- Services
Veo is Google DeepMind’s closed-source text-to-video model family. Veo 2 and Veo 3 power video generation in the Gemini app and Vertex AI.
See all models from GoogleModels in family
2
Open weight
0
API only
2
Avg score
42.1
Top benchmark
71.1
Video Arena
Total HF downloads
—
Primary modality
Video
First release
May 2025
Latest release
Oct 2025
Every release in the Veo family, ranked by composite score across benchmarks, popularity, efficiency, and versatility.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | Veo 3API | video | BB56.9 | — | May 2025 |
| 2 | Veo 3.1API |
When each release shipped, newest first. Useful for tracking version cadence.
Oct 15
Closed-source releases accessed through Google’s API.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | Veo 3API | video | BB56.9 | — | May 2025 |
| 2 | Veo 3.1API |
The Veo family is a series of AI models from Google. This page lists every release in the family with its benchmark scores, parameter count, and hardware requirements.
By composite score, Veo 3 is currently the top model in the family. For local inference, match the parameter count to your VRAM budget. For quality, pick the highest scorer that fits.
See the open-weight section above for models you can run locally. The API-only section lists closed releases that must be accessed through the provider’s API.
Spin up an instance in the cloud, or pick local hardware that fits.
Advertising disclosure: we earn commissions when you shop through the links below.
Benchmark data sourced from: Hugging Face, Arena.ai, Artificial Analysis.
DD27.3 |
| — |
| Oct 2025 |
May 20
Composite grades across this family. Higher is better, blending benchmarks, popularity, and efficiency.
DD27.3 |
| — |
| Oct 2025 |
Vultr
GPU cloud with hourly and monthly plans, starting at $0.50/hr.
