modelbenchmark.io

Ministral 3 14B Instruct

Mistral · ministral-3-14b-instruct

Compare

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

Specification

most-agreed values

Context
100K
Max output
26K
Released
2025-12-02
Knowledge cutoff
Retires
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.37
Output
$0.50

Available from 6 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
amazon-bedrock$0.20$0.20128K4K
bedrock_converse$0.20$0.20128K8K
fireworks_ai$0.20$0.20256K256K
together_ai$0.20$0.20262K
edenai · infomaniak$0.3465$0.462100K262K
infomaniak$0.37$0.50100K26K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-12edenai · infomaniakInput$0.3478
2026-09-15edenai · infomaniakInput$0.3465
2026-09-12edenai · infomaniakOutput$0.4637
2026-09-15edenai · infomaniakOutput$0.462

More from Mistral

most-hosted first