Skip to main content
Use these quickstarts when you already know the model family or task you want to build. Each page shows a minimal request, a Python example, a Node.js example, the request flow, common parameters, and links back to the API reference. For account setup, API keys, and the first generic call, start with Create an API key. For reusable platform guidance, use Core API guides.

​
Text APIs

OpenAI-compatible API

Use the OpenAI API-compatible Chat Completions route with a CometAPI model ID.

Claude API

Send Anthropic-compatible Messages requests to Claude models through CometAPI.

Gemini API

Start with Gemini native generateContent, or use OpenAI-compatible Chat Completions for existing SDK apps.

​
Image APIs

GPT Image API

Generate an image, decode b64_json, and save the result.

Gemini image API

Generate images with Gemini image models, including Nano Banana model families.

Flux API

Create a Flux image task, poll for the result, and download it before the URL expires.

​
Video APIs

Veo 3 API

Create a Veo video task with multipart form data and poll until completion.

Sora 2 API

Generate a Sora video, poll status, and download completed content.

Kling API

Submit a Kling text-to-video task and track it through polling or callbacks.

​
Supporting guides

Models

Find available model IDs and route each model to the correct API page.

Use OpenAI SDKs

Configure OpenAI-compatible SDK clients with the CometAPI base URL.

Estimate cost

Plan budget guards before token, image, or video requests.

Use webhooks and polling

Track async video generation with task IDs, polling, and callbacks.