modelbenchmark.io

Qwen: Qwen3 235B A22B Instruct 2507

Alibaba · qwen3-235b-a22b-07-25

Compare

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,...

Specification

most-agreed values

Context
262K
Max output
16K
Released
—
Knowledge cutoff
2025-06-30
Retires
—
Open weights
—
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.09
Output
$0.55

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
openrouter$0.09$0.55——262K16K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02openrouterCache read$0.0175
2026-09-12openrouterCache read$0.0175
2026-09-02openrouterInput$0.0875
2026-09-05openrouterInput$0.09
2026-09-10openrouterInput$0.22
2026-09-12openrouterInput$0.0875
2026-10-06openrouterInput$0.09
2026-09-02openrouterOutput$0.35
2026-09-05openrouterOutput$0.55
2026-09-10openrouterOutput$0.88
2026-09-12openrouterOutput$0.35
2026-10-06openrouterOutput$0.55

More from Alibaba

most-hosted first