# Flux 3

Black Forest Labs's first video model. Flux 3 generates clips up to 20 seconds with audio produced alongside the picture rather than dubbed on afterwards, from text, a starting frame, or a reference clip.

- **Model ID:** `bfl/flux-3-video`
- **Type:** video
- **Providers:** bfl
- **Context window:** Not applicable
- **Maximum output tokens:** 0
- **Pricing:** See the provider details below
- **Canonical page:** https://vercel.com/ai-gateway/models/flux-3-video

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { experimental_generateVideo as generateVideo } from 'ai';

const result = await generateVideo({
  model: 'bfl/flux-3-video',
  prompt: 'A serene mountain lake at sunrise.'
});
```

## About

Flux 3 is Black Forest Labs's first public video model, from the team whose earlier work underpins much of open image generation. It generates clips up to 20 seconds with synchronized audio, at HD and Full HD.

The distinguishing property is that one set of weights handles images, video, and audio together rather than stitching separate models into a pipeline. Audio is produced with the picture, so dialogue lands in sync and lip movement matches without a separate dubbing pass. Multilingual dialogue is supported across a broad language set with lip-sync.

Generation modes cover text-to-video, image-to-video from a starting frame or visual reference, video-to-video from a reference clip, generative continuation of existing footage, and keyframe-to-video for controlled transitions between defined points. Clips can be chained agentically into longer multi-shot sequences, which is how you get past the 20 second ceiling.

Generate video with `generateVideo` from the AI SDK.

## What to consider

Preference results published at launch are company-run. Black Forest Labs reports Flux 3 winning most head-to-head comparisons against other video models, but the margins narrow considerably against the strongest of them, and sample sizes, rater counts, and methodology were not published. Generate your own comparisons before committing a production pipeline.

Output tops out at Full HD. If your pipeline needs 4K natively, this is not the model for it.

Video generation is slower and costlier per output than image generation, and iterating on a 20 second clip compounds both. Prototype at shorter durations and lower resolution, then generate the final at full length. See the pricing panel on this page for current rates.

## When to use

### Best For

- **Dialogue-driven clips** where audio is generated with the picture and lip-sync holds
- **Multi-shot sequences** chained agentically past the single-clip ceiling
- **Keyframe transitions** moving between defined points under direction
- **Reference-guided video** continuing from a starting frame or matching a reference clip
- **Multilingual output** with lip-sync across a broad language set

### Consider Alternatives When

- **Native 4K** is required, since output tops out at Full HD
- **Clips beyond 20 seconds** are needed in a single generation rather than chained
- **Independently verified quality** is required, since launch comparisons are company-run
- **Still images** are the output, where the FLUX image models are the right family

## Best for

- **Dialogue-Driven Clips:** Audio generated with the picture, lip-sync intact
- **Multi-Shot Sequences:** Agentic chaining past the single-clip ceiling
- **Keyframe Transitions:** Controlled movement between defined points
- **Reference-Guided Video:** Continuation from a frame or a reference clip
- **Multilingual Output:** Lip-sync across a broad language set

## Consider alternatives

- **Native 4K Output:** Resolution tops out at Full HD
- **Single Clips Past 20 Seconds:** Longer runs require agentic chaining
- **Independently Verified Quality:** Launch comparisons are company-run
- **Still Image Generation:** The FLUX image models are the right family

## Frequently asked questions

### How long can a Flux 3 clip be?

Up to 20 seconds in a single generation, at HD or Full HD. Longer sequences come from chaining clips agentically into multi-shot runs.

### Does Flux 3 generate audio?

Yes, synchronized with the picture rather than dubbed afterwards. Multilingual dialogue is supported with lip-sync across a broad language set.

### How do I call Flux 3 on AI Gateway?

Use `generateVideo` from the AI SDK with `bfl/flux-3-video`. The Chat Completions, Responses, and Messages APIs do not serve video generation.

### What generation modes does Flux 3 support?

Text-to-video, image-to-video from a starting frame or visual reference, video-to-video from a reference clip, generative continuation, and keyframe-to-video for controlled transitions.

### Does Flux 3 output 4K?

No. Output is released at HD and Full HD. Choose a different model if your pipeline requires native 4K.

### How reliable are the quality comparisons for Flux 3?

They are company-run preference tests. Black Forest Labs reports winning most head-to-head comparisons, with narrower margins against the strongest competitors, but sample sizes and methodology were not published. Generate your own comparisons before committing.

### Does Flux 3 support Zero Data Retention?

Zero Data Retention is not currently available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

## Links

- [Model page](https://vercel.com/ai-gateway/models/flux-3-video)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://bfl.ai/blog/flux-3)
- [Provider pricing](https://bfl.ai/pricing)