Gemma 4 31B vs Kimi K3.1 Pro
API pricing, context, and independently measured performance, side by side. Gemma 4 31B starts 75% cheaper on input than Kimi K3.1 Pro at list prices.
Gemma 4 31B
Google · released Apr 2, 2026
Best input$0.099 / MTok
Best output$0.165 / MTok
Context262K
Providers19
Fastest measured0.35s° TTFT · 45 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
Kimi K3.1 Pro
Moonshot AI · released Oct 23, 2026
Best input$0.40 / MTok
Best output$7.88 / MTok
Context1.05M
Providers19
Fastest measured0.77s° TTFT · 298 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| Gemma 4 31B |  PrimeIntellect | $0.099 | $0.165 | — | — | — |
| Gemma 4 31B |  CoreWeave | $0.10 | $0.34 | 1.6s° | 5° tok/s | 5/5 |
| Gemma 4 31B |  Venice | $0.12 | $0.36 | 1.4s° | 45° tok/s | 5/5 |
| Kimi K3.1 Pro |  Relace | $0.40 | $7.88 | — | — | — |
| Kimi K3.1 Pro | PRPrimaLabs | $1.80 | $9.00 | 0.77s° | 298° tok/s | — |
| Kimi K3.1 Pro |  Wafer | $1.80 | $9.00 | — | — | — |
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