modelbenchmark.io

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

Alibaba · qwen3-vl-30b-a3b-instruct

Compare

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

Specification

most-agreed values

Context
262K
Max output
16K
Released
2025-10-05
Knowledge cutoff
2025-03-31
Retires
Open weights
no
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.15
Output
$0.60

Available from 11 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
kilo$0.13$0.52262K16K
deepinfra$0.15$0.60262K
fireworks_ai$0.15$0.60262K262K
llmgateway$0.15$0.60262K8K
nearai$0.15$0.5516K8K
openrouter$0.15$0.60262K16K
llmgateway-providers
$0.20
$0.15
$0.70
$0.60
131K
262K
33K
novita$0.20$0.70131K33K
novita-ai$0.20$0.70131K33K
siliconflow$0.29$1.00262K262K
siliconflow-cn$0.29$1.00262K262K

Price history

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

DateHostField$/M
2026-09-02llmgateway-providersInput$0.15
2026-09-04llmgateway-providersInput$0.20
2026-09-02openrouterInput$0.15
2026-09-06openrouterInput$0.15
2026-09-02llmgateway-providersOutput$0.60
2026-09-04llmgateway-providersOutput$0.70
2026-09-02openrouterOutput$0.60
2026-09-06openrouterOutput$0.60

More from Alibaba

most-hosted first