modelbenchmark.io

Groq-Llama-4-Maverick-17B-128E-Instruct

Meta · llama-4-maverick-17b-128e-instruct

Compare

Open multimodal Llama model for strong reasoning and fast responses

Specification

most-agreed values

Context
128K
Max output
4K
Released
2025-04-05
Knowledge cutoff
2025-01
Retires
2026-03-09
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
free
Output
free

Available from 4 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
llamafreefree128K4K
nvidiafreefree128K4K
groq$0.20$0.60131K8K2026-03-09
sambanova · sambanova$0.63$1.80131K131K

More from Meta

most-hosted first