modelbenchmark.io

llama-2-70b-chat

Meta · llama-2-70b-chat

Compare

Specification

most-agreed values

Context
4K
Max output
4K
Released
Knowledge cutoff
Retires
2024-10-30
Open weights
Input
Output

Price

US dollars per million tokens · most-agreed

Input
$0.50
Output
$1.50
Cache read
$0.50
Cache write
$0.50

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
databricks$0.50$1.50$0.50$0.504K4K2024-10-30
replicate · replicate$0.65$2.754K4K
perplexity$0.70$2.804K4K

Other listings of this model

same model, different key

More from Meta

most-hosted first