Gemma 4 31B vs gpt-oss-120b
API pricing, context, and independently measured performance, side by side. gpt-oss-120b starts 70% cheaper on input than Gemma 4 31B at list prices.
Gemma 4 31B
Google · released Apr 2, 2026
Best input$0.10 / MTok
Best output$0.335 / MTok
Context262K
Providers18
Fastest measured0.49s° TTFT · 106 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
gpt-oss-120b
OpenAI · released Aug 5, 2025
Best input$0.03 / MTok
Best output$0.15 / MTok
Context131K
Providers25
Fastest measured0.21s° TTFT · 248 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| Gemma 4 31B | KTKT | $0.10 | $0.34 | — | — | — |
| Gemma 4 31B | $0.10 | $0.34 | 1.5s° | 33° tok/s | 5/5 | |
| Gemma 4 31B | $0.12 | $0.36 | 2.1s° | 86° tok/s | 5/5 | |
| gpt-oss-120b | $0.03 | $0.15 | 1.6s° | 73° tok/s | — | |
| gpt-oss-120b | $0.03 | $0.15 | 17.4s° | 59° tok/s | — | |
| gpt-oss-120b | $0.03 | $0.17 | 0.6s° | 146° 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