modelbenchmark.io

Qwen3 235B A22B Instruct

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

Compare

Qwen instruction model for multilingual chat, reasoning, and tool use

Specification

most-agreed values

Context
262K
Max output
16K
Released
2025-08-13
Knowledge cutoff
—
Retires
2026-10-21
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.22
Output
$0.88

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputvertex_ai-qwen_models$0.11
Batch outputvertex_ai-qwen_models$0.44

Batch input is 50% below the interactive input price at the same listing.

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
google-vertex$0.22$0.88——262K16K—
vertex_ai-qwen_models$0.22$0.88——262K16K2026-10-21

More from Alibaba

most-hosted first