modelbenchmark.io

Ministral 8B Instruct

Mistral · ministral-8b-instruct

Compare

Efficient open Mistral edge model for on-device chat and function calling

Specification

most-agreed values

Context
128K
Max output
4K
Released
2024-10-16
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.15
Output
$0.15
Cache read
$0.15
Cache write
$0.15

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
pioneer$0.15$0.15$0.15$0.15128K4K

More from Mistral

most-hosted first