Kimi K2.7 Code vs Kimi K3
API pricing, context, and independently measured performance, side by side.
Kimi K2.7 Code
Moonshot AI · released Jun 12, 2026
Best input$0.671 / MTok
Best output$3.00 / MTok
Context262K
Providers12
Fastest measured0.44s° TTFT · 175 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
Kimi K3
Moonshot AI · released Jul 16, 2026
Best input$0.68 / MTok
Best output$9.75 / MTok
Context1.05M
Providers26
Fastest measured0.87s° TTFT · 69 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| Kimi K2.7 Code |  Inceptron | $0.671 | $3.35 | — | — | 5/5 |
| Kimi K2.7 Code |  CoreWeave | $0.71 | $3.50 | 0.51s° | 485° tok/s | 5/5 |
| Kimi K2.7 Code |  StreamLake | $0.713 | $3.00 | 1.7s° | 69° tok/s | — |
| Kimi K3 |  Wafer | $0.68 | $15.00 | 0.87s° | 69° tok/s | 0/5 |
| Kimi K3 |  Relace | $0.71 | $13.00 | 1.1s° | 150° tok/s | — |
| Kimi K3 |  InferenceNet | $0.72 | $15.00 | — | — | — |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) · chat10k profile (~10K in / 200 out) · ° = measured via OpenRouter routing (adds a hop) · SMOKE: of 5 programmatic capability probes passed · methodology v1.1 — full details on each model page