Kimi K3 vs gpt-oss-120b
API pricing, context, and independently measured performance, side by side. gpt-oss-120b starts 84% cheaper on input than Kimi K3 at list prices.
Kimi K3
Moonshot AI · released Jul 16, 2026
Best input$0.182 / MTok
Best output$9.50 / MTok
Context1.05M
Providers29
Fastest measured0.66s° TTFT · 162 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
gpt-oss-120b
OpenAI · released Aug 5, 2025
Best input$0.03 / MTok
Best output$0.076 / MTok
Context131K
Providers27
Fastest measured0.24s° TTFT · 253 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| Kimi K3 |  Relace | $0.182 | $11.01 | 1.6s° | 128° tok/s | — |
| Kimi K3 |  Wafer | $0.192 | $16.00 | 0.81s° | 135° tok/s | 0/5 |
| Kimi K3 |  InferenceNet | $0.234 | $15.00 | 0.74s° | 99° tok/s | — |
| gpt-oss-120b |  Near AI | $0.03 | $0.15 | 1.6s° | 73° tok/s | — |
| gpt-oss-120b |  Venice | $0.03 | $0.15 | 1.9s° | 60° tok/s | — |
| gpt-oss-120b |  CoreWeave | $0.03 | $0.17 | 0.79s° | 80° tok/s | 3/5 |
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