> ## 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.

> ## Agent Instructions
> fal has two developer products. Model APIs run hosted models through an API key. fal Serverless deploys your own Python apps and models on fal GPUs.
> To call a hosted model, start with the [Quick Start](https://fal.ai/docs/documentation/quickstart.md) and the [Model APIs overview](https://fal.ai/docs/documentation/model-apis/overview.md).
> To deploy your own model with fal Serverless, start with these pages:
> - [Introduction to Serverless](https://fal.ai/docs/documentation/serverless/index.md): What fal Serverless is and the three ways to deploy on it.
> - [Installation & Setup](https://fal.ai/docs/documentation/development/getting-started/installation.md): Install the fal CLI with `pip install fal` and authenticate.
> - [Quick Start](https://fal.ai/docs/documentation/development/getting-started/quick-start.md): Build a Hello World app, test it with `fal run`, and ship it with `fal deploy`.
> - [App Lifecycle](https://fal.ai/docs/documentation/development/app-lifecycle.md): How a `fal.App` goes from code to running runners.
> - [Define Your Endpoints](https://fal.ai/docs/documentation/development/endpoints-overview.md): Structure the API endpoints that your app exposes.
> - [Deploy to Production](https://fal.ai/docs/documentation/deployment/deploy-to-production.md): Persistent URLs, authentication modes, and automatic scaling.
> - [Machine Types](https://fal.ai/docs/documentation/deployment/machine-types.md): Available GPU and CPU machine types and how to choose one.
> - [Pricing](https://fal.ai/docs/documentation/serverless/pricing.md): Per-second billing and the runner states that are billed.
> - [Scaling Parameter Reference](https://fal.ai/docs/documentation/deployment/scale-your-application.md): Parameters that control runners, concurrency, and scale to zero.
> - [Optimizing Cold Starts](https://fal.ai/docs/documentation/serverless/optimizations/optimize-cold-starts.md): Causes of cold starts and ways to make them shorter.
> - [Examples](https://fal.ai/docs/examples/index.md): Complete Serverless apps for image, video, audio, 3D, realtime, and multi-GPU workloads.
> - [Migrating to fal](https://fal.ai/docs/documentation/development/migrating-to-fal.md): Guides to move an existing Docker server or an app from another platform to fal.
> fal Serverless deploys need access that the fal team approves for each account. Request access at https://fal.ai/dashboard/serverless-get-started.

# Available Models

> Endpoint IDs, inputs, outputs, and typical uses of the top fal models for video, image, audio, vision, and 3D.

This page lists the top models for each task. Pass the **Endpoint ID** to any [client library](/docs/documentation/model-apis/inference/client-setup) or to `https://queue.fal.run/<endpoint-id>`.

<Note>
  fal hosts 1,000+ models. Browse every model on [fal.ai/models](https://fal.ai/models), or list them programmatically with [`GET /v1/models`](/docs/api-reference/platform-apis/for-models). For per-model costs, see [Pricing](/docs/documentation/model-apis/pricing).
</Note>

**Input → Output** lists the media types that an endpoint accepts and returns. Under each model, **API** links to the endpoint's schema and code examples, and **Model page** links to its playground on fal.ai. Most models have more than one endpoint, for example text-to-video and image-to-video. The model page lists all of them.

## Generate Video

Create video from a text prompt, a starting image, or audio.

| Model | When to use | Endpoint ID | Input → Output |
| :- | :- | :- | :- |
| **MiniMax H3 Max Text to Video**<br />[API](https://fal.ai/models/minimax/h3-max/text-to-video/api) · [Model page](https://fal.ai/models/minimax/h3-max/text-to-video) | Default for most text-to-video. Up to 15s at 480p or 768p, and closely follows prompts | `minimax/h3-max/text-to-video` | Text, Audio → Video |
| **Kling Video v3 Image to Video \[Pro]**<br />[API](/docs/model-api-reference/video-generation-api/kling-video-v3-pro) · [Model page](https://fal.ai/models/fal-ai/kling-video/v3/pro/image-to-video) | Animating a still into a cinematic shot with native audio | `fal-ai/kling-video/v3/pro/image-to-video` | Text, Image → Video |
| **Flashtalk**<br />[API](https://fal.ai/models/fal-ai/flashtalk/api) · [Model page](https://fal.ai/models/fal-ai/flashtalk) | Talking-head video from one portrait photo plus a voice clip | `fal-ai/flashtalk` | Image, Audio → Video |
| **H3 Max Turbo Text to Video**<br />[API](https://fal.ai/models/minimax/h3-max-turbo/text-to-video/api) · [Model page](https://fal.ai/models/minimax/h3-max-turbo/text-to-video) | Cheaper H3 Max for drafts and high-volume runs | `minimax/h3-max-turbo/text-to-video` | Text, Audio → Video |
| **LTX 2.3 Pro Audio to Video**<br />[API](https://fal.ai/models/fal-ai/ltx-2.3/audio-to-video/api) · [Model page](https://fal.ai/models/fal-ai/ltx-2.3/audio-to-video) | Lightricks LTX 2.3 Pro, for video synchronized to an audio clip, with an optional starting image | `fal-ai/ltx-2.3/audio-to-video` | Text, Image, Audio → Video |
| **Seedance 2.5 Text to Video**<br />[API](https://fal.ai/models/bytedance/seedance-2.5/text-to-video/api) · [Model page](https://fal.ai/models/bytedance/seedance-2.5/text-to-video) | Long single takes (16–30s), exact 720p or 1080p, and synchronized audio | `bytedance/seedance-2.5/text-to-video` | Text → Video |

## Edit and Transform Video

Edit, restyle, dub, upscale, extend, or otherwise transform an existing video.

| Model | When to use | Endpoint ID | Input → Output |
| :- | :- | :- | :- |
| **Kling O3 Edit Video \[Pro]**<br />[API](/docs/model-api-reference/video-generation-api/kling-video-o3-pro-video-to-video) · [Model page](https://fal.ai/models/fal-ai/kling-video/o3/pro/video-to-video/edit) | Changing existing footage with a text prompt (restyle, swap, or remove elements) | `fal-ai/kling-video/o3/pro/video-to-video/edit` | Text, Image, Video → Video |
| **ElevenLabs Dubbing**<br />[API](https://fal.ai/models/fal-ai/elevenlabs/dubbing/api) · [Model page](https://fal.ai/models/fal-ai/elevenlabs/dubbing) | Translating the dialogue in a video or audio file into another language | `fal-ai/elevenlabs/dubbing` | Video, Audio → Video |
| **sync-3 Lipsync**<br />[API](https://fal.ai/models/fal-ai/sync-lipsync/v3/api) · [Model page](https://fal.ai/models/fal-ai/sync-lipsync/v3) | Matching lip movement in existing video to a new audio track. Newest sync model | `fal-ai/sync-lipsync/v3` | Video, Audio → Video |
| **Wan 3.0 Prime Reference to Video**<br />[API](https://fal.ai/models/alibaba/wan-3.0-prime/reference-to-video/api) · [Model page](https://fal.ai/models/alibaba/wan-3.0-prime/reference-to-video) | Keeping a character consistent across shots from image, video, and audio references. Also accepts a document or webpage URL as a reference | `alibaba/wan-3.0-prime/reference-to-video` | Text, Image, Video, Audio → Video |
| **Kling 3.0 Pro Motion Control**<br />[API](/docs/model-api-reference/video-generation-api/kling-video-v3-pro) · [Model page](https://fal.ai/models/fal-ai/kling-video/v3/pro/motion-control) | Moving a character to match the motion in a reference video | `fal-ai/kling-video/v3/pro/motion-control` | Text, Image, Video → Video |
| **ByteDance Video Upscaler**<br />[API](https://fal.ai/models/fal-ai/bytedance-upscaler/upscale/video/api) · [Model page](https://fal.ai/models/fal-ai/bytedance-upscaler/upscale/video) | Raising the resolution of existing video | `fal-ai/bytedance-upscaler/upscale/video` | Video → Video |

## Generate Images

Create images from a text prompt.

| Model | When to use | Endpoint ID | Input → Output |
| :- | :- | :- | :- |
| **FLUX.1 \[schnell]**<br />[API](/docs/model-api-reference/image-generation-api/flux-schnell) · [Model page](https://fal.ai/models/fal-ai/flux/schnell) | Fastest drafts in 1–4 steps, good for quick iteration | `fal-ai/flux/schnell` | Text → Image |
| **Nano Banana Pro**<br />[API](/docs/model-api-reference/image-generation-api/nano-banana-pro) · [Model page](https://fal.ai/models/fal-ai/nano-banana-pro) | Complex graphic design, precise brand work, and product mockups | `fal-ai/nano-banana-pro` | Text → Image |
| **GPT Image 2**<br />[API](https://fal.ai/models/openai/gpt-image-2/api) · [Model page](https://fal.ai/models/openai/gpt-image-2) | High-fidelity images with dense or exact typography | `openai/gpt-image-2` | Text → Image |
| **GPT Image 2.5 Flare Text to Image**<br />[API](https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image/api) · [Model page](https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image) | OpenAI's standard GPT Image 2.5 for general prompts | `openai/gpt-image-2.5/flare/text-to-image` | Text → Image |
| **Nano Banana 2.1**<br />[API](https://fal.ai/models/google/nano-banana-2.1/api) · [Model page](https://fal.ai/models/google/nano-banana-2.1) | Default text-to-image, including text, infographics, and consistent people or products. 1K–4K, up to 14 references | `google/nano-banana-2.1` | Text → Image |
| **Flux 2 Pro**<br />[API](/docs/model-api-reference/image-generation-api/flux-2-pro) · [Model page](https://fal.ai/models/fal-ai/flux-2-pro) | Production-ready images with no step or guidance tuning, and predictable batch results | `fal-ai/flux-2-pro` | Text → Image |

## Edit and Transform Images

Edit, restyle, upscale, segment, or otherwise transform existing images.

| Model | When to use | Endpoint ID | Input → Output |
| :- | :- | :- | :- |
| **Nano Banana Pro Edit**<br />[API](/docs/model-api-reference/image-generation-api/nano-banana-pro) · [Model page](https://fal.ai/models/fal-ai/nano-banana-pro/edit) | Brand and product edits that need Pro's established look | `fal-ai/nano-banana-pro/edit` | Text, Image → Image |
| **GPT Image 2.5 Sunburst Edit**<br />[API](https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit/api) · [Model page](https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit) | Small, targeted changes repeated across many rounds without drift | `openai/gpt-image-2.5/sunburst/edit` | Text, Image → Image |
| **GPT Image 2 Edit**<br />[API](https://fal.ai/models/openai/gpt-image-2/edit/api) · [Model page](https://fal.ai/models/openai/gpt-image-2/edit) | Edits that add or fix text and fine detail | `openai/gpt-image-2/edit` | Text, Image → Image |
| **Nano Banana 2.1 Edit**<br />[API](https://fal.ai/models/google/nano-banana-2.1/edit/api) · [Model page](https://fal.ai/models/google/nano-banana-2.1/edit) | Default image edit. Semantic and region edits, up to 14 reference images, 1K–4K | `google/nano-banana-2.1/edit` | Text, Image, Video → Image |
| **Nano Banana Edit**<br />[API](/docs/model-api-reference/image-generation-api/nano-banana) · [Model page](https://fal.ai/models/fal-ai/nano-banana/edit) | Basic edits where cost matters more than resolution | `fal-ai/nano-banana/edit` | Text, Image → Image |
| **BiRefNet v2 Background Removal**<br />[API](/docs/model-api-reference/image-generation-api/birefnet) · [Model page](https://fal.ai/models/fal-ai/birefnet/v2) | Removing image backgrounds with high-resolution segmentation | `fal-ai/birefnet/v2` | Image → Image |

## Generate Audio

Create speech, music, and sound effects.

| Model | When to use | Endpoint ID | Input → Output |
| :- | :- | :- | :- |
| **ElevenLabs Eleven v4**<br />[API](https://fal.ai/models/elevenlabs/tts/eleven-v4/api) · [Model page](https://fal.ai/models/elevenlabs/tts/eleven-v4) | Expressive text-to-speech, with emotion and delivery directed by audio tags | `elevenlabs/tts/eleven-v4` | Text → Audio |
| **ElevenLabs Sound Effects v2**<br />[API](https://fal.ai/models/fal-ai/elevenlabs/sound-effects/v2/api) · [Model page](https://fal.ai/models/fal-ai/elevenlabs/sound-effects/v2) | Sound effects from a short text description | `fal-ai/elevenlabs/sound-effects/v2` | Text → Audio |
| **Sonilo v1.1 Video to Sound Effects**<br />[API](https://fal.ai/models/sonilo/v1.1/video-to-sound-effects/api) · [Model page](https://fal.ai/models/sonilo/v1.1/video-to-sound-effects) | Sonilo v1.1, for sound effects timed to the action in a video | `sonilo/v1.1/video-to-sound-effects` | Text, Video → Audio |
| **MiniMax Speech 2.8 \[HD]**<br />[API](https://fal.ai/models/fal-ai/minimax/speech-2.8-hd/api) · [Model page](https://fal.ai/models/fal-ai/minimax/speech-2.8-hd) | HD tier of MiniMax Speech 2.8, for high-quality speech in many voices | `fal-ai/minimax/speech-2.8-hd` | Text → Audio |
| **ElevenLabs Music**<br />[API](https://fal.ai/models/fal-ai/elevenlabs/music/api) · [Model page](https://fal.ai/models/fal-ai/elevenlabs/music) | ElevenLabs' music model, for songs with fine-grained controls | `fal-ai/elevenlabs/music` | Text → Audio |
| **Mirelo SFX v1.5 Video to Audio**<br />[API](https://fal.ai/models/mirelo-ai/sfx-v1.5/video-to-audio/api) · [Model page](https://fal.ai/models/mirelo-ai/sfx-v1.5/video-to-audio) | Synced sound effects for an existing video, returned as a new soundtrack | `mirelo-ai/sfx-v1.5/video-to-audio` | Text, Video → Audio |

## Process Audio

Transcribe speech, convert voices, and transform audio.

| Model | When to use | Endpoint ID | Input → Output |
| :- | :- | :- | :- |
| **ElevenLabs Speech to Text - Scribe V2**<br />[API](https://fal.ai/models/fal-ai/elevenlabs/speech-to-text/scribe-v2/api) · [Model page](https://fal.ai/models/fal-ai/elevenlabs/speech-to-text/scribe-v2) | ElevenLabs Scribe v2, for fast speech-to-text | `fal-ai/elevenlabs/speech-to-text/scribe-v2` | Audio → Text |
| **NVIDIA Nemotron 3 Nano Omni Audio**<br />[API](https://fal.ai/models/nvidia/nemotron-3-nano-omni/audio/api) · [Model page](https://fal.ai/models/nvidia/nemotron-3-nano-omni/audio) | Audio variant of NVIDIA Nemotron 3 Nano Omni, for questions about audio | `nvidia/nemotron-3-nano-omni/audio` | Text, Audio → Text |
| **Demucs**<br />[API](https://fal.ai/models/fal-ai/demucs/api) · [Model page](https://fal.ai/models/fal-ai/demucs) | Source-separation model, for splitting vocals, drums, bass, and other stems | `fal-ai/demucs` | Audio → Audio |
| **Resemble AI Chatterbox HD Speech to Speech**<br />[API](https://fal.ai/models/resemble-ai/chatterboxhd/speech-to-speech/api) · [Model page](https://fal.ai/models/resemble-ai/chatterboxhd/speech-to-speech) | Resemble AI Chatterbox, for voice conversion with built-in watermarking | `resemble-ai/chatterboxhd/speech-to-speech` | Audio → Audio |
| **Wizper (Whisper v3, fal edition)**<br />[API](https://fal.ai/models/fal-ai/wizper/api) · [Model page](https://fal.ai/models/fal-ai/wizper) | fal-optimized Whisper v3 Large, with the same accuracy at about twice the speed | `fal-ai/wizper` | Audio → Text |
| **Silero VAD**<br />[API](https://fal.ai/models/fal-ai/silero-vad/api) · [Model page](https://fal.ai/models/fal-ai/silero-vad) | Lightweight voice activity detector, for speech timestamps | `fal-ai/silero-vad` | Audio → Text |

## Vision

Caption, describe, detect, and answer questions about images and video.

| Model | When to use | Endpoint ID | Input → Output |
| :- | :- | :- | :- |
| **OpenRouter \[Vision]**<br />[API](/docs/model-api-reference/vision-api/openrouter-router) · [Model page](https://fal.ai/models/openrouter/router/vision) | Router to many vision-language models (Claude, GPT, Gemini, and others) through one endpoint | `openrouter/router/vision` | Text, Image → Text |
| **NVIDIA Nemotron 3 Nano Omni Vision**<br />[API](https://fal.ai/models/nvidia/nemotron-3-nano-omni/vision/api) · [Model page](https://fal.ai/models/nvidia/nemotron-3-nano-omni/vision) | Vision variant of NVIDIA Nemotron 3 Nano Omni, for visual reasoning | `nvidia/nemotron-3-nano-omni/vision` | Text, Image → Text |
| **NSFW Filter**<br />[API](/docs/model-api-reference/vision-api/imageutils) · [Model page](https://fal.ai/models/fal-ai/imageutils/nsfw) | Lightweight classifier, for NSFW probability scores | `fal-ai/imageutils/nsfw` | Image → Text |
| **NSFW Checker**<br />[API](https://fal.ai/models/fal-ai/x-ailab/nsfw/api) · [Model page](https://fal.ai/models/fal-ai/x-ailab/nsfw) | Lightweight classifier, for yes/no NSFW checks | `fal-ai/x-ailab/nsfw` | Image → Text |
| **Video Understanding**<br />[API](https://fal.ai/models/fal-ai/video-understanding/api) · [Model page](https://fal.ai/models/fal-ai/video-understanding) | Video question answering, for describing what happens in a video | `fal-ai/video-understanding` | Text, Image, Video → Text |
| **Moondream 3 Preview Detect**<br />[API](https://fal.ai/models/fal-ai/moondream3-preview/detect/api) · [Model page](https://fal.ai/models/fal-ai/moondream3-preview/detect) | Moondream 3 preview, for low-cost detection, pointing, and OCR | `fal-ai/moondream3-preview/detect` | Text, Image → Text |

## Generate 3D

Create and process 3D assets from text, images, or meshes.

| Model | When to use | Endpoint ID | Input → Output |
| :- | :- | :- | :- |
| **Tripo H3.1 Text to 3D**<br />[API](https://fal.ai/models/tripo3d/h3.1/text-to-3d/api) · [Model page](https://fal.ai/models/tripo3d/h3.1/text-to-3d) | Tripo H3.1, for 3D models from a text prompt | `tripo3d/h3.1/text-to-3d` | Text → 3D |
| **Hunyuan 3D Pro Image to 3D**<br />[API](/docs/model-api-reference/3d-api/hunyuan-3d-v3.1-pro) · [Model page](https://fal.ai/models/fal-ai/hunyuan-3d/v3.1/pro/image-to-3d) | Pro tier of Tencent Hunyuan 3D v3.1, for 3D models from images | `fal-ai/hunyuan-3d/v3.1/pro/image-to-3d` | Image → 3D |
| **Meshy Rigging**<br />[API](https://fal.ai/models/fal-ai/meshy/rigging/api) · [Model page](https://fal.ai/models/fal-ai/meshy/rigging) | Meshy's rigging model, for rigging humanoid models with basic animations | `fal-ai/meshy/rigging` | 3D → 3D |
| **Hunyuan Motion \[1B]**<br />[API](https://fal.ai/models/fal-ai/hunyuan-motion/api) · [Model page](https://fal.ai/models/fal-ai/hunyuan-motion) | Tencent's 1B-parameter Hunyuan Motion, for 3D human motion from text | `fal-ai/hunyuan-motion` | Text → 3D |
| **Trellis 2**<br />[API](/docs/model-api-reference/3d-api/trellis-2) · [Model page](https://fal.ai/models/fal-ai/trellis-2) | Microsoft Trellis 2, for high-quality 3D assets from images | `fal-ai/trellis-2` | Image → 3D |
| **Meshy 6 Lite Retexture**<br />[API](https://fal.ai/models/meshy/v6-lite/retexture/api) · [Model page](https://fal.ai/models/meshy/v6-lite/retexture) | Lite tier of Meshy 6, for retexturing existing models with PBR maps | `meshy/v6-lite/retexture` | 3D → 3D |