Veo 2
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
- 16 December 2024
- Authors
- Agrim Gupta, Ali Razavi, Ankush Gupta, Dumitru Erhan, Eric Lau, Frank Belletti, Gabe Barth-Maron, Hakan Erdogan, Hakim Sidahmed, Henna Nandwani, Hernan Moraldo, Hyunjik Kim, Jeff Donahue, José Lezama, Kory Mathewson, Kurtis David, Marc van Zee, Medhini Narasimhan, Miaosen Wang, Mohammad Babaeizadeh, Nelly Papalampidi, Nick Pezzotti, Nilpa Jha, Parker Barnes, Pieter-Jan Kindermans, Rachel Hornung, …
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Video, Vision
- Task
- Video generation, Text-to-video, Image-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/2-0-generate-001
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
- Record confidence
- Unknown
"Veo has achieved state of the art results in head-to-head comparisons of outputs by human raters over top video generation models. Participants viewed 1003 prompts and respective videos on MovieGenBench, a benchmark dataset released by Meta. Veo 2 performs best on overall preference, and for its capability to follow prompts accurately." SOTA qualification is unclear solely from MovieGenBench, which is subjective and depends on human raters. But Veo 2 seems to be SOTA over Meta Movie Gen, Klin…
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
What this model is
Veo 2 was published by Google DeepMind, in the country recorded as United States of America, during December 2024. It comes out of an organisation categorised as industry.
It works in the domain of Video, Vision, and is recorded as performing the task of video generation, Text-to-video, Image-to-video.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Training and provenance
It is tracked in the underlying dataset for one reason in particular: sOTA improvement.
Answers
Veo 2 — common questions
Veo 2— what GPU do I need to run it?
None. This 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.
Veo 2— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
Veo 2— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
Veo 2— who created it?
It was published by Google DeepMind, based in United States of America, an organisation categorised as industry.
Veo 2— when was it released?
It was published in December 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
Veo 2— what is it used for?
It works in the domain of Video, Vision, and is recorded as handling the task of video generation, Text-to-video, Image-to-video. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
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.