Google DeepMind

Veo 3.1 Fast

Generally availableProprietary400K context

Summary

Veo 3.1 Fast is a proprietary video generation model from Google DeepMind, released on 15 Oct 2025. It accepts text and images and generates video, with a 400K-token context window and up to 8K output tokens per response.

Video model for prompt-guided generation, editing, and motion workflows

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperGoogle DeepMind
Release date15 Oct 2025 [models.dev]
StatusGenerally available [models.dev]
WeightsProprietary (API only) [models.dev]
Context window400K (400,000 tokens) [models.dev]
Max output8K tokens [models.dev]
InputText and images [models.dev]
OutputVideo [models.dev]
Reasoning modeNo [models.dev]
Tool callingNo [models.dev]

Veo 3.1 Fast API pricing by provider

USD per million tokens. Sorted by input price.

We do not currently track a paid API listing for this model.

Frequently asked questions

What is the context window of Veo 3.1 Fast?

Veo 3.1 Fast has a context window of 400,000 tokens (400K) and can generate up to 8,192 tokens in a single response, according to models.dev.

Is Veo 3.1 Fast open source?

No. Veo 3.1 Fast is a proprietary model; Google DeepMind has not released its weights.

When was Veo 3.1 Fast released?

Google DeepMind released Veo 3.1 Fast on 15 Oct 2025, according to models.dev.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Wan 2.6Alibaba (Qwen)3 Dec 2025400K––Closed
Seedance 2.5ByteDance Seed31 Jul 2026–––Closed
MiniMax H3 MaxMiniMax26 Aug 2026–––Closed
Seedance 2.0ByteDance Seed12 Feb 20264K––Closed
Grok Imagine VideoxAI28 Jan 20261K––Closed
MiniMax H3MiniMax31 Jul 2026–––Open

Change history

  • Name changed from Veo 3.1 fast to Veo 3.1 Fast
  • Context window changed from 480 to 400K
  • Input modalities changed from text, image, video to text, image
  • No longer listed on google

Sources