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

Google positions Veo 3.1 Lite Generate as its most cost-effective video model and states that it matches the generation speed of Veo 3.1 Fast. Compare the rates on each model page for the current difference. Both sit below Veo 3.1 Generate, which applies full generation compute per request.

What durations and resolutions does Veo 3.1 Lite Generate support?

Durations of 4, 6, or 8 seconds at 720p or 1080p, in landscape (16:9) or portrait (9:16). Cost adjusts with the duration you request. See the Specs table on this page for provider-specific options.

Does Veo 3.1 Lite Generate generate audio?

Yes. Native audio generation runs across the Veo 3.1 family, covering ambient sound, effects, and dialogue described in the prompt, without a separate audio pass.

Does Veo 3.1 Lite Generate support image-to-video?

Yes. Provide a reference image alongside a text description and Veo 3.1 Lite Generate animates it with the motion the prompt describes. Text-to-video works the same way without an image.

When should I use Veo 3.1 Generate instead?

Use `google/veo-3.1-generate-001` when a clip is a deliverable and frame quality decides whether the output ships. Use Veo 3.1 Lite Generate when generation volume drives your cost and any single clip is one of many.

How is Veo 3.1 Lite Generate priced?

Rates for Veo 3.1 Lite Generate are listed on this page as N/A, and N/A breaks out the resolution and duration tiers. Duration is the main lever, so a 4-second clip costs less than an 8-second one. AI Gateway reflects provider pricing with no markup.

How do I use Veo 3.1 Lite Generate on AI Gateway?

Use the identifier `google/veo-3.1-lite-generate-001` with `generateVideo` from the AI SDK. AI Gateway handles provider routing and failover automatically.

How does Zero Data Retention work with Veo 3.1 Lite Generate through AI Gateway?

Yes, Zero Data Retention is 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.

Google

Veo 3.1 Lite Generate

Veo 3.1 Lite Generate is the cost-optimized tier of the Veo 3.1 family, supporting text-to-video and image-to-video with native audio at 720p and 1080p, built for high-volume video applications that generate continuously rather than one deliverable at a time.

View API reference

Price: $0.03, Per second
Lowest available configuration

Get API key Read the docs

import { experimental_generateVideo as generateVideo } from 'ai';

const result = await generateVideo({
  model: 'google/veo-3.1-lite-generate-001',
  prompt: 'A serene mountain lake at sunrise.'
});

Read docs

Overview Playground Providers API Similar About FAQ

Copy link to headingPlayground

Try out Veo 3.1 Lite Generate by Google. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

Veo 3.1 Lite Generate

Images(optional)

Add up to 3 images

Videos(optional)

Prompt(optional)

Your generated video will appear here.

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Provider

Input	Output	Capabilities	ZDR	No Training	Free Tier	Release Date

Google Vertex AI

Legal:Terms•Privacy

$0.03/sec+1 more

04/02/2026

Getting started

Generate videos with Veo 3.1 Lite Generate using the experimental_generateVideo function from AI SDK 6 or later. AI Gateway handles routing and polls until the video is ready.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the video generation quickstart.

index.ts

import { experimental_generateVideo as generateVideo } from 'ai';
import fs from 'node:fs';
import 'dotenv/config';

async function main() {
  const result = await generateVideo({
    model: 'google/veo-3.1-lite-generate-001',
    prompt: 'A drone shot of a coastal cliff with crashing waves at golden hour.',
  });

  // Save the generated video
  fs.writeFileSync('output.mp4', result.videos[0].uint8Array);

  console.log('Video saved to output.mp4');
}

main().catch(console.error);

Top-level parameters

Load the common, top-level parameters supported across video models.

top-level-params.ts

import { experimental_generateVideo as generateVideo } from 'ai';
import fs from 'node:fs';
import 'dotenv/config';

async function main() {
  const result = await generateVideo({
    model: 'google/veo-3.1-lite-generate-001',
    prompt: 'A drone shot of a coastal cliff with crashing waves at golden hour.',
    duration: 5,
    aspectRatio: '16:9',
    resolution: '1280x720',
  });

  // Save the generated video
  fs.writeFileSync('output.mp4', result.videos[0].uint8Array);

  console.log('Video saved to output.mp4');
}

main().catch(console.error);

Parameter	Type	Required	Description
`prompt`	`string`	No	Text description of the video to generate.
`duration`	`4 \| 6 \| 8`	No	Video length in seconds. 4 or 6 or 8 seconds.
`resolution`	`string`	No	Resolution ('1280x720', '1920x1080').
`aspectRatio`	`string`	No	Aspect ratio ('9:16', '16:9').

Input limits

Input	Formats	Sources	Max count	Max size	Limits
Image	jpg, jpeg, png	url, base64	3	20 MB	—
Video	mp4	url	1	—	—

Provider options

Pass provider-specific options under providerOptions.vertex.

provider-options.ts

import { experimental_generateVideo as generateVideo } from 'ai';
import fs from 'node:fs';
import 'dotenv/config';

async function main() {
  const result = await generateVideo({
    model: 'google/veo-3.1-lite-generate-001',
    prompt: 'A drone shot of a coastal cliff with crashing waves at golden hour.',
    duration: 5,
    providerOptions: {
      vertex: {
        pollTimeoutMs: 600000,
      },
    },
  });

  // Save the generated video
  fs.writeFileSync('output.mp4', result.videos[0].uint8Array);

  console.log('Video saved to output.mp4');
}

main().catch(console.error);

Pass these under providerOptions.vertex in your generateVideo call.

Parameter	Type	Required	Description
`providerOptions.vertex.pollIntervalMs`	`number`	No	How often to check task status. Defaults to `5000`.
`providerOptions.vertex.pollTimeoutMs`	`number`	No	Maximum wait time. Defaults to `600000` (10 minutes).

Copy link to headingMore models by Google

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

google/gemini-3.8-flash

1.9 s

417 tps

$0.75/M

$3.75/M

Read$0.08/M

$14/K+1 more

09/02/2026

google/gemini-3.7-flash

0.9 s

279 tps

$0.75/M

$3.75/M

Read$0.08/M

$14/K+1 more

08/13/2026

google/gemini-3.5-flash-lite

0.5 s

307 tps

$0.30/M

$2.50/M

Read$0.03/M

$14/K+1 more

07/21/2026

google/gemini-3.1-flash-lite

0.6 s

255 tps

$0.25/M

$1.50/M

Read$0.03/M

$14/K+1 more

05/07/2026

google/gemini-3-flash

0.6 s

199 tps

$0.50/M+1 more

$3/M+1 more

Read$0.05/M

$14/K+1 more

12/17/2025

google/gemini-2.5-flash-lite

0.3 s

271 tps

$0.10/M

$0.40/M

Read$0.01/M

$35/K+1 more

06/17/2025

Copy link to headingAbout Veo 3.1 Lite Generate

Veo 3.1 Lite Generate completes the Veo 3.1 family, released on April 2, 2026. Google positions it as its most cost-effective video model, aimed at developers building high-volume video applications, and states that it matches the generation speed of Veo 3.1 Fast. Cost, not turnaround, is what distinguishes the two tiers.

Veo 3.1 Lite Generate supports text-to-video and image-to-video with native audio generation, the capability shared across the whole Veo 3.1 family. Framing covers landscape (16:9) and portrait (9:16), output runs at 720p or 1080p, and duration is configurable at 4, 6, or 8 seconds with cost adjusting to the length you request.

The tier exists for applications where video generation is a continuous product feature rather than a production step. A social app that renders a clip for every post, a commerce catalog animating thousands of product shots, or a creative testing pipeline generating ad variants all hit a volume ceiling set by per-generation cost. Veo 3.1 Lite Generate raises that ceiling. Veo 3.1 Fast remains the iteration tier inside a creative workflow, and Veo 3.1 Generate remains the final-render tier for work that goes straight to distribution.

Rates for Veo 3.1 Lite Generate are listed on this page as N/A, with N/A breaking out resolution and duration tiers. Calling Veo 3.1 Lite Generate through AI Gateway adds usage and cost tracking, automatic retries, and provider failover on one API surface, which matters more across thousands of generations than it does for a single render.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: Duration is the direct cost lever on Veo 3.1 Lite Generate. Clips run 4, 6, or 8 seconds, and cost adjusts with the length you request, so trimming a pipeline from 8 seconds to 4 changes the unit economics of every generation you run. Confirm provider rate limits before you route sustained production volume, so batch jobs do not queue unexpectedly. Validate output quality against a representative sample of your prompts before you standardize a pipeline on Veo 3.1 Lite Generate, since Veo 3.1 Generate remains the quality ceiling of the family.
Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen to Use Veo 3.1 Lite Generate

Best for

High-Volume Video Applications: Per-generation cost sets the ceiling on how much video a product can render
Product Catalog Animation: Thousands of still product shots become short clips through image-to-video
Ad Variant Generation: Creative testing pipelines produce many versions of the same concept
User-Generated Video Features: A clip per user action stays economical at this tier
Rapid Prompt Iteration: Generation speed matches Veo 3.1 Fast at a lower listed rate

Consider alternatives when

Final Production Renders: google/veo-3.1-generate-001 applies full generation compute for finished deliverables
Maximum Motion Fidelity: Veo 3.1 Generate is the quality ceiling of the Veo 3.1 family
Conversational Video Editing: google/gemini-omni-flash-preview revises a clip across turns instead of regenerating
Still Image Output: google/imagen-4.0-fast-generate-001 returns images rather than video clips

Copy link to headingConclusion

Veo 3.1 Lite Generate is the tier to pick when video generation is a product feature rather than a production step. Text-to-video, image-to-video, and native audio all carry over from the rest of the Veo 3.1 family at the lowest listed rate in it, which is what makes continuous, high-volume generation practical.

Copy link to headingFrequently Asked Questions

How does Veo 3.1 Lite Generate differ from Veo 3.1 Fast?
Google positions Veo 3.1 Lite Generate as its most cost-effective video model and states that it matches the generation speed of Veo 3.1 Fast. Compare the rates on each model page for the current difference. Both sit below Veo 3.1 Generate, which applies full generation compute per request.
What durations and resolutions does Veo 3.1 Lite Generate support?
Durations of 4, 6, or 8 seconds at 720p or 1080p, in landscape (16:9) or portrait (9:16). Cost adjusts with the duration you request. See the Specs table on this page for provider-specific options.
Does Veo 3.1 Lite Generate generate audio?
Yes. Native audio generation runs across the Veo 3.1 family, covering ambient sound, effects, and dialogue described in the prompt, without a separate audio pass.
Does Veo 3.1 Lite Generate support image-to-video?
Yes. Provide a reference image alongside a text description and Veo 3.1 Lite Generate animates it with the motion the prompt describes. Text-to-video works the same way without an image.
When should I use Veo 3.1 Generate instead?
Use google/veo-3.1-generate-001 when a clip is a deliverable and frame quality decides whether the output ships. Use Veo 3.1 Lite Generate when generation volume drives your cost and any single clip is one of many.
How is Veo 3.1 Lite Generate priced?
Rates for Veo 3.1 Lite Generate are listed on this page as N/A, and N/A breaks out the resolution and duration tiers. Duration is the main lever, so a 4-second clip costs less than an 8-second one. AI Gateway reflects provider pricing with no markup.
How do I use Veo 3.1 Lite Generate on AI Gateway?
Use the identifier google/veo-3.1-lite-generate-001 with generateVideo from the AI SDK. AI Gateway handles provider routing and failover automatically.
How does Zero Data Retention work with Veo 3.1 Lite Generate through AI Gateway?
Yes, Zero Data Retention is 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.

Your use is subject to Google's Terms & Privacy Policies.

Agent Stack

Core Platform

Tools

Learn

Build

Explore

Veo 3.1 Lite Generate

Copy link to headingPlayground

Copy link to headingProviders

Getting started

Top-level parameters

Input limits

Provider options

Copy link to headingMore models by Google

Copy link to headingAbout Veo 3.1 Lite Generate

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use Veo 3.1 Lite Generate

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions

Advanced

Getting started

Top-level parameters

Input limits

Provider options

Best for

Consider alternatives when

Copy link to headingFrequently Asked Questions