Llama 4 Maverick vs Llama 4 Scout
API pricing, context, and independently measured performance, side by side. Llama 4 Scout starts 50% cheaper on input than Llama 4 Maverick at list prices.
Llama 4 Maverick
Meta · released Apr 5, 2025
Best input$0.20 / MTok
Best output$0.696 / MTok
Context1.05M
Providers5
Fastest measured0.37s° TTFT · 110 tok/s
Open weightsVisionToolsStructured outputPrompt caching
Llama 4 Scout
Meta · released Apr 5, 2025
Best input$0.10 / MTok
Best output$0.30 / MTok
Context1.31M
Providers4
Fastest measured0.41s° TTFT · 50 tok/s
Open weightsVisionToolsStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | DIDigitalOcean | $0.20 | $0.696 | 1s° | 24° tok/s | 5/5 |
| Llama 4 Maverick |  DeepInfra | $0.20 | $0.80 | 0.37s° | 95° tok/s | 4/5 |
| Llama 4 Maverick |  Novita | $0.27 | $0.85 | 0.37s° | 110° tok/s | 4/5 |
| Llama 4 Scout | DeepInfra | $0.10 | $0.30 | 0.41s° | 50° tok/s | — |
| Llama 4 Scout |  Groq | $0.11 | $0.34 | 0.67s° | 439° tok/s | — |
| Llama 4 Scout | Novita | $0.18 | $0.59 | 0.86s° | 77° tok/s | — |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 72h) · 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