Video model · Google DeepMind

Veo 3.1 (Standard / Fast / Lite)

8s max4KAudioOfficial price#12 LMArena T2V (Audio)

Specs

VersionVeo 3.1; Lite Mar 2026
ReleasedJan 2026 (AA listing) artificialanalysis.ai ↗ checked 2026-10-17
Max length8 s
Max resolution4K (Standard/Fast); 1080p Lite
AudioYes
X@GoogleDeepMind

Features

  • text/image-to-video
  • audio included

ai.google.dev ↗ checked 2026-10-17

Pricing Official list

standard 720p 1080p$0.40/s
standard 4k$0.60/s
fast 720p$0.10/s
fast 1080p$0.12/s
fast 4k$0.30/s
lite 720p$0.05/s
lite 1080p$0.08/s

ai.google.dev ↗ checked 2026-10-17

Where to use it

  • Gemini API / Vertex; Google Ads Asset Studio image-to-video (≤10 s from up to 3 images) business.google.com ↗ checked 2026-10-17
  • Higgsfield (named in model catalog) github.com ↗ checked 2026-10-17

Benchmarks

BoardRankScoreBoard dateSource
AA Text-to-Video v2.1#19968liveartificialanalysis.ai ↗ checked 2026-10-17
AA Image-to-Video#131028liveartificialanalysis.ai ↗ checked 2026-10-17
LMArena Text-to-Video (Audio)#1213642026-09-21lmarena.ai ↗ checked 2026-10-17
LMArena Image-to-Video (Audio)#1313982026-09-21lmarena.ai ↗ checked 2026-10-17

Use cases

Veo in Google Ads Asset Studio animates advertiser images into video ads

Tags show who made each item: vendor, contest entry, creator or self-promo.

The weekly diff

What changed in AI coding plans: prices, limits, resets. Email signups open soon. Until then, updates go out on X.

Follow @QuietlyByG on X RSS feed

No email form yet, so we don't collect any email addresses.