SPEC DATASHEET // llama-4-scout
Meta AI/RELEASED May 10, 2026
Llama 4 Scout (16E)
LONG CONTEXT MOEExtended-context open-weights model capable of ingesting 1.31 million tokens in a single prompt for codebase-wide document analysis.
Context
1,310,720 tokens
Architecture
16-Expert MoE
Pricing (1M)
Free / Open
License
Meta Community License
Verified Benchmark Suite
MMLU-PRO
78.4%
Quickstart Snippet
curl -s https://modelregistry.tirup.in/api/cli?model=llama-4-scout