Unified audio-video generation model taking text, image, audio and video references, up to 15s.
Released
Feb 12, 2026
Context window
Not disclosed
Max output
Not disclosed
Parameters
Not disclosed
Input price
Not disclosed
Output price
Not disclosed
Prices are first-party list prices in USD at the standard tier. Last verified Oct 30, 2026.
Pricing
Launch priceApr 1, 2026
$0.15 per second
Current price
since Apr 1, 2026
$0.15 per second
Specifications
- Developer
- ByteDance
- Model type
- Video gen
- Architecture
- Not disclosed
- Parameters
- Not disclosed
- Input
- Text Image Audio Video
- Output
- Audio Video
- Knowledge cutoff
- Not disclosed
- License
- Proprietary
- API access
- First-party API