Qwen: Qwen3 235B A22B Instruct 2507

qwen/qwen3-235b-a22b-2507

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...

Modalities
Text
In / out price
₩158 / ₩965
1M
Context
262.14K
Released
Jul 22, 2025

Apps

Apps that use this model the most.

Appstokens
Hermes Agent11.32T
Zazen (Freebuff fork)3.16T
Cline2.56T
Kilo Code2.44T
pi1.59T
OpenClaw1.05T
Codex938.81B
DeepSeek Harness847.26B
Portkey AI639.39B
HighLevel375.1B
ISEKAI ZERO364.56B
Framer348.63B
Hello Minds, powered by Ethoswarm316.97B
ZCode279.83B
Descript253.44B