# Veo 3.1 Fast Generate

Veo 3.1 architecture at reduced latency, built for workflows where generation volume and iteration speed matter as much as final output quality.

- **Model ID:** `google/veo-3.1-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-3.1-fast-generate-001

## Supported parameters

- **Parameters:** `aspectRatio`, `resolution`, `duration`, `fps`
- **Operations:** `text-to-video`, `image-to-video`
- **Input modalities:** `text`, `image`
- **Output modalities:** `video`
- **Aspect ratios:** `16:9`, `9:16`
- **Resolutions:** `1280x720`, `1920x1080`
- **Durations:** `4s`, `6s`, `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-3.1-fast-generate-001',
  prompt: 'A serene mountain lake at sunrise.'
});
```

## About

Veo 3.1 Fast Generate is the fast-tier configuration of the Veo 3.1 generation. It shares the same architecture as Veo 3.1 Generate but trades some generation compute for faster response times. This makes it the logical choice for exploratory and iterative phases of video production: generating multiple prompt variations, testing scene descriptions before committing to full-quality renders, and running batch jobs where throughput matters.

The Veo 3.1 generation brings improvements over 3.0 in motion quality and prompt adherence. Veo 3.1 Fast Generate carries those improvements into the fast tier. Teams upgrading from Veo 3.0 Fast get better generation quality at similar or improved latency. For new projects starting on Veo 3.1, this is the recommended fast-tier entry point over Veo 3.0 Fast.

Parallel generation workflows benefit particularly from the reduced per-generation latency. A batch of 10 prompt variations completes faster, and the quicker turnaround supports tighter feedback loops between creative direction and generation output.

## What to consider

For high-frequency batch generation, confirm provider rate limits before routing production load to ensure generation jobs do not queue unexpectedly.

## When to use

### Best For

**Prompt iteration and A/B testing at scale:** Generate multiple variations of a scene description quickly, evaluate which direction works, then use Veo 3.1 Generate for the final render of the selected approach.

**Parallel batch generation:** Running many concurrent generation jobs (advertising variants, scene options, visual development exploration) benefits from the lower per-job latency and faster batch completion.

**New projects on the Veo 3.1 generation:** For teams starting fresh, Veo 3.1 Fast Generate is the recommended fast-tier entry point; it carries 3.1's generation improvements over choosing Veo 3.0 Fast instead.

**High-frequency creative pipelines:** Workflows where video is generated and reviewed continuously (content moderation testing, generative art pipelines, automated video production systems) benefit from the throughput of the fast tier.

### Consider Alternatives When

**Final production-quality output is the goal:** Veo 3.1 Generate applies full generation compute to each request and is more appropriate for final deliverables than for exploratory generation.

**Existing workflows are tuned to Veo 3.0:** If prompt tuning and output validation was done against Veo 3.0 Fast, migrating to 3.1 Fast should be validated before replacing production traffic.

**Maximum Veo 3.1 quality regardless of speed:** Veo 3.1 Generate is the quality ceiling within the Veo 3.1 family.

## Best for

- **Prompt iteration and A/B testing at scale:** Generate multiple variations of a scene description quickly, evaluate which direction works, then use Veo 3.1 Generate for the final render of the selected approach
- **Parallel batch generation:** Running many concurrent generation jobs (advertising variants, scene options, visual development exploration) benefits from the lower per-job latency and faster batch completion
- **New projects on the Veo 3.1 generation:** For teams starting fresh, Veo 3.1 Fast Generate is the recommended fast-tier entry point; it carries 3.1's generation improvements over choosing Veo 3.0 Fast instead
- **High-frequency creative pipelines:** Workflows where video is generated and reviewed continuously (content moderation testing, generative art pipelines, automated video production systems) benefit from the throughput of the fast tier

## Consider alternatives

- **Final production-quality output is the goal:** Veo 3.1 Generate applies full generation compute to each request and is more appropriate for final deliverables than for exploratory generation
- **Existing workflows are tuned to Veo 3.0:** If prompt tuning and output validation was done against Veo 3.0 Fast, migrating to 3.1 Fast should be validated before replacing production traffic
- **Maximum Veo 3.1 quality regardless of speed:** Veo 3.1 Generate is the quality ceiling within the Veo 3.1 family

## Frequently asked questions

### How does Veo 3.1 Fast Generate differ from Veo 3.0 Fast Generate?

Veo 3.1 Fast Generate is the Veo 3.1 generation. The 3.1 generation brings motion quality and prompt adherence improvements over 3.0. For new projects in the fast tier, 3.1 Fast is the recommended choice over 3.0 Fast.

### How does Veo 3.1 Fast Generate differ from Veo 3.1 Generate?

Both are Veo 3.1 generation models. Fast Generate uses reduced generation compute for lower latency, appropriate for iteration and batch work. Standard Generate applies full compute for production-quality output.

### What is the ideal workflow combining both Veo 3.1 variants?

Use Veo 3.1 Fast Generate for prompt exploration and variation generation. Once a direction is validated, run the selected prompt through Veo 3.1 Generate for the final production-quality render.

### Does Veo 3.1 Fast Generate support image-to-video generation?

Yes, image-to-video is supported alongside text-to-video at the fast-tier latency profile.

### What resolution and duration does Veo 3.1 Fast Generate support?

Up to 1080p. Duration and aspect ratios depend on the provider; see the Specs table on this page for details.

### How do I use Veo 3.1 Fast Generate on AI Gateway?

Use the identifier `google/veo-3.1-fast-generate-001` with the generateVideo interface. AI Gateway handles provider routing automatically.

## Links

- [Model page](https://vercel.com/ai-gateway/models/veo-3.1-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/3-1-generate#3.1-fast-generate-001)
- [Provider pricing](https://cloud.google.com/vertex-ai/generative-ai/pricing#veo)