modelbenchmark.io

Mistral: Mixtral 8x7B Instruct

Mistral · mixtral-8x7b-instruct

Compare

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Specification

most-agreed values

Context
33K
Max output
16K
Released
2023-12-10
Knowledge cutoff
Retires
2025-04-30
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
free
Output
free
Cache read
$0.50
Cache write
$0.50

Available from 7 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nvidiafreefree33K16K
perplexity$0.07$0.284K4K
deepinfra$0.40$0.4033K33K
databricks$0.50$1.00$0.50$0.504K4K2025-04-30
fireworks_ai$0.50$0.5033K33K
bedrock
$0.59
$0.45
$0.91
$0.70
32K8K
together_ai$0.60$0.602026-04-16

More from Mistral

most-hosted first