openapi: 3.1.0
info:
  title: CometAPI Unified API
  description: >-
    CometAPI is an OpenAI-compatible aggregator that exposes a single REST
    surface for 500+ AI models from multiple vendors (OpenAI, Anthropic,
    Google, xAI, DeepSeek, Alibaba, and more). Endpoints follow OpenAI's
    request/response shapes for chat, embeddings, images, video, and
    speech, so existing OpenAI SDK clients can switch by changing only the
    base URL and API key.
  version: '1.0.0'
  contact:
    name: CometAPI
    url: https://www.cometapi.com/
externalDocs:
  description: CometAPI Documentation
  url: https://apidoc.cometapi.com/
servers:
  - url: https://api.cometapi.com/v1
    description: Production
tags:
  - name: Chat
    description: Chat completions across LLM providers.
  - name: Embeddings
    description: Vector embeddings for retrieval and similarity.
  - name: Images
    description: Text-to-image and image-to-image generation.
  - name: Audio
    description: Speech synthesis, transcription, and translation.
  - name: Video
    description: Text-to-video, image-to-video, and video extension.
  - name: Models
    description: List of supported models routable by CometAPI.
security:
  - bearerAuth: []
paths:
  /chat/completions:
    post:
      operationId: createChatCompletion
      summary: Create chat completion
      description: >-
        Send a chat completion request to any supported LLM. The `model`
        field selects the upstream provider (e.g. `gpt-5.5`, `claude-4-7-opus`,
        `gemini-2.5-pro`, `deepseek-v4`).
      tags:
        - Chat
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChatCompletionRequest'
      responses:
        '200':
          description: Completion response.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ChatCompletionResponse'
        '401':
          description: Invalid API key.
        '429':
          description: Rate limit or budget exceeded.
  /embeddings:
    post:
      operationId: createEmbedding
      summary: Create embedding
      description: Generate vector embeddings for text input.
      tags:
        - Embeddings
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required: [model, input]
              properties:
                model:
                  type: string
                input:
                  oneOf:
                    - type: string
                    - type: array
                      items:
                        type: string
      responses:
        '200':
          description: Embedding response.
  /images/generations:
    post:
      operationId: createImage
      summary: Generate image
      description: Generate an image from a text prompt using providers like Nano Banana, GPT Image, or Seedream.
      tags:
        - Images
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required: [model, prompt]
              properties:
                model:
                  type: string
                prompt:
                  type: string
                size:
                  type: string
                n:
                  type: integer
                  default: 1
                style:
                  type: string
                response_format:
                  type: string
                  enum: [url, b64_json]
      responses:
        '200':
          description: Generated image URLs or base64 data.
  /videos/generations:
    post:
      operationId: createVideo
      summary: Generate video
      description: Asynchronously generate a video from text or an image. Supported models include Sora, Veo, Grok, and Kling.
      tags:
        - Video
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required: [model, prompt]
              properties:
                model:
                  type: string
                prompt:
                  type: string
                image:
                  type: string
                  format: uri
                duration:
                  type: integer
      responses:
        '202':
          description: Video generation job accepted; poll for completion.
  /audio/speech:
    post:
      operationId: createSpeech
      summary: Create speech
      description: Synthesize speech audio from text (TTS).
      tags:
        - Audio
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required: [model, input]
              properties:
                model:
                  type: string
                input:
                  type: string
                voice:
                  type: string
                response_format:
                  type: string
      responses:
        '200':
          description: Audio bytes.
  /audio/transcriptions:
    post:
      operationId: createTranscription
      summary: Transcribe audio
      description: Transcribe an audio file to text using Whisper-class models.
      tags:
        - Audio
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                file:
                  type: string
                  format: binary
                model:
                  type: string
                language:
                  type: string
      responses:
        '200':
          description: Transcript.
  /models:
    get:
      operationId: listModels
      summary: List models
      description: Return the catalog of models routable through CometAPI.
      tags:
        - Models
      responses:
        '200':
          description: List of models.
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
  schemas:
    ChatCompletionRequest:
      type: object
      required: [model, messages]
      properties:
        model:
          type: string
          description: Routing key for the upstream model.
          example: gpt-5.5
        messages:
          type: array
          items:
            type: object
            required: [role, content]
            properties:
              role:
                type: string
                enum: [system, user, assistant, tool]
              content:
                type: string
        stream:
          type: boolean
          default: false
        temperature:
          type: number
          minimum: 0
          maximum: 2
        max_tokens:
          type: integer
        tools:
          type: array
          items:
            type: object
    ChatCompletionResponse:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
        model:
          type: string
        created:
          type: integer
        choices:
          type: array
          items:
            type: object
            properties:
              index:
                type: integer
              message:
                type: object
                properties:
                  role:
                    type: string
                  content:
                    type: string
              finish_reason:
                type: string
        usage:
          type: object
          properties:
            prompt_tokens:
              type: integer
            completion_tokens:
              type: integer
            total_tokens:
              type: integer