modelbenchmark.io

Qwen3.8 2.4T A95B (NVFP4)

Alibaba · qwen3-8-2-4t-a95b-nvfp4

Compare

Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows

Specification

most-agreed values

Context
262K
Max output
33K
Released
2026-08-12
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$2.00
Output
$6.00
Cache read
$0.20

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
runinfra · inferact$2.00$6.00$0.20262K33K

More from Alibaba

most-hosted first