modelbenchmark.io

Mistral Small 3.2 24B

Mistral · mistral-small-3-2-24b

Compare

Efficient Mistral model for fast chat, extraction, and production assistants

Specification

most-agreed values

Context
256K
Max output
16K
Released
2025-06-20
Knowledge cutoff
2023-10-31
Retires
—
Open weights
yes
Input
image, text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.021
Output
$0.054
Cache read
$0.0031

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
opencheap$0.021$0.054$0.0031—256K16K—

More from Mistral

most-hosted first