modelbenchmark.io

Llama 3.1 405B

Meta · llama-3-1-405b-instruct

Compare

Llama 3.1 405B hosted by IONOS in Berlin, Germany. Zero data retention.

Specification

most-agreed values

Context
131K
Max output
8K
Released
2026-09-10
Knowledge cutoff
2023-12
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$2.0265
Output
$2.0265

Available from 4 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
cortecs$1.95$1.95128K128K
nano-gpt · meta-llama$2.0265$2.0265131K8K
together_ai$3.50$3.50
oci · oci$10.68$10.68128K4K

Other listings of this model

same model, different key

More from Meta

most-hosted first