← Models

Veo 3.1

Google · Veo

Google's active Veo 3.1 preview family for video generation with native audio and stronger 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 October 2025 · Updated June 8, 2026

Overview

Freshness note: Model capabilities, limits, lifecycle dates, and pricing can change quickly. This profile is a point-in-time snapshot last verified on June 8, 2026.

Veo 3.1 is Google’s active Veo preview family in the Gemini API. It is now the recommended migration target for older Veo 3 stable routes, with Standard, Fast, and Lite preview variants for different quality, latency, and price needs.

Capabilities

Veo 3.1 is designed for prompt-driven video generation where scene quality, continuity, and audio matter together. Google’s current docs position it for professional-grade 4K output, natively synchronized audio, complex camera movements, reference-image workflows, and stronger scene control.

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. Veo 3.1 Lite is the lower-cost lane for high-volume applications, but it does not support 4K output or video extension.

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
  • veo-3.1-lite-generate-preview

The docs list text/image input, video-with-audio output, a 1,024-token text input limit, and one output video. Google’s video guide documents 8-second 720p, 1080p, and 4K clips with native audio, portrait and landscape formats, first/last-frame control, video extension, and up to three reference images. Lite does not support 4K or extension.

Pricing & Access

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

  • Standard video with audio: 0.40persecondfor720p/1080pand0.40 per second for 720p/1080p and 0.60 per second for 4K.
  • Fast video with audio: 0.10persecondfor720p,0.10 per second for 720p, 0.12 per second for 1080p, and $0.30 per second for 4K.
  • Lite video with audio: 0.05persecondfor720pand0.05 per second for 720p and 0.08 per second for 1080p; 4K output is not supported.

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. Google notes that users are charged only if the video is successfully generated.

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): Older stable route now listed as deprecated with shutdown coming soon; 3.1 is the recommended migration lane.
  • 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 and API workflows.