modelbenchmark.io

Llama 4 Scout 17B Instruct

Meta · llama4-scout-17b-instruct

Compare

Open Llama with long-context vision for efficient multimodal agents

Specification

most-agreed values

Context
10M
Max output
8K
Released
2025-04-05
Knowledge cutoff
2024-08
Retires
2027-03-30
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.17
Output
$0.66

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputbedrock_converse$0.085
Batch outputbedrock_converse$0.33

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

Available from 4 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
amazon-bedrock$0.17$0.66——10M8K—
amazon-bedrock · us$0.17$0.66——10M8K—
bedrock_converse$0.17$0.66——10M8K2027-03-30
bedrock_converse · us$0.17$0.66——10M8K2027-03-30

Other listings of this model

same model, different key

More from Meta

most-hosted first