Plain-English Summary
Google’s high-quality text- and image-to-video model for cinematic clips.
Veo 3.1 Preview
Google’s high-quality text- and image-to-video model for cinematic clips.
Veo
Video
Preview
Open weights: No
API: Yes
Technical Notes
Generative video model supporting prompt-based video creation with advanced motion, scene, and audiovisual controls.
Best For
Cinematic clips, advertising concepts, storyboards, visual effects
Watch Out For
Preview; generation is slower and more expensive than image models and may have duration limits.
Model Specs
- Maker
- Country
- Not listed
- Family
- Veo
- Type
- Video
- Release date
- Not listed
- Date confidence
- Not publicly stated
- Status
- Preview
- Context window
- Varies
- Max output
- Not listed
- Parameters
- Not disclosed
- Active parameters
- Not disclosed
- Architecture
- Proprietary video diffusion / transformer system
- Reasoning
- Not applicable
- Tool calling
- No
- Structured output
- No
- API available
- Yes
- Open weights
- No
- Self-hostable
- No
- License
- Proprietary
- Inputs
- Text, image
- Outputs
- Video
- Approx. price
- See provider pricing
- How to access
- Provider website or API
- Model / API ID
- veo-3.1-generate-preview
- Knowledge cutoff
- Not publicly disclosed
- Fine-tuning
- Prompting / RAG
- Completeness
- 76 %
- Verified
- Jul 18, 2026
- Snapshot date
- Jul 18, 2026
- Source
- Official source