← All models
Qwen: Qwen3.8 2.4T A95B logo

Qwen · Text

Qwen: Qwen3.8 2.4T A95B

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...

Open-weightIn: TextOut: Text

Input / M

$2.00 / M

Output / M

$6.00 / M

Cache read / M

$0.25 / M

Context

1M

Released

Aug 12, 2026