modelbenchmark.io

Qwen3-Vl 30b A3b Thinking

Alibaba · qwen3-vl-30b-a3b-thinking

Compare

Multimodal model for analyzing text, images, documents, and rich media

Specification

most-agreed values

Context
262K
Max output
33K
Released
2026-02-09
Knowledge cutoff
2025-03-31
Retires
Open weights
no
Input
text, image, video
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.20
Output
$2.40

Available from 8 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
fireworks_ai$0.15$0.60262K262K
kilo$0.20$2.40131K33K
novita$0.20$1.00131K33K
novita-ai$0.20$1.00131K33K
openrouter$0.20$2.40262K33K
siliconflow$0.29$1.00262K262K
siliconflow-cn$0.29$1.00262K262K
qiniu-ai128K32K

Price history

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

DateHostField$/M
2026-09-02openrouterInput$0.20
2026-09-06openrouterInput$0.20
2026-09-02openrouterOutput$2.40
2026-09-06openrouterOutput$2.40

More from Alibaba

most-hosted first