CometAPI

CometAPI is an AI API aggregator that consolidates access to 500+ models from multiple providers (OpenAI, Anthropic, Google, xAI, DeepSeek, Alibaba, and more) behind a single OpenAI-compatible REST surface. It supports chat completions, embeddings, image generation, text-to-video and image-to-video, speech synthesis, and audio transcription. CometAPI positions itself as a drop-in replacement for the OpenAI SDK (changing only the base URL and key), with pay-as-you-go pricing reportedly 20-40% cheaper than direct vendor rates, sub-400ms median latency, and 99.9% service availability.

1 APIs 0 Features

AIAggregatorAudioChatEmbeddingsGenerative AIImagesLLMMulti-ModelOpenAI-CompatibleVideo

Sources

opencollection: 1.0.0
info:
  name: CometAPI Unified API
  version: 1.0.0
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Chat
    type: folder
  items:
  - info:
      name: Create chat completion
      type: http
    http:
      method: POST
      url: https://api.cometapi.com/v1/chat/completions
      body:
        type: json
        data: '{}'
    docs: 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`).
- info:
    name: Embeddings
    type: folder
  items:
  - info:
      name: Create embedding
      type: http
    http:
      method: POST
      url: https://api.cometapi.com/v1/embeddings
      body:
        type: json
        data: '{}'
    docs: Generate vector embeddings for text input.
- info:
    name: Images
    type: folder
  items:
  - info:
      name: Generate image
      type: http
    http:
      method: POST
      url: https://api.cometapi.com/v1/images/generations
      body:
        type: json
        data: '{}'
    docs: Generate an image from a text prompt using providers like Nano Banana, GPT Image, or Seedream.
- info:
    name: Video
    type: folder
  items:
  - info:
      name: Generate video
      type: http
    http:
      method: POST
      url: https://api.cometapi.com/v1/videos/generations
      body:
        type: json
        data: '{}'
    docs: Asynchronously generate a video from text or an image. Supported models include Sora, Veo, Grok, and Kling.
- info:
    name: Audio
    type: folder
  items:
  - info:
      name: Create speech
      type: http
    http:
      method: POST
      url: https://api.cometapi.com/v1/audio/speech
      body:
        type: json
        data: '{}'
    docs: Synthesize speech audio from text (TTS).
  - info:
      name: Transcribe audio
      type: http
    http:
      method: POST
      url: https://api.cometapi.com/v1/audio/transcriptions
      body:
        type: multipart-form
        data:
        - name: file
          type: text
          value: ''
        - name: model
          type: text
          value: ''
        - name: language
          type: text
          value: ''
    docs: Transcribe an audio file to text using Whisper-class models.
- info:
    name: Models
    type: folder
  items:
  - info:
      name: List models
      type: http
    http:
      method: GET
      url: https://api.cometapi.com/v1/models
    docs: Return the catalog of models routable through CometAPI.
bundled: true

CometAPI

APIs

CometAPI Unified API

Collections

CometAPI Unified API

Pricing Plans

Cometapi Plans Pricing

Rate Limits

Cometapi Rate Limits

FinOps

Cometapi Finops

Semantic Vocabularies

Cometapi Context

API Governance Rules

CometAPI API Rules

Resources

Sources