> ## Documentation Index
> Fetch the complete documentation index at: https://apidoc.cometapi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Model API quickstarts: Build with CometAPI models

> Choose a CometAPI model API quickstart for text, image, and video workflows with curl, Python, Node.js, and links to the API reference.

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](https://apidoc.cometapi.com/overview/quick-start.md). For reusable platform guidance, use [Core API guides](https://apidoc.cometapi.com/guides/use-cometapi-with-openai-sdk.md).

## Text APIs

> [card] [OpenAI-compatible API](https://apidoc.cometapi.com/quickstarts/text/openai-compatible-api.md)
>
> Use the OpenAI API-compatible Chat Completions route with a CometAPI model ID.

> [card] [Claude API](https://apidoc.cometapi.com/quickstarts/text/claude-api.md)
>
> Send Anthropic-compatible Messages requests to Claude models through CometAPI.

> [card] [Gemini API](https://apidoc.cometapi.com/quickstarts/text/gemini-api.md)
>
> Start with Gemini native `generateContent`, or use OpenAI-compatible Chat Completions for existing SDK apps.

## Image APIs

> [card] [GPT Image API](https://apidoc.cometapi.com/quickstarts/image/gpt-image-api.md)
>
> Generate an image, decode `b64_json`, and save the result.

> [card] [Gemini image API](https://apidoc.cometapi.com/quickstarts/image/gemini-image-api.md)
>
> Generate images with Gemini image models, including Nano Banana model families.

> [card] [Flux API](https://apidoc.cometapi.com/quickstarts/image/flux-api.md)
>
> Create a Flux image task, poll for the result, and download it before the URL expires.

## Video APIs

> [card] [Veo 3 API](https://apidoc.cometapi.com/quickstarts/video/veo-3-api.md)
>
> Create a Veo video task with multipart form data and poll until completion.

> [card] [Kling API](https://apidoc.cometapi.com/quickstarts/video/kling-api.md)
>
> Submit a Kling text-to-video task and track it through polling or callbacks.

## Supporting guides

> [card] [Models](https://apidoc.cometapi.com/overview/models.md)
>
> Find available model IDs and route each model to the correct API page.

> [card] [Use OpenAI SDKs](https://apidoc.cometapi.com/guides/use-cometapi-with-openai-sdk.md)
>
> Configure OpenAI-compatible SDK clients with the CometAPI base URL.

> [card] [Estimate cost](https://apidoc.cometapi.com/guides/how-to-estimate-cost-before-calling-a-model.md)
>
> Plan budget guards before token, image, or video requests.

> [card] [Use webhooks and polling](https://apidoc.cometapi.com/guides/webhook-and-polling-for-video-generation.md)
>
> Track async video generation with task IDs, polling, and callbacks.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.