modelbenchmark.io

Ministral 3 14B Reasoning 2512

Mistral · ministral-3-14b-reasoning

Compare

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

Specification

most-agreed values

Context
262K
Max output
262K
Released
2025-12-01
Knowledge cutoff
2025-12
Retires
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$2.50
Output
$1.70

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
clarifai$2.50$1.70262K262K

More from Mistral

most-hosted first