130B open speech-text model for spoken dialogue, released with Step-Audio-TTS-3B.
Released
Feb 17, 2025
Context window
Not disclosed
Max output
Not disclosed
Parameters
130B
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
No first-party API. This is an open-weights release you can run yourself.
Specifications
- Developer
- StepFun
- Model type
- Multimodal
- Architecture
- Not disclosed
- Parameters
- 130B
- Input
- Text Audio
- Output
- Text Audio
- Knowledge cutoff
- Not disclosed
- License
- Apache License 2.0
- API access
- No first-party API