Video
Legacy
Proprietary
Veo 3
The first widely available audio-enabled video generation
Release2025-05
Context10K
Max output—
ParametersUndisclosed
Local / VRAMAPI only
LicenseProprietary
Overview
Veo 3 is a model in the Video category from Google DeepMind. It was released in 2025-05. The vendor is based in US/UK. Best for: The first widely available audio-enabled video generation.
Strengths
- Native audio
- Cinematic
Limits
- Overtaken by Veo 3.1
- Short clips
Specifications
| Vendor | Google DeepMind |
|---|---|
| Category | Video |
| Release | 2025-05 |
| Status | Legacy |
| License | Proprietary |
| Commercial use | Not specified |
| Context window | 10K |
| Input modalities | Text, Image |
| Output modalities | Video, Audio |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 clip |
| Resolution | 720p-1080p |
| Duration | 8s |
| Frame rate | 24 fps |
| Audio generation | Yes |
| Local deployment | No |
| API access | Yes |
| Pricing | $0.40-0.75 / second |
| Confidence | High |
| Vendor country | US/UK |
| Vendor type | Frontier lab |
Pricing & hardware
$0.40-0.75 / second
API-only: local GPU memory is not applicable. API access is available.