← Models

Veo 3.1

Google · Veo

Google's latest Veo preview tier for higher-end video generation with native audio and stronger reference control.

Part of Veo family · Other versions: Veo 3
Type
video
Context
N/A
Max Output
N/A
Status
preview
API Access
Yes
License
proprietary
video-generation native-audio creative filmmaking google preview
Released September 2025 · Updated April 4, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on April 4, 2026.

Veo 3.1 is Google’s latest Veo preview model in the Gemini API. It extends the Veo 3 line rather than replacing it outright, and Google’s current docs position it as the newest developer-facing video generation route for teams that want native audio plus stronger control over reference-driven scene generation.

Capabilities

Veo 3.1 is designed for prompt-driven video generation where scene quality, continuity, and audio matter together. The practical upgrade is not just “newer Veo.” Google’s current docs highlight Veo 3.1 as the version that supports reference-image workflows more explicitly, which makes it more usable for brand, product, and explainer-video pipelines where subject consistency matters.

That makes it a better fit than older one-shot video models for workflows that need early previs, repeated asset families, or visually coherent drafts across multiple scenes.

Technical Details

Veo 3.1 is still best treated as a video-native model rather than a token-centric language model. In Signal Lens, contextWindow and maxOutput are stored as 0 intentionally and should be interpreted as N/A for typical UI comparisons.

Google’s current video docs list preview model IDs:

  • veo-3.1-generate-preview
  • veo-3.1-fast-generate-preview

The docs also note that Veo 3.1 can use up to three reference images, which is a meaningful workflow improvement for character, product, or visual-style consistency.

Pricing & Access

Google’s current Gemini API pricing lists Veo 3.1 at:

  • Standard video with audio: $0.40 per second
  • Fast video with audio: $0.15 per second

Veo 3.1 is available on the paid tier of the Gemini API and remains a preview model, so teams should assume tighter limits and faster behavioral change than on stable production routes.

Best Use Cases

Use Veo 3.1 for short-form product demos, storyboard-grade concept videos, campaign explorations, and explainer clips where native audio and reference-image control materially improve the workflow. It is especially useful when the project needs more continuity than a simple “prompt and hope” video pipeline.

Comparisons

  • Veo 3 (Google): Stable current Veo route, while 3.1 is the newer preview track with stronger reference-image support.
  • Sora 2 (OpenAI): Strong alternative for storyboarded video ideation and collaborative branching.
  • Runway-style tools: Often better as end-user production environments, while Veo 3.1 is the model-layer capability behind higher-level creative surfaces.