modelbenchmark.io

Mistral Medium 3.1

Mistral · mistral-medium-3-1

Compare

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

Specification

most-agreed values

Context
131K
Max output
33K
Released
2025-08-12
Knowledge cutoff
2025-06-30
Retires
—
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.40
Output
$2.00
Cache read
$0.20

Available from 4 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
kilo$0.40$2.00$0.04—131K105K—
nano-gpt$0.40$2.00$0.20—131K33K—
openrouter$0.40$2.00$0.04—131K105K—
aimlapi$0.4232$2.116$0.0423—131K105K—

Price history

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

DateHostField$/M
2026-09-02openrouterCache read$0.04
2026-09-06openrouterCache read$0.04
2026-10-10openrouterCache read$0.04
2026-09-02openrouterInput$0.40
2026-09-06openrouterInput$0.40
2026-10-10openrouterInput$0.40
2026-09-02openrouterOutput$2.00
2026-09-06openrouterOutput$2.00
2026-10-10openrouterOutput$2.00
2026-10-13aimlapiCache read$0.055
2026-10-23aimlapiCache read$0.0423
2026-10-13aimlapiInput$0.5502
2026-10-23aimlapiInput$0.4232
2026-10-13aimlapiOutput$2.7508
2026-10-23aimlapiOutput$2.116

More from Mistral

most-hosted first