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

text-to-video
Use with AI GatewayView 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
OverviewAPIAboutProvidersSimilarFAQ

About 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.