modelbenchmark.io

Llama 3.1 405B Instruct Turbo

Meta · meta-llama-3-1-405b-instruct-turbo

Compare

Compact Llama instruction model for fast chat and local deployment

Specification

most-agreed values

Context
128K
Max output
4K
Released
2024-07-23
Knowledge cutoff
Retires
2026-02-06
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$3.50
Output
$3.50

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
abacus · meta-llama$3.50$3.50128K4K
together_ai$3.50$3.502026-02-06

More from Meta

most-hosted first