LLMap
Models /Kimi K3 /Where to run
Provider guide

Where to run Kimi K3

17 live offers tracked.

CHEAPEST
Novita AI
$3.00 / $15.00
per 1M tokens in / out
FASTEST MEASURED
Wafer
133 tok/s
measured throughput · $3.00 input / $15.00 output per million tokens
Novita AICHEAPEST$3.00 in/1M$15.00 out/1M—1M—7h agoModal$3.00 in/1M$15.00 out/1M—1Mfp46d agoOpenRouter$3.00 in/1M$15.00 out/1M—1M—33m agoChutes$3.00 in/1M$15.00 out/1M20 tok/s1Mmxfp48h agoMoonshot AI$3.00 in/1M$15.00 out/1M—1Mint47d agoWafer$3.00 in/1M$15.00 out/1M133 tok/s912Kfp832m agoNebius AI Studio$3.00 in/1M$15.00 out/1M44 tok/s1Mfp45d agoMorphzero-retention$2.90 in/1M$14.00 out/1M36 tok/s1M—32m agoModalzero-retention$3.00 in/1M$15.00 out/1M50 tok/s1Mmxfp432m agoFireworks AIzero-retention$3.00 in/1M$15.00 out/1M44 tok/s1M—32m agoTogether AIzero-retention$3.00 in/1M$15.00 out/1M37 tok/s1M—32m agoDigitalOcean Gradientzero-retention$3.00 in/1M$15.00 out/1M23 tok/s1M—32m agoBasetenzero-retention$3.00 in/1M$15.00 out/1M55 tok/s1Mfp832m agoMoonshot AIzero-retention$3.00 in/1M$15.00 out/1M24 tok/s1Mmxfp432m agoMorphfast tierzero-retention$6.00 in/1M$22.50 out/1M48 tok/s1M—32m agoFireworks AIfast tierzero-retention$4.50 in/1M$22.50 out/1M81 tok/s1M—32m agoWaferfast tier$4.50 in/1M$22.50 out/1M53 tok/s1Mfp832m ago
Full specs, hardware verdicts and benchmarks on theKimi K3 model page →