openapi: 3.0.3
info:
  title: FlexAI Token Factory 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
  - name: Completions
    description: Legacy text completions
  - name: Models
    description: Model catalog
  - name: Embeddings
    description: Vector embeddings
  - name: Audio
    description: Speech-to-text and text-to-speech
  - name: Images
    description: Image generation
  - name: Video
    description: Video generation
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'
  /completions:
    post:
      operationId: createCompletion
      summary: Create a text completion (legacy)
      description: >-
        Legacy text-completion endpoint kept for OpenAI compatibility. Prefer
        /chat/completions for new work.
      tags: [Completions]
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required: [model, prompt]
              properties:
                model:
                  type: string
                prompt:
                  type: string
                max_tokens:
                  type: integer
                temperature:
                  type: number
                stream:
                  type: boolean
      responses:
        '200':
          description: A text completion
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '429':
          $ref: '#/components/responses/TooManyRequests'
  /models:
    get:
      operationId: listModels
      summary: List available models
      description: >-
        Return the live catalog of models served by FlexAI across all
        modalities, with category annotations (text, code, reasoning, vision,
        embedding, image, video, audio).
      tags: [Models]
      responses:
        '200':
          description: The list of available models
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModelList'
        '401':
          $ref: '#/components/responses/Unauthorized'
  /embeddings:
    post:
      operationId: createEmbedding
      summary: Create embeddings
      description: >-
        Generate vector embeddings for the given input using an open embedding
        model. Billed per token.
      tags: [Embeddings]
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required: [model, input]
              properties:
                model:
                  type: string
                input:
                  description: A string or array of strings to embed.
                  oneOf:
                    - type: string
                    - type: array
                      items:
                        type: string
                encoding_format:
                  type: string
                  enum: [float, base64]
                  default: float
      responses:
        '200':
          description: The embedding vectors
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '429':
          $ref: '#/components/responses/TooManyRequests'
  /audio/transcriptions:
    post:
      operationId: createTranscription
      summary: Transcribe audio to text (speech-to-text)
      description: >-
        Transcribe audio using an open transcription model (e.g. Whisper).
        Billed per minute of audio.
      tags: [Audio]
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [model, file]
              properties:
                model:
                  type: string
                file:
                  type: string
                  format: binary
      responses:
        '200':
          description: The transcription result
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '429':
          $ref: '#/components/responses/TooManyRequests'
  /audio/speech:
    post:
      operationId: createSpeech
      summary: Synthesize speech from text (text-to-speech)
      description: >-
        Generate audio from input text using an open TTS model (e.g. Kokoro).
        Billed per character.
      tags: [Audio]
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required: [model, input]
              properties:
                model:
                  type: string
                input:
                  type: string
                voice:
                  type: string
      responses:
        '200':
          description: The synthesized audio stream
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '429':
          $ref: '#/components/responses/TooManyRequests'
  /images/generations:
    post:
      operationId: createImage
      summary: Generate images
      description: >-
        Generate one or more images from a text prompt using an open image
        model (e.g. FLUX.1). Billed per image.
      tags: [Images]
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required: [model, prompt]
              properties:
                model:
                  type: string
                prompt:
                  type: string
                n:
                  type: integer
                size:
                  type: string
      responses:
        '200':
          description: The generated image(s)
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '429':
          $ref: '#/components/responses/TooManyRequests'
  /videos/generations:
    post:
      operationId: createVideo
      summary: Generate video (async)
      description: >-
        Generate video from a text prompt using an open text-to-video model
        (Wan2.2). Asynchronous; available on demand on dedicated GPUs. Billed
        per generated video.
      tags: [Video]
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required: [model, prompt]
              properties:
                model:
                  type: string
                prompt:
                  type: string
      responses:
        '200':
          description: The video generation job
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '429':
          $ref: '#/components/responses/TooManyRequests'
components:
  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.
  responses:
    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'
    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'
  schemas:
    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
    ChatMessage:
      type: object
      required: [role, content]
      properties:
        role:
          type: string
          enum: [system, user, assistant, tool]
        content:
          type: string
        name:
          type: string
    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
    ModelList:
      type: object
      properties:
        object:
          type: string
          example: list
        data:
          type: array
          items:
            $ref: '#/components/schemas/Model'
    Model:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          example: model
        created:
          type: integer
        owned_by:
          type: string
    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