modelbenchmark.io

Llama 3.3 70B Turbo

Meta · llama-3-3-70b-instruct-turbo

Compare

Compact Llama instruction model for fast chat and local deployment

Specification

most-agreed values

Context
131K
Max output
16K
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
$0.10
Output
$0.32

Available from 4 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
deepinfra$0.10$0.32131K131K
deepinfra · meta-llama$0.10$0.32131K16K
together_ai$1.04$1.04131K
togetherai · meta-llama$1.04$1.04131K131K

More from Meta

most-hosted first