Models /Qwen3 VL 30B A3B Instruct /Where to run
Provider guide

Where to run Qwen3 VL 30B A3B Instruct

9 live offers tracked.

CHEAPEST
$0.15 / $0.60
per 1M tokens in / out
FASTEST MEASURED
66 tok/s
measured throughput · $0.13 input / $0.52 output per million tokens
Alibaba Cloud$0.13 in/1M$0.52 out/1M19 tok/s131Kfp842m agoAlibaba Cloud$0.13 in/1M$0.52 out/1M66 tok/s131K7d agoOpenRouterCHEAPEST$0.15 in/1M$0.60 out/1M262K44m agoDeepInfra$0.15 in/1M$0.60 out/1M262Kfp87h agoPhala$0.20 in/1M$0.70 out/1M128K8d agoNovita AI$0.20 in/1M$0.70 out/1M131K7h agoDeepInfrazero-retention$0.15 in/1M$0.60 out/1M12 tok/s262Kfp842m agoNovita AIzero-retention$0.20 in/1M$0.70 out/1M7 tok/s131Kbf1642m agoSiliconFlowzero-retention$0.29 in/1M$1.00 out/1M3 tok/s262Kfp842m ago
Full specs, hardware verdicts and benchmarks on theQwen3 VL 30B A3B Instruct model page →