Comparison

Llama 4 Maverick vs Llama 4 Scout

Llama 4 Scout costs 33% less per input token than Llama 4 Maverick. Output pricing favors Llama 4 Scout, 50% less per token than Llama 4 Maverick. Llama 4 Scout accepts more context per request than Llama 4 Maverick.

FieldLlama 4 Maverick
Llama 4 Scout
ProviderMetaMeta
Context window1M10M
Max output
Input / 1M$0.15$0.1033% cheaper
Output / 1M$0.60$0.3050% cheaper
Cached input / 1M
Batch discount
Release date2025-04-05

Worked cost examples

Estimated monthly cost on three common usage shapes

WorkloadLlama 4 MaverickLlama 4 Scout

Chatbot

800 input / 200 output tokens per request, 100,000 requests/month

$24.00$14.00cheaper

RAG pipeline

6,000 input / 700 output tokens per request, 30,000 requests/month

$39.60$24.30cheaper

Batch summarization

20,000 input / 1,500 output tokens per request, 5,000 requests/month

$19.50$12.25cheaper

Llama 4 Maverick vs Llama 4 Scout FAQ

Is Llama 4 Maverick cheaper than Llama 4 Scout?
Llama 4 Maverick costs $0.15 per 1M input tokens versus $0.10 for Llama 4 Scout — Llama 4 Scout is 50% cheaper per input token.
Which is cheaper for output tokens, Llama 4 Maverick or Llama 4 Scout?
Llama 4 Maverick charges $0.60 per 1M output tokens; Llama 4 Scout charges $0.30 per 1M output tokens.
Which has the larger context window, Llama 4 Maverick or Llama 4 Scout?
Llama 4 Scout does, with a 10,000,000-token context window.
Do Llama 4 Maverick and Llama 4 Scout offer cache pricing?
Llama 4 Maverick has no documented cache discount. Llama 4 Scout has no documented cache discount.

Looking for another matchup? See all comparisons.