Text-to-Video
Veo 3.1 Fast is a specialized, high-speed variant of Google DeepMind’s Veo 3.1 text-to-video model, optimized for rapid generation of 8-second, high-fidelity videos. It is designed to create cinematic, 1080p, or 720p content with improved prompt adherence and native audio, making it ideal for creating quick, high-quality video clips, social media content, and ad creatives.
1,217
Oct 2025
video
$0.10/s
Catalog
Category rows come directly from Artificial Analysis when the endpoint exposes category-level Elo scores.
| Category | Elo | 95% CI | Appearances |
|---|---|---|---|
| Text | 1,287 | -29/29 | 473 |
| Specific location or era | 1,267 | -21/21 | 944 |
| Indoor | 1,254 | -17/17 | 1,247 |
| Sports | 1,254 | -25/25 | 542 |
| People | 1,252 | -11/11 | 2,863 |
| Buildings | 1,250 | -13/13 | 2,168 |
| Long prompt | 1,247 | -23/23 | 667 |
| Sci Fi | 1,245 | -20/20 | 845 |
| Transport |
| 1,237 |
| -15/15 |
| 1,725 |
| Weather and effects | 1,236 | -11/11 | 3,031 |
| Screens | 1,231 | -31/31 | 372 |
| Specific lighting | 1,226 | -12/12 | 2,660 |