Llama 3.3 70B Instruct vs gpt-oss-20b
API pricing, context, and independently measured performance, side by side. gpt-oss-20b starts 80% cheaper on input than Llama 3.3 70B Instruct at list prices.
Llama 3.3 70B Instruct
Meta · released Dec 6, 2024
Best input$0.10 / MTok
Best output$0.32 / MTok
Context131K
Providers13
Fastest measured—
Open weightsToolsStructured outputPrompt caching
gpt-oss-20b
OpenAI · released Aug 5, 2025
Best input$0.02 / MTok
Best output$0.10 / MTok
Context131K
Providers13
Fastest measured1s° TTFT · 54 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| Llama 3.3 70B Instruct |  DeepInfra | $0.10 | $0.32 | — | — | 5/5 |
| Llama 3.3 70B Instruct |  Nebius | $0.13 | $0.40 | — | — | 5/5 |
| Llama 3.3 70B Instruct |  Novita | $0.135 | $0.40 | — | — | 5/5 |
| gpt-oss-20b | DADarkbloom | $0.02 | $0.10 | — | — | — |
| gpt-oss-20b | CWCoreWeave | $0.03 | $0.13 | — | — | 5/5 |
| gpt-oss-20b | DeepInfra | $0.03 | $0.14 | — | — | 2/5 |