Veo 3.1
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
- 15 October 2025
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Video, Vision
- Task
- Image-to-video, Video generation, Text-to-video, Audio generation
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
we're opening up new possibilities for richer, more powerful video storytelling right inside Flow. The Veo 3.1 model is also available via the Gemini API for developers, Vertex AI for enterprise customers, and the Gemini app. New capabilities are available in both Gemini API 2 and Vertex AI 3
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Why it is tracked
- SOTA improvement
- Record confidence
- Unknown
"Veo 3.1 has achieved state of the art results in head-to-head comparisons of outputs by human raters over top video generation models." https://deepmind.google/models/veo/evals/
Sources
Where this record came from and when it was last checked.
- Reference
- Introducing Veo 3.1 and advanced capabilities in Flow
- Last updated
- 28 November 2025
What the numbers mean
What this model is
Veo 3.1 was published by Google DeepMind, in United States of America, in October 2025. It comes out of industry.
It works in Video, Vision, and is recorded as doing image-to-video, Video generation, Text-to-video, Audio generation.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
What went into building it
It is tracked in the underlying dataset for one reason in particular: sOTA improvement.
Answers
Veo 3.1 — common questions
How many parameters does Veo 3.1 have?
No parameter count has been published for Veo 3.1, which is why no memory or speed figure appears on this page.
Who created Veo 3.1?
Veo 3.1 was published by Google DeepMind, based in United States of America, categorised as industry.
When was Veo 3.1 released?
Veo 3.1 was published in October 2025.
What is Veo 3.1 used for?
Veo 3.1 works in Video, Vision, and is recorded as handling image-to-video, Video generation, Text-to-video, Audio generation. 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.
What GPU do I need to run Veo 3.1?
None. Veo 3.1 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.
Is Veo 3.1 open source?
No. Veo 3.1 has not had its weights published, so it exists only as a service controlled by its owner.
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.