modelbenchmark.io

Llama 3.3 Instruct (70B)

Meta · llama3-3-70b-instruct

Compare

Open Llama instruction model for multilingual chat, reasoning, and coding

Specification

most-agreed values

Context
128K
Max output
4K
Released
2024-12-06
Knowledge cutoff
2023-12
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.65
Output
$0.65

Available from 6 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
digitalocean$0.65$0.65128K4K
gradient_ai · gradient-ai$0.65$0.65128K2K
amazon-bedrock$0.72$0.72128K4K
amazon-bedrock · us$0.72$0.72128K4K
bedrock_converse$0.72$0.72128K4K
bedrock_converse · us$0.72$0.72128K4K

More from Meta

most-hosted first