Provider guide
Where to run Qwen3 VL 30B A3B Thinking
5 live offers tracked — output prices vary 2.4× between the cheapest and most expensive host, so the provider choice matters as much as the model choice.
FASTEST MEASURED
125 tok/s
measured throughput · $0.20 input / $2.40 output per million tokens
Novita AI$0.20 in/1M$1.00 out/1M—131K—10h agoAlibaba Cloud$0.13 in/1M$1.56 out/1M123 tok/s131K—7d agoOpenRouterCHEAPEST$0.20 in/1M$2.40 out/1M—262K—4h agoAlibaba Cloud$0.20 in/1M$2.40 out/1M125 tok/s131Kfp84h agoSiliconFlowzero-retention$0.29 in/1M$1.00 out/1M61 tok/s262Kfp84h ago
Novita AIFull specs, hardware verdicts and benchmarks on theQwen3 VL 30B A3B Thinking model page →