Provider guide
Where to run Qwen3 Coder 30B A3B Instruct
5 live listings tracked — output prices vary 5.4× between the cheapest and most expensive host, so the provider choice matters as much as the model choice.
FASTEST MEASURED
45 tok/s
measured throughput · $0.070 input / $0.27 output per million tokens
Novita AIzero-retention through OpenRouterDirect and through OpenRouter$0.070 in/1M$0.27 out/1M45 tok/sthrough OpenRouter160Kfp84 hours agoOpenRouterCHEAPEST$0.070 in/1M$0.28 out/1M—262K—4 hours agoSiliconFlowzero-retention$0.070 in/1M$0.28 out/1M23 tok/s262Kfp84 hours agoAmazon Bedrockzero-retention$0.15 in/1M$0.60 out/1M—0—4 hours agoAlibaba Cloud$0.29 in/1M$1.46 out/1M39 tok/s262K—4 hours ago
Amazon BedrockFull specs, hardware verdicts and benchmarks on the Qwen3 Coder 30B A3B Instruct model page →