modelbenchmark.io

Ministral 14B

Mistral · ministral-14b

Compare

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

Specification

mistral listing

Context
262K
Max output
262K
Released
2025-12-04
Knowledge cutoff
2024-10
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · mistral list price

Input
$0.20
Output
$0.20
Cache read
$0.02
Cache write
$0.20

Available from 10 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
mistralvendor$0.20$0.20$0.02262K262K
kilo$0.20$0.20$0.02262K210K
llmgateway$0.20$0.20262K8K
llmgateway-providers$0.20$0.20262K262K
nano-gpt$0.20$0.20$0.10262K33K
openrouter$0.20$0.20$0.02262K
210K
262K
pioneer$0.20$0.20$0.20$0.20256K131K
vercel$0.20$0.20256K256K
cortecs$0.24$0.24$0.022256K256K
302ai$0.33$0.33128K128K

Price history

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

DateHostField$/M
2026-09-02cortecsInput$0.223
2026-09-15cortecsInput$0.24
2026-09-02cortecsOutput$0.223
2026-09-15cortecsOutput$0.24

More from Mistral

most-hosted first