Step-Audio 2 mini

Open weights Active Multimodal step-audio-2-mini

8B open end-to-end speech understanding and conversation model from the Step-Audio 2 family.

Released
Aug 29, 2025
Context window
Not disclosed
Max output
Not disclosed
Parameters
8B
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
8B
Input
Text Audio
Output
Text Audio
Knowledge cutoff
Not disclosed
License
Apache License 2.0
API access
No first-party API