Models / Video
Veo 3.1
By Google, in Claude, ChatGPT, Cursor, Claude Code, and the API.
Google's premium video model: 1080p clips with sound. It spends credits faster than any other video model, so it's for when only Veo will do.
- Made by
- Type
- Video
- Price band
- Premium
- Blind tests
- #14 on Artificial Analysis's text-to-video arena, September 2026
- Lengths
- 4, 6, 8 seconds, default 8
- Sound
- Yes
- Shapes
- landscape, portrait
- Reference image
- The clip starts from your image
- Model id
- veo-3.1
Ask for it by name
Your AI uses the default for video unless you name another. Say Veo 3.1 and it uses this one.
youMake a 8-second Veo 3.1 clip of waves breaking at dusk, with sound.
A Studio month (3,000 credits) covers about 6 8-second clips with Veo 3.1, or a mix with any other model. See plans.
From your own code
The same key your assistant uses works as a bearer token. See the docs.
curl https://getstudiopass.com/v1/generations \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"modality":"video","model":"veo-3.1","prompt":"Waves breaking at dusk","duration_seconds":8}'