modelbenchmark.io

Llama 3.1 8B Instruct fp8

Meta · llama-3-1-8b-instruct-fp8

Compare

Open Llama instruction model for multilingual chat, reasoning, and coding

Specification

most-agreed values

Context
32K
Max output
32K
Released
2024-07-23
Knowledge cutoff
2023-12
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.152
Output
$0.287

Rate limits

Requests per minute
300

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
cloudflare$0.152$0.28732K32K
cloudflare-workers-ai · cf$0.152$0.28732K32K

More from Meta

most-hosted first