Provider guide
Where to run Kimi K2.6
26 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
229 tok/s
measured throughput · $0.65 input / $3.41 output per million tokens
Baidu$0.59 in/1M$2.48 out/1M21 tok/s262Kfp45h agoNovita AICHEAPEST$0.80 in/1M$3.40 out/1M—262K—5h agoModelRun$0.70 in/1M$3.40 out/1M111 tok/s262Kfp44d agoOpenRouter$0.60 in/1M$3.41 out/1M—262K—5h agoChutes$0.66 in/1M$3.50 out/1M9 tok/s262Kint45h agoDeepInfra$0.75 in/1M$3.50 out/1M—262Kfp45h agoStreamLake$0.85 in/1M$3.60 out/1M19 tok/s256Kfp85h agoAtlasCloud$0.95 in/1M$4.00 out/1M13 tok/s262Kint45h agoCloudflare Workers AI$0.95 in/1M$4.00 out/1M31 tok/s262K—5h agoSail Research$1.00 in/1M$4.00 out/1M—262Kfp87d agoDigitalOcean Gradientzero-retention$0.76 in/1M$3.20 out/1M47 tok/s262K—7h agoSiliconFlowzero-retention$0.77 in/1M$3.40 out/1M22 tok/s262Kfp87h agoNovita AIzero-retention$0.80 in/1M$3.40 out/1M6 tok/s262K—5h agoDecartzero-retention$0.66 in/1M$3.40 out/1M114 tok/s262Kfp419h agoInceptronzero-retention$0.60 in/1M$3.41 out/1M64 tok/s262Kint47h agoCoreWeavezero-retention$0.65 in/1M$3.41 out/1M229 tok/s262Kfp45h agoDeepInfrazero-retention$0.75 in/1M$3.50 out/1M23 tok/s262Kfp45h agoVenice AIzero-retention$0.75 in/1M$3.50 out/1M24 tok/s256Kint45h agoCrusoezero-retention$0.70 in/1M$3.50 out/1M68 tok/s262Kbf167h agoParasailzero-retention$0.75 in/1M$3.50 out/1M33 tok/s262Kint45h agoBasetenzero-retention$0.95 in/1M$4.00 out/1M61 tok/s262Kfp45h agoMoonshot AIzero-retention$0.95 in/1M$4.00 out/1M26 tok/s262Kint45h agoFireworks AIzero-retention$0.95 in/1M$4.00 out/1M50 tok/s262K—19h agoSail Researchzero-retention$1.00 in/1M$4.00 out/1M15 tok/s262Kint45h agoTogether AIzero-retention$1.20 in/1M$4.50 out/1M109 tok/s262K—5h agoPhalazero-retention$1.09 in/1M$4.60 out/1M32 tok/s262K—7h ago
Full specs, hardware verdicts and benchmarks on theKimi K2.6 model page →