Hy-MT2-30B-A3B

Open weights Active Text LLM MoE

Open-weight MoE fast-thinking translation model from the Hy-MT2 family, supporting 33 languages.

Released
May 21, 2026
Context window
262K tokens
Max output
Not disclosed
Parameters
30B 3B active
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
Tencent
Model type
Text LLM
Architecture
MoE
Parameters
30B (3B active)
Input
Text
Output
Text
Knowledge cutoff
Not disclosed
License
Apache License 2.0
API access
No first-party API