modelbenchmark.io

llama-4-scout-17b-128e-instruct-maas

Meta · llama-4-scout-17b-128e-instruct-maas

Compare

Specification

most-agreed values

Context
10M
Max output
10M
Released
Knowledge cutoff
Retires
Open weights
Input
Output

Price

US dollars per million tokens · most-agreed

Input
$0.25
Output
$0.70

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
vertex_ai-llama_models$0.25$0.7010M10M

More from Meta

most-hosted first