Provider guide
Where to run Qwen3.6 35B A3B
12 live offers tracked — output prices vary 1.6× between the cheapest and most expensive host, so the provider choice matters as much as the model choice.
FASTEST MEASURED
162 tok/s
measured throughput · $0.25 input / $1.25 output per million tokens
DeepInfra$0.10 in/1M$0.95 out/1M—262Kfp86h agoOpenRouterCHEAPEST$0.14 in/1M$1.00 out/1M—262K—18m agoAtlasCloud$0.19 in/1M$1.11 out/1M60 tok/s262Kfp816m agoNovita AI$0.25 in/1M$1.49 out/1M—262K—6h agoVenice AIzero-retention$0.098 in/1M$0.95 out/1M104 tok/s256Kfp816m agoDeepInfrazero-retention$0.10 in/1M$0.95 out/1M38 tok/s262Kfp816m agoParasailzero-retention$0.15 in/1M$1.00 out/1M43 tok/s262Kfp816m agoAkashMLzero-retention$0.14 in/1M$1.00 out/1M58 tok/s262Kfp816m agoCoreWeavezero-retention$0.25 in/1M$1.25 out/1M162 tok/s262Kfp816m agoPhalazero-retention$0.20 in/1M$1.27 out/1M35 tok/s262K—16m agoSiliconFlowzero-retention$0.20 in/1M$1.60 out/1M48 tok/s262Kfp816m agoIo Netzero-retention$0.29 in/1M$1.89 out/1M153 tok/s262Kfp816m ago
DeepInfra
Novita AIFull specs, hardware verdicts and benchmarks on theQwen3.6 35B A3B model page →