# Nunchux AI Docs

> ## Agent Instructions
> Authenticate every request with your API key in the `X-API-Key` header or `Authorization: Bearer`. Keys start with `sk-nunchux-`.
> Image generation is synchronous: the image is in the response.
> Video generation is asynchronous: submit the job, poll its task until it reaches a terminal status, then download the output promptly, because output URLs expire.

- [Overview](https://docs.nunchux.ai/overview.md): Generate images and videos with one API key and one credit balance.
- [QuickStart](https://docs.nunchux.ai/quickstart.md): Get started generating images and videos with the Nunchux API in minutes.
- [Authentication](https://docs.nunchux.ai/authentication.md): Learn how to authenticate with the Nunchux API using API keys.
- [Performance Tiers](https://docs.nunchux.ai/performance-tiers.md): Balance speed and cost with the performance tiers of the Nunchux Image API.
- [Credits & Pricing](https://docs.nunchux.ai/credits-pricing.md): Understand how credits work for the Nunchux API.
- [Discounts](https://docs.nunchux.ai/discounts.md): A multiplier on list price, applied per entrypoint.
- [Rate Limits](https://docs.nunchux.ai/rate-limits.md): Per-plan caps on requests per minute and simultaneous jobs, which requests count toward each, and how to back off from a 429.
- [Errors](https://docs.nunchux.ai/errors.md): API error codes, response formats, and retry guidance for the Nunchux API.
- [Use Nunchux with coding agents](https://docs.nunchux.ai/coding-agents.md): Connect Claude Code, Cursor and other AI coding tools to the Nunchux docs through MCP, llms.txt, and Markdown versions of every page.
- [Overview](https://docs.nunchux.ai/nunchux-optimized/overview.md): Models optimized by Nunchux, served through Nunchux's own endpoints. One request returns the output.
- [Text-to-image](https://docs.nunchux.ai/nunchux-optimized/text-to-image.md): Generate an image from a text prompt with a Nunchux Optimized model. The image is in the response.
- [Image-to-image](https://docs.nunchux.ai/nunchux-optimized/image-to-image.md): Edit an image with a text prompt with a Nunchux Optimized model. The edited image is in the response.
- [Text-to-video](https://docs.nunchux.ai/nunchux-optimized/text-to-video.md): Generate a video clip from a text prompt with LTX. The clip is in the response.
- [Image-to-video](https://docs.nunchux.ai/nunchux-optimized/image-to-video.md): Animate a still image into a video clip with LTX. The clip is in the response.
- [OpenAI Compatibility](https://docs.nunchux.ai/nunchux-optimized/openai-compatibility.md): Use the OpenAI Python or JavaScript SDK with the Nunchux API for image generation.
- [Overview](https://docs.nunchux.ai/partner-models/overview.md): Third-party models served through your Nunchux key. Each provider keeps its own routes, request shapes and job lifecycle.
- [Nano Banana](https://docs.nunchux.ai/partner-models/nano-banana.md): Generate and edit images with Google's Nano Banana models in one synchronous call.
- [Veo 3.1](https://docs.nunchux.ai/partner-models/veo.md): Generate video with native audio from a text prompt or a starting image with Google's Veo 3.1 models.
- [Kling](https://docs.nunchux.ai/partner-models/kling.md): Kling V3 and Kling V3 Omni video generation with your Nunchux key: text-to-video, image-to-video, omni video and motion control.
- [Wan](https://docs.nunchux.ai/partner-models/wan.md): Alibaba Cloud's Wan video models for text-to-video, image-to-video and reference-to-video through one asynchronous endpoint.
- [HappyHorse](https://docs.nunchux.ai/partner-models/happyhorse.md): Alibaba Cloud's HappyHorse video models for text-to-video, image-to-video and reference-to-video, with a soundtrack on every clip.
- [Seedance](https://docs.nunchux.ai/partner-models/seedance.md): ByteDance's Seedance video model for text-to-video and image-to-video with generated audio.
- [MiniMax H3](https://docs.nunchux.ai/partner-models/minimax.md): MiniMax's H3 video model for text-to-video, image-to-video and reference-to-video through one asynchronous endpoint.
- [HeyGen Avatar](https://docs.nunchux.ai/partner-models/heygen.md): Turn a photo or a HeyGen avatar into a lip-synced talking-avatar video with HeyGen Avatar 4 Photo and Avatar 5 Digital, driven by audio or a script in a chosen voice.
- [Changelog](https://docs.nunchux.ai/changelog.md): Models available in the Nunchux playground and when they arrived: image, video, and avatar models, newest first.

## Optional

- [Status](https://www.nunchux.ai/status)
- [Blog](https://www.nunchux.ai/blog)


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