modelbenchmark.io

meta-llama-3-1-405b-instruct

Meta · meta-llama-3-1-405b-instruct

Compare

Specification

most-agreed values

Context
128K
Max output
2K
Released
Knowledge cutoff
Retires
2026-06-13
Open weights
Input
Output

Price

US dollars per million tokens · most-agreed

Input
$5.33
Output
$16.00
Cache read
$5.00
Cache write
$5.00

Available from 5 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
hyperbolic$0.12$0.3033K33K
nebius$1.00$3.00128K128K
databricks$5.00$15.00$5.00$5.00128K128K2026-02-15
sambanova · sambanova$5.00$10.0016K16K2025-06-25
azure_ai$5.33$16.00128K2K2026-06-13

More from Meta

most-hosted first