Veo 3.1

Video modelCard summarized

A model for generating 8-second videos (720p, 1080p, or 4k) with natively generated audio

● Re-checked 12 Oct 2026 · 72 facts · 0 correctionsSource: Veo 3 Model Card (covers Veo 3 and subsequent versions) (6 pp)

Use it via API

$0.40 / sec

Code example Compare

Where to call it

Gemini APIveo-3.1-generate-preview
Google Vertex AIveo-3.1-generate-001

Supports

Image input

Full feature support

Good for

High-quality, high-resolution video in a wide range of cinematic and visual styles
Follows simple and complex instructions
Simulates real-world physics and represents motion accurately

Overview

Google · 02Veo

Veo 3.1

A model for generating 8-second videos (720p, 1080p, or 4k) with natively generated audio

Typical price

$0.40 / sec

720p or 1080p, with audio

Max resolution: 4K
Max length: 8 s
Modes: text-to-video, image-to-video
Released: 15 Oct 2025

Google · 02Veo

Veo 3.1

veo-3.1-generate-preview

Inputs: Text, Images, Video
License: Proprietary
Sound: Yes
Frame rate: 24

720p or 1080p, with audio$0.40 / sec
4K, with audio$0.60 / sec
720p or 1080p, video only (Vertex AI)$0.20 / sec

From the model card

High-quality, high-resolution video in a wide range of cinematic and visual styles
Follows simple and complex instructions
Consistency in complex scenes
Demographic skew

Veo 3 is a video generation system capable of synthesizing high-quality, high-resolution video with audio from a text prompt or input image. The card covers Veo 3 and later versions (last updated 13 Jan 2026); there is no separate card for Veo 3.1. p.2

veo-3.1-generate-preview

Typical price: $0.40 / sec
Max resolution: 4K
Max length: 8 s
Aspect ratios: 16:9, 9:16
Frame rate: 24
Released: 15 Oct 2025

text-to-video
image-to-video
first and last frame interpolation
reference images (up to 3)
video extension (+7 s, up to 20 times)