, and unauthenticated catalog/status resources. All inference skins share one routing, wallet, cache, media, privacy, and receipt engine. Public registration creates an account; the account email must be verified, the wallet must be funded, and a scoped API key must be created before metered inference. Route availability is dynamic, so read the public status resource immediately before use. Infer does not attest an upstream provider identity.'
  termsOfService: https://infer.flow7.org/terms
  contact:
    name: Infer by Flow7 support
    url: https://infer.flow7.org/support
  version: 0.9.0
  x-infer-access:
    mode: public-paid
    url: https://infer.flow7.org/signup
    automaticAccountProvisioning: true
    emailVerificationRequired: true
    fundingRequiredForLiveInference: true
  x-infer-streaming:
    mode: live-incremental
    providerDeltasForwarded: true
    reasoningDeltas: true
    toolArgumentDeltas: true
    heartbeatSeconds: 15
    inferTotalGenerationDeadline: null
    finalSettlementMetadata: true
    clientDisconnectCancelsUpstream: true
    clientDisconnectCharge: generated_usage_up_to_reservation
servers:
- url: https://infer.flow7.org
  description: Infer's production origin. Read /api/public/status for current route availability.
tags:
- name: Chat Completions
paths:
  /v1/chat/completions:
    post:
      operationId: createChatCompletion
      summary: Create a chat completion
      description: OpenAI Chat Completions-compatible skin over the same Infer routing, wallet, privacy, cache, media, tool, and receipt engine used by /v1/responses. With stream=true, chat.completion.chunk events carry upstream reasoning, text, and tool-call argument deltas as they arrive; the final finish chunk includes relay receipt metadata and stream_options.include_usage adds the settled usage chunk. Infer emits keepalive comments during quiet periods and does not impose a generation wall-clock timeout while the connection remains alive.
      security:
      - bearerAuth: []
      parameters:
      - name: Idempotency-Key
        in: header
        required: false
        schema:
          type: string
          maxLength: 200
        description: Optional Infer idempotency key. A one-use key is generated when omitted.
      - name: X-Session-Affinity
        in: header
        required: false
        schema:
          type: string
          maxLength: 200
        description: Optional Infer session-affinity/cache-routing extension.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChatCompletionRequest'
      responses:
        '200':
          description: Chat completion or SSE stream
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ChatCompletionResponse'
            text/event-stream:
              schema:
                $ref: '#/components/schemas/ChatCompletionEventStream'
        '400':
          description: Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenAICompatErrorEnvelope'
        '401':
          description: Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenAICompatErrorEnvelope'
        '403':
          description: Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenAICompatErrorEnvelope'
        '413':
          description: Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenAICompatErrorEnvelope'
        '422':
          description: Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenAICompatErrorEnvelope'
        '429':
          description: Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenAICompatErrorEnvelope'
        '500':
          description: Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenAICompatErrorEnvelope'
        '503':
          description: Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenAICompatErrorEnvelope'
      tags:
      - Chat Completions
components:
  schemas:
    ChatMessage:
      type: object
      required:
      - role
      properties:
        role:
          type: string
          enum:
          - system
          - developer
          - user
          - assistant
          - tool
          - function
        content: {}
        name:
          type: string
        tool_call_id:
          type: string
        tool_calls:
          type: array
          items:
            type: object
            additionalProperties: true
        function_call:
          type: object
          additionalProperties: true
      additionalProperties: true
      description: OpenAI-compatible chat message. Text, image_url, input_audio, file, and video_url content parts are normalized into the Infer canonical request.
    OpenAICompatErrorEnvelope:
      type: object
      required:
      - error
      - request_id
      properties:
        error:
          type: object
          required:
          - message
          - type
          - param
          - code
          properties:
            message:
              type: string
            type:
              type: string
            param:
              type:
              - string
              - 'null'
            code:
              type:
              - string
              - 'null'
          additionalProperties: false
        request_id:
          type: string
      additionalProperties: false
    RelayResponseMetadata:
      type: object
      required:
      - receipt_id
      - price_version
      - tier
      - resolved_model_class
      - cache_status
      - environment
      - provider_disclosed
      - customer_cost_usd
      properties:
        receipt_id:
          type: string
        price_version:
          type: string
          description: Opaque reference (pv_…) to the immutable price version that priced this request. It matches the catalog option and the usage receipt and reveals no supplier or cost information.
        tier:
          type: string
          enum:
          - low-cost
          - balanced
          - stable
          - official
        resolved_model_class:
          type: string
        cache_status:
          type: string
          enum:
          - hit
          - partial
          - miss
        environment:
          type: string
          enum:
          - live
        provider_disclosed:
          type: boolean
          const: false
        customer_cost_usd:
          type: number
          minimum: 0
        idempotent_replay:
          type: boolean
      additionalProperties: true
    RelayRequestOptions:
      type: object
      properties:
        session_id:
          type: string
          minLength: 1
          maxLength: 200
        privacy:
          type: string
          enum:
          - standard
          - no-training
          - zero-retention
          default: standard
      additionalProperties: false
    ChatCompletionResponse:
      type: object
      required:
      - id
      - object
      - created
      - model
      - choices
      - usage
      - relay
      properties:
        id:
          type: string
        object:
          type: string
          const: chat.completion
        created:
          type: integer
        model:
          type: string
        choices:
          type: array
          items:
            type: object
            additionalProperties: true
        usage:
          type: object
          additionalProperties: true
        relay:
          $ref: '#/components/schemas/RelayResponseMetadata'
      additionalProperties: true
    ChatCompletionRequest:
      type: object
      required:
      - model
      - messages
      properties:
        model:
          type: string
          pattern: ^infer/[a-z0-9._/-]+:(low-cost|balanced|stable|official)$
        messages:
          type: array
          minItems: 1
          items:
            $ref: '#/components/schemas/ChatMessage'
        max_completion_tokens:
          type: integer
          minimum: 1
          description: Requested output ceiling. Capacity is limited by the selected Infer model/price option and its eligible routes, not by a global Infer token cap.
        max_tokens:
          type: integer
          minimum: 1
          deprecated: true
          description: Requested output ceiling. Capacity is limited by the selected Infer model/price option and its eligible routes, not by a global Infer token cap.
        stream:
          type: boolean
          default: false
        stream_options:
          type: object
          additionalProperties: true
        temperature:
          type: number
        top_p:
          type: number
        presence_penalty:
          type: number
        frequency_penalty:
          type: number
        seed:
          type: integer
        stop: {}
        tools:
          type: array
          items:
            type: object
            additionalProperties: true
        tool_choice: {}
        parallel_tool_calls:
          type: boolean
        response_format:
          type: object
          additionalProperties: true
        store:
          type: boolean
        prompt_cache_key:
          type: string
        cache_control:
          type: object
          additionalProperties: true
        relay:
          $ref: '#/components/schemas/RelayRequestOptions'
      additionalProperties: true
      description: OpenAI Chat Completions compatibility request. Infer normalizes this into the same canonical request used by /v1/responses; n values other than 1, audio output, prediction, web_search_options, and returned logprobs are not currently supported.
    ChatCompletionEventStream:
      type: string
      description: 'Live incremental OpenAI-compatible chat.completion.chunk SSE ending with data: [DONE]. Text, reasoning extensions, and tool-call arguments are forwarded as upstream deltas arrive; keepalive comments preserve quiet long-reasoning connections; final usage and relay receipt metadata are emitted only after wallet settlement.'
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: Infer API key
      description: Infer API key. Do not place it in a URL, prompt, support request, or public diagnostic output.
    anthropicApiKey:
      type: apiKey
      in: header
      name: x-api-key
      description: Infer API key accepted on the Anthropic Messages compatibility endpoint. Bearer authentication is also supported.
externalDocs:
  description: Human-readable Infer API documentation
  url: https://infer.flow7.org/docs
x-provenance:
  method: harvested
  publisher: Infer by Flow7
  source: https://infer.flow7.org/openapi.json
  note: split by refine-openapis from the provider's own published document, verified by fetch (openapi/_original/*.fetch.json);
    stamped by stamp-openapi-provenance.py (roadmap#793)