modelbenchmark.io

Qwen/Qwen3-VL-30B-A3B-Thinking

Alibaba · qwen3-vl-30b-a3b-thinking

Compare

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

Specification

most-agreed values

Context
262K
Max output
262K
Released
2025-10-11
Knowledge cutoff
2025-03-31
Retires
—
Open weights
yes
Input
text, image, video
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.1046
Output
$0.4185

Available from 7 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
siliconflow-cn$0.1046$0.4185——262K262K—
qiniu-ai$0.1087$1.087——128K32K—
fireworks_ai$0.15$0.60——262K262K—
novita$0.20$1.00——131K33K—
kilo$0.29$1.00——262K236K—
openrouter$0.29$1.00——262K236K—
siliconflow$0.29$1.00——262K262K—

Price history

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

DateHostField$/M
2026-09-02kiloInput$0.20
2026-10-10kiloInput$0.29
2026-09-02openrouterInput$0.20
2026-09-06openrouterInput$0.20
2026-10-10openrouterInput$0.29
2026-09-02siliconflow-cnInput$0.29
2026-10-22siliconflow-cnInput$0.1046
2026-09-02kiloOutput$2.40
2026-10-10kiloOutput$1.00
2026-09-02openrouterOutput$2.40
2026-09-06openrouterOutput$2.40
2026-10-10openrouterOutput$1.00
2026-09-02siliconflow-cnOutput$1.00
2026-10-22siliconflow-cnOutput$0.4185

More from Alibaba

most-hosted first