Video Generation Model

Veo 3.1 Fast

Veo 3.1 Fast is a video generation model from Google designed for rapid text-to-video and image-to-video synthesis.

Start Building with Veo 3.1 Fast View All Models

Publisher

Google

TypeVideo

Context Window1,000 tokens

ReleasedOctober 2025

Price$0.10–$0.35/second

FAST

Try Veo 3.1 Fast →

About Veo 3.1 Fast

Fast video generation from text and images

Veo 3.1 Fast is a video generation model developed by Google, released in October 2025 as part of the Veo model family. It accepts text prompts and image inputs to produce video outputs, and is tagged as a fast variant, indicating it is optimized for lower-latency generation compared to standard Veo releases. The model supports a context window of 1,000 tokens and is available directly through MindStudio without requiring separate API credentials.

Veo 3.1 Fast is suited for workflows that require quick video drafts, iterative creative exploration, or production pipelines where turnaround speed matters. It supports configurable options including duration, aspect ratio, resolution, audio generation, and prompt auto-enhancement, as well as first-frame and last-frame image conditioning for more controlled outputs. Reference image inputs are also supported, giving users additional tools to guide the visual style or content of generated videos.

Capabilities

What Veo 3.1 Fast supports

Text-to-Video Generation

Generates video clips from text prompts using a 1,000-token context window to interpret scene descriptions and motion instructions.

Image-to-Video Conditioning

Accepts an input image as the first frame and a separate image as the last frame, allowing the model to animate between defined visual anchors.

Reference Image Support

Takes an array of reference images to guide the visual style or subject consistency of the generated video.

Audio Generation

Optionally generates audio alongside the video clip, toggled via the Include Audio setting.

Aspect Ratio and Resolution Control

Supports selectable aspect ratios and resolution settings so outputs can be tailored to different display formats.

Prompt Auto-Enhancement

Includes an optional auto-enhance prompt toggle that rewrites or expands user prompts to improve generation quality.

Negative Prompt Filtering

Accepts a negative prompt as a text input to suppress unwanted visual elements or styles from the generated output.

Fast Generation Speed

Designated as a fast variant in the Veo 3.1 family, targeting reduced latency for iterative or high-throughput video workflows.

Reproducible Outputs via Seed

Supports a seed input so users can reproduce or iterate on specific generated results with consistent randomness.

Ready to build with Veo 3.1 Fast?

Get Started Free

FAQ

Common questions about Veo 3.1 Fast

What is the context window for Veo 3.1 Fast?

Veo 3.1 Fast has a context window of 1,000 tokens, which applies to the text prompt input used to describe the video content.

Does Veo 3.1 Fast support image inputs?

Yes. The model accepts a first-frame image, a last-frame image, and an array of reference images, enabling image-to-video and style-guided generation workflows.

Can Veo 3.1 Fast generate audio with the video?

Yes. Audio generation is an optional toggle in the model's inputs, allowing users to include or exclude audio in the output.

What aspect ratios and resolutions does Veo 3.1 Fast support?

The model provides selectable aspect ratio and resolution options via toggle inputs, though the specific supported values are configured within MindStudio's interface.

Is pricing information available for Veo 3.1 Fast?

No published pricing is listed in the current metadata for Veo 3.1 Fast. You should check MindStudio or Google's official pricing pages for current cost information.

When was Veo 3.1 Fast released?

Veo 3.1 Fast was released in October 2025 and was added to the MindStudio catalog in January 2026.

Resources