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

# Model API Reference

> Complete API reference for fal.ai's image, video, audio, vision, and 3D generation models on fal.ai.

API reference for top models on fal.ai — complete input/output schemas, code examples in Python, JavaScript, and cURL, plus real prompt-and-output examples.

Whether you're generating images with FLUX or Nano Banana, creating videos with Seedance or Kling, synthesizing audio with ElevenLabs, or building 3D assets — find the full API documentation for each endpoint below.

<Card title="Explore All Models" icon="grid" href="https://fal.ai/models">
  Browse and try all models interactively on fal.ai
</Card>

## Models by Category

<CardGroup cols={2}>
  <Card title="Video Generation API" href="/model-api-reference/video-generation-api/overview">
    Generate videos from text prompts or images using cutting-edge video generation models. 59 models documented.

    <Frame>
      <img src="https://v3b.fal.media/files/b/0a9460e7/626QXDcTbiOI5I3LPidrR_1ae86d7b0fbb47b3b6d1a41e7fc00956.jpg" alt="Video Generation example" noZoom />
    </Frame>
  </Card>

  <Card title="Image Generation API" href="/model-api-reference/image-generation-api/overview">
    Generate and edit images using state-of-the-art diffusion and transformer models. 59 models documented.

    <Frame>
      <img src="https://v3b.fal.media/files/b/0a900b9e/ptbZcVWIQ_fXGGHfv8Zez_0ea5ca41bdf143a29e21e30a53120672.jpg" alt="Image Generation example" noZoom />
    </Frame>
  </Card>

  <Card title="Audio API" href="/model-api-reference/audio-api/overview">
    Models for audio processing including text-to-speech, speech-to-text, voice cloning, and music generation.. 5 models documented.

    <Frame>
      <img src="https://storage.googleapis.com/falserverless/gallery/whisper.jpg" alt="Audio example" noZoom />
    </Frame>
  </Card>

  <Card title="Vision API" href="/model-api-reference/vision-api/overview">
    Models for understanding and analyzing images, including captioning, visual question answering, and object detection.. 3 models documented.

    <Frame>
      <img src="https://v3b.fal.media/files/b/penguin/v-wl5CGbHxNVatcGXntIY_e14c7922d88348769a90469d1c206501.jpg" alt="Vision example" noZoom />
    </Frame>
  </Card>

  <Card title="3D API" href="/model-api-reference/3d-api/overview">
    Generate 3D assets from text or images using AI models. 6 models documented.

    <Frame>
      <img src="https://v3b.fal.media/files/b/0a87573c/DwQCx7YBl36dnFSHaU8OT_bfc26b64d210462489530b5d5d5d98e1.jpg" alt="3D example" noZoom />
    </Frame>
  </Card>
</CardGroup>

## Getting Started

New to fal.ai? Check out these resources:

* [Model APIs Overview](/documentation/model-apis/overview) — How to call model APIs
* [Authentication](/documentation/authentication) — Set up your API key
* [Explore Models](https://fal.ai/models) — Browse and try models interactively
* [fal.ai Pricing](https://fal.ai/pricing) — Pricing details for all models