modelbenchmark.io

Ministral 3 8B

Mistral · ministral-3-8b-instruct

Compare

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Specification

most-agreed values

Context
262K
Max output
262K
Released
2025-12-15
Knowledge cutoff
Retires
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.15
Output
$0.15

Available from 4 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
amazon-bedrock$0.15$0.15128K4K
bedrock_converse$0.15$0.15128K8K
fireworks_ai$0.20$0.20256K256K
digitalocean262K262K

Other listings of this model

same model, different key

More from Mistral

most-hosted first