modelbenchmark.io

Llama 4 Maverick 17B Instruct (US)

Meta · llama4-maverick-17b-instruct

Compare

Open multimodal Llama for strong reasoning with efficient everyday serving

Specification

most-agreed values

Context
1M
Max output
8K
Released
2025-04-05
Knowledge cutoff
2024-08
Retires
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.24
Output
$0.97

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputbedrock_converse$0.12
Batch outputbedrock_converse$0.485

Batch input is 50% below the interactive input price at the same listing.

Available from 4 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
amazon-bedrock$0.24$0.971M8K
amazon-bedrock · us$0.24$0.971M8K
bedrock_converse$0.24$0.97128K4K
bedrock_converse · us$0.24$0.97128K4K

More from Meta

most-hosted first