Veo 2 is our stable line of video generation models. This page documents the capabilities and features of Veo 2.
Model ID
veo-2.0-generate-001
Modalities
Capabilities
- Supported
- Not supported
- Provisioned Throughput
Not supported - Batch inference
Not supported - Pay-as-you-go
Not supported - Fixed quota
Supported
Quotas
- Regional online prediction requests per base model per minute per base model: 10
Technical specifications
Video
- Video lengths: 5 to 8 seconds
- Maximum number of output videos per prompt: 4
- Image-to-video maximum input image size: 20 MB
- Supported aspect ratios: 9:16, 16:9
- Supported output resolutions: 720p
- Supported input resolutions: 720p
- Supported framerates: 24 FPS
- Supported MIME types:
video/mp4
Prompt languages
- English
Supported regions
Model availability
- United States
- us-central1
- Europe
- europe-west3
Versions
-
veo-2.0-generate-001 - Launch stage: GA
- Release date: May 27, 2025
- Retirement date: June 30, 2026
Security controls
Online prediction
- Data residency
- CMEK
- VPC-SC
- AXT
For Veo pricing information, see the Veo section of the Cost of building and deploying AI models in Agent Platform page.
