Veo 3

Closed weights Google DeepMind May 2025

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Google DeepMind
Organisation type
Industry
Country
United States of America
Published
21 May 2025
Authors
Abhishek Sharma, Alina Kuznetsova, Ali Razavi, Aleksander Holynski, Alina Kuznetsova, Ankush Gupta, Austin Waters, Ben Poole, Daniel Tanis, Derek Gasaway, Dumitru Erhan, Enric Corona, Frank Belletti, Gabe Barth-Maron, Hakan Erdogan, Henna Nandwani, Hernan Moraldo, Ilya Figotin, Igor Saprykin, Jason Baldridge, Jeff Donahue, Jimmy Shi, Kurtis David, Mai Gimenez, Medhini Narasimhan, Miaosen Wang, Min…

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Video, Vision
Task
Video generation, Image-to-video, Text-to-video

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Training data
tokens

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
API access
Training code
Unreleased

https://cloud.google.com/vertex-ai/generative-ai/docs/models/veo/3-0-generate-preview

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Likely above 10²³ FLOP
Yes
Why it is tracked
SOTA improvement

https://deepmind.google/models/veo/evals/

Record confidence
Unknown

Sources

Where this record came from and when it was last checked.

Reference
Our state-of-the-art video generation model
Last updated
28 November 2025

What the numbers mean

Background

Veo 3 was published by Google DeepMind, in United States of America, in May 2025. The organisation is categorised as industry.

It works in Video, Vision, and is recorded as doing video generation, Image-to-video, Text-to-video.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

How it was trained

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Answers

Veo 3 — common questions

01

Is Veo 3 open source?

No. Veo 3 has not had its weights published, so it exists only as a service controlled by its owner.

02

How many parameters does Veo 3 have?

No parameter count has been published for Veo 3, which is why no memory or speed figure appears on this page.

03

Who created Veo 3?

Veo 3 was published by Google DeepMind, based in United States of America, categorised as industry.

04

When was Veo 3 released?

Veo 3 was published in May 2025.

05

What is Veo 3 used for?

Veo 3 works in Video, Vision, and is recorded as handling video generation, Image-to-video, Text-to-video. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

06

What GPU do I need to run Veo 3?

None. Veo 3 is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.