Model · Google DeepMind · Proprietary

Veo 3.1 Lite

Text-to-videoImage-to-videoVideo editProprietary
Open the AIContentDrop generator →
Arena rating
No votes yet
Crowd votes (Design Arena board)
27,782
Arena status
Pre-launch
Facts checked
2026-10-06

Vendor-sourced facts

Published facts for Veo 3.1 Lite — vendor-sourced, checked 2026-10-06
FactValue
VendorGoogle DeepMind [1]
LicenceProprietary (API/app only) [1]
Licence detailAPI only; model ID veo-3.1-lite-generate-preview in the Gemini API [1]
ModesText-to-video, Image-to-video, Video edit [1]
Release2026-04 [1]
Max resolutionNot stated [1]
Max clip durationNot stated [1]
Native audioYes [1]
AccessAPI, web app [1]
Vendor pagehttps://deepmind.google/models/model-cards/veo-3-1-lite/ [1]

Arena rating: no votes yet. Nothing on this page is a score, a rank or a measurement by us — every value is what Google DeepMind publishes, with the page it came from listed under Sources.

Crowd votes · external board

On Design Arena's video board Veo 3.1 Lite appears as “Veo 3.1 Lite”: Elo 1177 · #19 of 48 · win rate 57.5% ± 0.6% · 27,782 votes (15,970W 11,812L) · avg 50.1s.[2] These are their voters' numbers, not this arena's — our own arena has no votes yet.

Source: Design Arena (designarena.ai/leaderboard/video), checked 2026-10-21.

About Veo 3.1 Lite

Veo 3.1 Lite is the low-cost member of the Veo 3.1 family, listed in Google's Gemini API model catalogue as veo-3.1-lite-generate-preview and dated April 2026. It carries the same three modes as its larger sibling — text-to-video, image-to-video and editing — and the same native audio support. [1]

Google does not state a maximum resolution or a maximum clip length for the Lite model on the pages we read, so both cells say Not stated rather than inheriting Veo 3.1's numbers. That restraint matters: a cheaper variant in the same family is the most tempting place to assume a specification, and assumptions are what this site exists not to publish.

“High-efficiency, low-cost, developer-first video generation, editing, and cinematic control from the Veo 3.1 family.”

Google DeepMind on Veo 3.1 Lite [1]

Want hands-on context before trusting anyone's ranking? Generate your own clips with a multi-model workflow on AIContentDrop: open AIContentDrop · wire generation into your editor via MCP.

Sources

  1. Google DeepMind — Veo 3.1 Lite, vendor documentation https://ai.google.dev/gemini-api/docs/models — checked 2026-10-06
  2. Design Arena — video leaderboard https://www.designarena.ai/leaderboard/video — checked 2026-10-21

Each [n] above is the vendor page the fact beside the marker was read from, on the date shown. Where a vendor states nothing, the table says “Not stated” and no value is inferred from anywhere else.