# Veo 3.0 Fast Generate

When your goal is moving through prompt variations quickly, Veo 3.0 Fast is the right starting point. It trades some output fidelity for shorter generation cycles, letting you test ideas, discard what doesn't work, and narrow in on the right approach before routing to a quality-focused model.

- **Model ID:** `google/veo-3.0-fast-generate-001`
- **Type:** video
- **Providers:** vertex
- **Context window:** Not applicable
- **Maximum output tokens:** 0
- **Pricing:** See the provider details below
- **Canonical page:** https://vercel.com/ai-gateway/models/veo-3.0-fast-generate-001

## Supported parameters

- **Parameters:** `aspectRatio`, `resolution`, `duration`, `fps`
- **Operations:** `text-to-video`, `image-to-video`
- **Input modalities:** `text`, `image`
- **Output modalities:** `video`, `audio`
- **Aspect ratios:** `16:9`, `9:16`
- **Resolutions:** `720p`, `1080p`
- **Durations:** `8s`
- **Frame rates:** `24 fps`
- **Maximum outputs per request:** Not reported
- **Maximum input images:** 1
- **Input image formats:** Not reported
- **Maximum input image size:** 20 MB

## Example

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

const result = await generateVideo({
  model: 'google/veo-3.0-fast-generate-001',
  prompt: 'A serene mountain lake at sunrise.'
});
```

## About

Veo 3.0 Fast Generate is the fast-tier variant of Google's Veo 3.0 video generation family. It launched simultaneously with the other Veo variants on AI Gateway as the model to use when iteration speed matters more than maximum fidelity.

Fast mode reduces per-generation latency. For a team building a video generation tool, that means running a dozen scene descriptions through the model in the time a single quality-tier generation might take, and finding which framing, style, or narrative direction works before investing in a full-quality pass. Despite the speed focus, the fast tier carries Veo 3.0's core capabilities. Enable native audio generation (sound effects, ambient audio, and synchronized dialogue) with `generateAudio: true` in `providerOptions.vertex`. Image-to-video is also supported, letting you animate a starting frame with natural motion.

For batch workflows like generating multiple versions of the same scene, testing audio-on versus audio-off, or comparing aspect ratios, the fast tier's lower latency compounds across a batch and significantly shortens the feedback loop.

## What to consider

This variant is designed for rapid iterations. That makes it a natural fit for the early and exploratory stages of any video generation workflow, and for batch jobs where generation volume matters more than squeezing every last bit of visual quality out of each clip.

## When to use

### Best For
- Prompt development phases where you need to test many scene descriptions and discard what doesn't work
- Batch video generation jobs where throughput volume is the constraint and per-clip quality is not the primary metric
- Previewing image-to-video animations before committing to a full-quality render of the final frame
- Building interactive prototypes or demos that need fast generation response times
- A/B testing prompt phrasing, framing, or audio settings across large sets of variations

### Consider Alternatives When
- The generation is a final deliverable and quality takes precedence over speed (consider `google/veo-3.0-generate-001`)
- You want fast iteration on the Veo 3.1 generation (consider `google/veo-3.1-fast-generate-001`)
- You need the highest-quality tier in the Veo 3.1 family (consider `google/veo-3.1-generate-001`)
- Your use case requires still images rather than video (consider the Imagen 4 family)

## Best for

- **Prompt development phases:** Testing many scene descriptions and discarding what doesn't work
- **Batch video generation:** Throughput volume is the constraint and per-clip quality is not the primary metric
- **Image-to-video previews:** Evaluate animations before committing to a full-quality render of the final frame
- **Interactive prototypes and demos:** Applications that need fast generation response times
- **A/B testing variations:** Prompt phrasing, framing, or audio settings across large sets

## Consider alternatives

- **Final deliverable quality:** Generation is a final deliverable and quality takes precedence over speed (consider `google/veo-3.0-generate-001`)
- **Veo 3.1 fast iteration:** You want rapid iteration on the 3.1 generation (consider `google/veo-3.1-fast-generate-001`)
- **Highest Veo 3.1 quality:** The top tier of the 3.1 family is required (consider `google/veo-3.1-generate-001`)
- **Still images required:** Video output is not needed (consider the Imagen 4 family)

## Frequently asked questions

### How much faster is fast mode compared to the standard generation tier?

Exact latency varies by clip length and prompt complexity. The fast tier produces noticeably shorter turnaround per generation compared to standard mode.

### Can I run a batch of prompt variations in parallel with this model?

Yes. AI Gateway supports concurrent requests. Running multiple fast-tier generations simultaneously is an effective way to evaluate a prompt space, generate many variations in parallel, review the results, and select which to advance to a quality-tier render.

### Does the fast tier produce lower quality output, and is that a problem?

The fast tier trades some fidelity for speed. For prompt exploration and iteration, this is usually fine: you are evaluating composition, motion, subject matter, and narrative, not evaluating every pixel. At the final-render stage, use `google/veo-3.0-generate-001` or a higher Veo tier.

### Does native audio work in fast mode?

Yes. Set `generateAudio: true` in `providerOptions.vertex`. The model generates synchronized sound effects, ambient audio, and dialogue even in fast mode, which is useful for previewing audio treatment before committing to a quality-tier render.

### Is there a cost-efficient workflow pattern for using fast and standard tiers together?

The standard workflow is to develop prompts on the fast tier, iterate until the output matches the creative direction, then route the finalized prompt to `google/veo-3.0-generate-001` for final output. Only the model slug changes between the two phases.

### Does image-to-video generation work with this model?

Yes. Pass a source image URL in your `generateVideo` call. The model animates the image with natural motion. Fast mode lets you preview how different starting frames behave before committing to full-quality animation.

### Is video generation in beta?

Yes. Video generation is in beta on AI Gateway, available to Pro and Enterprise plans and paid AI Gateway users.

### How do I call this model from the AI SDK?

Use `experimental_generateVideo` (aliased as `generateVideo`) from AI SDK 6 with `model: 'google/veo-3.0-fast-generate-001'`.

## Links

- [Model page](https://vercel.com/ai-gateway/models/veo-3.0-fast-generate-001)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/veo/3-0-generate#3.0-fast-generate-001)
- [Provider pricing](https://cloud.google.com/vertex-ai/generative-ai/pricing#veo)