modelbenchmark.io

Qwen 3.8 Max

Alibaba · qwen-3-8-max

Compare

Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows

Specification

most-agreed values

Context
1M
Max output
131K
Released
2026-07-22
Knowledge cutoff
Retires
Open weights
no
Input
text, image, video
Output
text

Price

US dollars per million tokens · most-agreed

Input
$2.50
Output
$7.50
Cache read
$0.3125
Cache write
$3.125

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
venice$2.50$7.50$0.3125$3.1251M131K

More from Alibaba

most-hosted first