LLMap
Models /Kimi K2.5 /Where to run
Provider guide

Where to run Kimi K2.5

14 live offers tracked.

CHEAPEST
OpenRouter
$0.57 / $2.85
per 1M tokens in / out
FASTEST MEASURED
Amazon Bedrock
65 tok/s
measured throughput · $0.60 input / $3.00 output per million tokens
Chutes$0.44 in/1M$2.00 out/1M20 tok/s262Kint47d agoDeepInfra$0.45 in/1M$2.25 out/1M—262Kfp47h agoAtlasCloud$0.49 in/1M$2.50 out/1M30 tok/s262Kint439m agoStreamLake$0.54 in/1M$2.70 out/1M29 tok/s256Kfp839m agoOpenRouterCHEAPEST$0.57 in/1M$2.85 out/1M—262K—40m agoNovita AI$0.60 in/1M$3.00 out/1M—262K—7h agoDigitalOcean Gradientzero-retention$0.38 in/1M$2.02 out/1M10 tok/s262K—7h agoDeepInfrazero-retention$0.45 in/1M$2.25 out/1M26 tok/s262Kfp439m agoSiliconFlowzero-retention$0.45 in/1M$2.25 out/1M55 tok/s262Kint414h agoNovita AIzero-retention$0.57 in/1M$2.85 out/1M26 tok/s262K—39m agoPhalazero-retention$0.60 in/1M$3.00 out/1M36 tok/s262K—39m agoAmazon Bedrockzero-retention$0.60 in/1M$3.00 out/1M65 tok/s262K—39m agoMoonshot AIzero-retention$0.60 in/1M$3.00 out/1M30 tok/s262Kint439m agoVenice AIzero-retention$0.56 in/1M$3.50 out/1M26 tok/s256K—7h ago
Full specs, hardware verdicts and benchmarks on theKimi K2.5 model page →