Kimi K3 vs gpt-oss-120b
API pricing, context, and independently measured performance, side by side. gpt-oss-120b starts 98% cheaper on input than Kimi K3 at list prices.
Kimi K3
Moonshot AI · released Jul 16, 2026
Best input$1.50 / MTok
Best output$9.75 / MTok
Context1.05M
Providers22
Fastest measured0.63s° TTFT · 102 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
gpt-oss-120b
OpenAI · released Aug 5, 2025
Best input$0.03 / MTok
Best output$0.17 / MTok
Context131K
Providers26
Fastest measured0.28s° TTFT · 233 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| Kimi K3 | SRSail Research | $1.50 | $10.76 | 1.6s° | 142° tok/s | 2/5 |
| Kimi K3 |  InferenceNet | $1.95 | $9.75 | 57.9s° | 7° tok/s | — |
| Kimi K3 |  Relace | $1.95 | $9.75 | — | — | — |
| gpt-oss-120b |  AkashML | $0.03 | $0.17 | 1.3s° | 71° tok/s | 4/5 |
| gpt-oss-120b |  CoreWeave | $0.03 | $0.17 | 0.69s° | 96° tok/s | 3/5 |
| gpt-oss-120b | DEDekaLLM | $0.03 | $0.18 | — | — | — |
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