0

Llama 4 Scout

Open weights

Meta's small Llama 4 variant - 17B-active / 109B-total MoE that fits on a single H100, with a 10M-token context window.

Family
Llama 4
Params
109B total / 17B active (16 experts)
Context
10M
Input
Output
Released
Apr 2025

Cite

Notes

Only stored in your browser.

Context
10M
Input
$0.17
/1M tok
Output
$0.66
/1M tok
Blended
$0.29
#230/ 414/1M · 3:1
Speed
116
#92/ 414tok/s

Price & speed via Artificial Analysis · ranked across tracked models

Reported on 13 evals across 8 domains - best 84.4% on MATH-500 · #75 of 178

Reported eval scores

13