Video Generation Model

Veo 3.1 Lite

Veo 3.1 Lite is a video generation model from Google designed for fast, low-cost video creation with audio support.

Start Building with Veo 3.1 Lite View All Models

Publisher

Google

TypeVideo

Context Window1,000 tokens

ReleasedMarch 2026

Price$0.05–$0.08/second

FASTLOW COST

Try Veo 3.1 Lite →

About Veo 3.1 Lite

Fast, low-cost video generation from Google

Veo 3.1 Lite is a video generation model developed by Google, released in March 2026 as part of the Veo model family. It accepts text prompts and image inputs to generate video clips, and supports optional audio generation alongside video output. The model is tagged as fast and low cost, positioning it as an accessible option for workflows that require quick turnaround or high-volume generation.

The model offers a range of configurable inputs including aspect ratio, resolution, duration, and seed control, giving users meaningful control over output format and reproducibility. It also supports image-to-video generation by accepting both a starting frame and a last frame image, enabling interpolation-style workflows. A built-in prompt enhancement option allows the model to automatically refine text prompts before generation.

Capabilities

What Veo 3.1 Lite supports

Text-to-Video

Generates video clips from text prompts with up to 1000 tokens of prompt context. An auto-enhance option can refine prompts before generation.

Image-to-Video

Accepts an input image as the first frame to animate, enabling video generation grounded in a specific visual starting point.

Last Frame Control

Accepts a second image as the last frame, allowing the model to generate video that interpolates between a defined start and end visual.

Audio Generation

Optionally generates audio alongside video output, controlled via a toggle input at generation time.

Aspect Ratio & Resolution

Supports selectable aspect ratios and resolution settings so output dimensions can be matched to the target use case.

Seed Control

Accepts a seed value to make generation reproducible, useful for iterating on a prompt while holding other variables constant.

Negative Prompting

Accepts a negative prompt to steer the model away from unwanted visual elements or styles in the output.

Fast Generation

Tagged as a fast model, making it suited for workflows that require quick iteration or high-volume video generation.

Low Cost Operation

Tagged as low cost, making it a practical choice for budget-conscious projects or large-scale generation pipelines.

Ready to build with Veo 3.1 Lite?

Get Started Free

FAQ

Common questions about Veo 3.1 Lite

What is the context window for Veo 3.1 Lite?

Veo 3.1 Lite has a context window of 1000 tokens, which applies to the text prompt used to guide video generation.

Does Veo 3.1 Lite support audio in generated videos?

Yes. The model includes an optional audio generation toggle, allowing users to include or exclude audio in the output video.

Can I use an existing image as input to Veo 3.1 Lite?

Yes. The model accepts an input image as the first frame and optionally a second image as the last frame, enabling image-to-video and frame-interpolation workflows.

What output formats and resolutions does Veo 3.1 Lite support?

The model supports selectable aspect ratios, resolutions, and durations via toggle inputs. Specific resolution and duration values are configured at generation time within MindStudio.

When was Veo 3.1 Lite released?

Veo 3.1 Lite was released in March 2026 by Google.

How is pricing structured for Veo 3.1 Lite?

Specific published pricing is not listed in the available metadata. The model is tagged as low cost, and pricing details can be confirmed through MindStudio or Google's official channels.

Resources