FlexAI Chat API

openapi: 3.0.3
info:
  title: FlexAI Token Factory Audio Chat API
  version: v1
  description: 'OpenAI-compatible inference API for FlexAI Token Factory. A single API key provides access to open models across text, code, reasoning, vision, embedding, image, video, and audio modalities, priced by usage per model. The API is a drop-in replacement for the OpenAI API: point the OpenAI SDK (or any OpenAI-compatible client) at the FlexAI base URL and supply a FlexAI API key. This specification captures the endpoints FlexAI documents as supported; some OpenAI endpoints (assistants, threads, runs, files, fine-tuning, batches) are explicitly not served by this endpoint.'
  contact:
    name: FlexAI
    url: https://docs.flex.ai
  termsOfService: https://flex.ai/terms-of-service
  x-provenance:
    generated: '2026-07-19'
    method: generated
    source: https://docs.flex.ai/inference-api/reference/openai-compatibility and https://flex.ai/llms.txt — generated from FlexAI's documented OpenAI-compatible endpoint surface. Not a provider-published OpenAPI file.
servers:
- url: https://tokens.flex.ai/v1
  description: FlexAI Token Factory (serverless inference)
security:
- bearerAuth: []
tags:
- name: Chat
  description: Chat completions
paths:
  /chat/completions:
    post:
      operationId: createChatCompletion
      summary: Create a chat completion
      description: 'Generate a model response for a chat conversation. OpenAI-compatible. Supports streaming via server-sent events when stream=true. Note: non-streaming responses are capped at 2048 output tokens regardless of max_tokens (finish_reason "length"); n > 1 is rejected with a 400.'
      tags:
      - Chat
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChatCompletionRequest'
      responses:
        '200':
          description: A chat completion (or an SSE stream when stream=true)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ChatCompletion'
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '429':
          $ref: '#/components/responses/TooManyRequests'
components:
  schemas:
    ChatCompletion:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          example: chat.completion
        created:
          type: integer
        model:
          type: string
        choices:
          type: array
          items:
            type: object
            properties:
              index:
                type: integer
              message:
                $ref: '#/components/schemas/ChatMessage'
              finish_reason:
                type: string
                enum:
                - stop
                - length
                - tool_calls
                - content_filter
        usage:
          type: object
          properties:
            prompt_tokens:
              type: integer
            completion_tokens:
              type: integer
            total_tokens:
              type: integer
    ChatMessage:
      type: object
      required:
      - role
      - content
      properties:
        role:
          type: string
          enum:
          - system
          - user
          - assistant
          - tool
        content:
          type: string
        name:
          type: string
    ChatCompletionRequest:
      type: object
      required:
      - model
      - messages
      properties:
        model:
          type: string
          description: Model id from the /models catalog.
        messages:
          type: array
          items:
            $ref: '#/components/schemas/ChatMessage'
        temperature:
          type: number
        top_p:
          type: number
        stop:
          oneOf:
          - type: string
          - type: array
            items:
              type: string
        seed:
          type: integer
        user:
          type: string
        max_tokens:
          type: integer
          description: Non-streaming responses are capped at 2048 output tokens regardless of this value.
        stream:
          type: boolean
        stream_options:
          type: object
          properties:
            include_usage:
              type: boolean
        tools:
          type: array
          items:
            type: object
        tool_choice:
          oneOf:
          - type: string
          - type: object
        response_format:
          type: object
        presence_penalty:
          type: number
        frequency_penalty:
          type: number
    ErrorResponse:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
            type:
              type: string
            param:
              type: string
              nullable: true
            code:
              type: string
            doc_url:
              type: string
  responses:
    Unauthorized:
      description: Invalid or missing API key (error code `authentication_error`; includes a `doc_url` extension pointing at the auth docs).
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    TooManyRequests:
      description: Account-level rate limit or budget exceeded. Includes `Retry-After` and `x-ratelimit-*` response headers.
      headers:
        Retry-After:
          schema:
            type: integer
          description: Seconds to wait before retrying.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    BadRequest:
      description: Request validation failure. The error object includes a `param` field indicating the offending path (OpenAI-compatible error envelope).
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: 'FlexAI API key passed as a bearer token: `Authorization: Bearer $FLEXAI_API_KEY`. Create a key at https://tokens.flex.ai/signup.'