Provider guide
Where to run Kimi K2.6
19 live listings tracked — output prices vary 2.5× between the cheapest and most expensive host, so the provider choice matters as much as the model choice.
FASTEST MEASURED
102 tok/s
measured throughput · $0.65 input / $3.41 output per million tokens
OpenRouterCHEAPEST$0.43 in/1M$1.83 out/1M—262K—2 hours agoBaidu$0.43 in/1M$1.83 out/1M51 tok/s262Kfp42 hours agoDigitalOcean Gradientzero-retention$0.57 in/1M$2.40 out/1M36 tok/s262K—2 hours agoInceptronzero-retention$0.43 in/1M$2.45 out/1M46 tok/s262Kint42 hours agoDecartzero-retention$0.59 in/1M$2.47 out/1M55 tok/s262Kfp42 hours agoStreamLake$0.60 in/1M$2.52 out/1M62 tok/s256Kfp82 hours agoChutes$0.50 in/1M$2.85 out/1M47 tok/s262Kint42 hours agoSiliconFlowzero-retention$0.77 in/1M$3.40 out/1M24 tok/s262Kfp82 hours agoNovita AIzero-retention through OpenRouterDirect and through OpenRouter$0.80 in/1M$3.40 out/1M31 tok/sthrough OpenRouter262K—2 hours agoCoreWeavezero-retention$0.65 in/1M$3.41 out/1M102 tok/s262Kfp42 hours agoDeepInfrazero-retention through OpenRouterDirect and through OpenRouter$0.75 in/1M$3.50 out/1M21 tok/sthrough OpenRouter262Kfp42 hours agoVenice AIzero-retention$0.75 in/1M$3.50 out/1M22 tok/s256Kint42 hours agoCrusoezero-retention$0.70 in/1M$3.50 out/1M77 tok/s262Kbf162 hours agoParasailzero-retention$0.75 in/1M$3.50 out/1M66 tok/s262Kint42 hours agoGMICloud$0.85 in/1M$3.60 out/1M21 tok/s262Kfp82 hours agoAtlasCloud$0.95 in/1M$4.00 out/1M95 tok/s262Kint42 hours agoMoonshot AIzero-retention$0.95 in/1M$4.00 out/1M46 tok/s262Kint42 hours agoCloudflare Workers AI$0.95 in/1M$4.00 out/1M35 tok/s262K—2 hours agoPhalazero-retention$1.09 in/1M$4.60 out/1M27 tok/s262K—2 hours ago
Baidu
DigitalOcean Gradient
Novita AI
DeepInfra
Cloudflare Workers AIFull specs, hardware verdicts and benchmarks on the Kimi K2.6 model page →