LLMap
Models /Kimi K2 Thinking /Where to run
Provider guide

Where to run Kimi K2 Thinking

4 live offers tracked.

CHEAPEST
OpenRouter
$0.60 / $2.50
per 1M tokens in / out
FASTEST MEASURED
Novita AI
32 tok/s
measured throughput · $0.60 input / $2.50 output per million tokens
OpenRouterCHEAPEST$0.60 in/1M$2.50 out/1M—262K—14m agoNovita AI$0.60 in/1M$2.50 out/1M—262K—6h agoNovita AIzero-retention$0.60 in/1M$2.50 out/1M32 tok/s262Kbf1613m agoGoogle Vertex AIzero-retention$0.60 in/1M$2.50 out/1M24 tok/s262K—13m ago
Full specs, hardware verdicts and benchmarks on theKimi K2 Thinking model page →