modelbenchmark.io

Qwen3 235B A22B Instruct 2507 FP8

Alibaba · qwen3-235b-a22b-instruct-2507-tput

Compare

Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use

Specification

most-agreed values

Context
262K
Max output
262K
Released
2025-07-21
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.20
Output
$0.60

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
togetherai$0.20$0.60——262K262K—

More from Alibaba

most-hosted first