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...
Rank
#145
No change
Tokens
8.7B
2026-08-14
Requests
172.1K
172,126
Tool calls
-
Input / M
$2.00
Output / M
$6.00
Cache / M
$0.25
Context
1.0M
1,048,576 tokens