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
42 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/1M42 tok/sthrough OpenRouter160Kfp89 hours ago direct3 hours ago through OpenRouterOpenRouterCHEAPEST$0.070 in/1M$0.28 out/1M—262K—3 hours agoSiliconFlowzero-retention$0.070 in/1M$0.28 out/1M30 tok/s262Kfp83 hours agoAmazon Bedrockzero-retention$0.15 in/1M$0.60 out/1M—0—3 hours agoAlibaba Cloud$0.29 in/1M$1.46 out/1M36 tok/s262K—3 hours ago
Full specs, hardware verdicts and benchmarks on the Qwen3 Coder 30B A3B Instruct model page →