Llama 4 Scout

Llama 4 Scout is the best multimodal model in the world in its class and is more powerful than our Llama 3 models, while fitting in a single H100 GPU. Additionally, Llama 4 Scout supports an industry-leading context window of up to 10M tokens.

Introducing Llama 4

TypeLanguage

ReleaseApr 5, 2025

Context327,680

Tagstool-use, vision

10.0

8.2

$0.300/M

* Cost is inverted: lower input, output, and blended prices rank higher.

Model Details

Runtime

Output Speed112.8 tok/s

First Token0.60s

Max Output16,384

Pricing

Blended$0.300/M

Input$0.180/M

All Benchmarks

Metric	Domain	Value	Rank
Artificial Analysis Intelligence Index	overall	10.0	#390
Artificial Analysis Coding Index	coding	8.2	#249
Artificial Analysis Math Index	math	14.0	#221
MMLU-Pro	reasoning	75.2%	#156

Llama 4 Scout

Model Snapshot

Overall

Coding

Blended Price

Strength Profile

Benchmark Percentiles

Model Details

Runtime

Pricing

All Benchmarks

Metadata