Provider guide
Where to run Qwen3.5-122B-A10B
9 live offers tracked — output prices vary 1.5× between the cheapest and most expensive host, so the provider choice matters as much as the model choice.
FASTEST MEASURED
152 tok/s
measured throughput · $0.29 input / $2.40 output per million tokens
Alibaba CloudCHEAPEST$0.26 in/1M$2.08 out/1M54 tok/s262K—7d agoAlibaba Cloud$0.26 in/1M$2.08 out/1M112 tok/s262Kfp844m agoOpenRouter$0.26 in/1M$2.08 out/1M—262K—46m agoAtlasCloud$0.30 in/1M$2.40 out/1M64 tok/s262Kfp844m agoDeepInfra$0.29 in/1M$2.40 out/1M—262Kfp47h agoNovita AI$0.40 in/1M$3.20 out/1M—262K—7h agoSiliconFlowzero-retention$0.26 in/1M$2.08 out/1M18 tok/s262Kfp844m agoDeepInfrazero-retention$0.29 in/1M$2.40 out/1M152 tok/s262Kfp47h agoNovita AIzero-retention$0.40 in/1M$3.20 out/1M87 tok/s262Kbf1644m ago
OpenRouter
Novita AIFull specs, hardware verdicts and benchmarks on theQwen3.5-122B-A10B model page →