Video Generation Model

Veo 3.1 Fast

A fast video generation model from Google designed for quick, high-quality AI video creation via Vertex AI and the Gemini API.

Start Building with Veo 3.1 Fast View All Models

Publisher

Google

TypeVideo

Context Window1,000 tokens

Training DataJuly 2025

Price$0.10/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, part of the Veo 3.1 model family. It is optimized for speed, making it suitable for workflows that require rapid video output at scale. The model is available through both the Gemini API and Vertex AI, giving developers two integration paths for production use. The stable endpoint identifier is veo-3.1-fast-generate-001, which replaced an earlier preview endpoint.

Veo 3.1 Fast accepts text prompts as well as image inputs, including single images and image arrays, allowing for both text-to-video and image-to-video generation workflows. It supports configuration options such as aspect ratio, duration, and resolution through toggle-based parameters. The model is best suited for developers and creators who need to generate video content quickly at scale and require a stable, production-grade API endpoint for integration into their pipelines.

Capabilities

What Veo 3.1 Fast supports

Text-to-Video

Generates video clips from natural language text prompts. Accepts up to 1,000 tokens of prompt input per request.

Image-to-Video

Animates or extends video from one or more input images. Supports single image URLs and image URL arrays as starting frames.

Fast Generation

Optimized for speed within the Veo 3.1 model family, reducing generation time for high-throughput video workflows.

Configurable Output

Supports multiple toggle-based settings including aspect ratio, resolution, and duration to control video output format.

Reproducible Seeds

Accepts a seed value as input, enabling reproducible video generation results across repeated requests.

API & Vertex AI Access

Available via both the Gemini API and Google Vertex AI, with a stable production endpoint at veo-3.1-fast-generate-001.

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 for video generation requests.

Where can I access Veo 3.1 Fast?

The model is available through both Google's Gemini API and Vertex AI. The stable production endpoint is veo-3.1-fast-generate-001.

What input types does Veo 3.1 Fast support?

The model accepts text prompts, single image URLs, and image URL arrays, along with configuration toggles for aspect ratio, resolution, and duration, plus an optional seed value.

What is the training data cutoff for Veo 3.1 Fast?

According to the available metadata, the training date for Veo 3.1 Fast is July 2025.

How does Veo 3.1 Fast differ from the preview endpoint?

The veo-3.1-fast-generate-001 endpoint is the stable, production-ready release. It replaced the earlier veo-3.1-fast-generate-preview endpoint, which was deprecated in early 2026.

Resources