modelbenchmark.io

Qwen3 VL 235B A22B Thinking

Alibaba · qwen3-vl-235b-a22b-thinking

Compare

Qwen vision-language thinking model for visual reasoning, documents, and agent tasks

Specification

dashscope listing

Context
131K
Max output
33K
Released
2025-09-23
Knowledge cutoff
2025-03-31
Retires
—
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · dashscope list price

Input
$0.40
Output
$4.00
Cache read
$0.25

Available from 10 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
fireworks_ai$0.22$0.88——262K262K—
merge-gateway$0.287$2.867$0.0574—131K33K—
dashscope · dashscope$0.40$4.00——131K33K—
orcarouter$0.40$4.00——131K41K—
qwen_ai_platform · qwen-ai-platform$0.40$4.00——131K33K—
qwencloud · qwencloud$0.40$4.00——131K33K—
nano-gpt$0.50$6.00$0.25—131K33K—
huggingface$0.98$3.95——131K33K—
jalapeno$0.98$3.95——131K33K—
novita$0.98$3.95——131K33K—

Price history

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

DateHostField$/M
2026-09-02openrouterInput$0.40
2026-09-06openrouterInput$0.40
2026-09-02openrouterOutput$4.00
2026-09-06openrouterOutput$4.00

More from Alibaba

most-hosted first