modelbenchmark.io

Mistral Small 3.2

Mistral · mistral-small-3-2-24b-instruct

Compare

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

Specification

most-agreed values

Context
128K
Max output
33K
Released
2025-06-20
Knowledge cutoff
2025-03
Retires
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.075
Output
$0.20
Cache read
$0.10

Available from 13 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
meganovafreefree33K8K
deepinfra$0.075$0.20128K128K
kilo$0.075$0.20128K16K
openrouter$0.075$0.20
256K
128K
16K
128K
ovhcloud · ovhcloud$0.09$0.28128K128K
venice$0.0938$0.25256K16K
cortecs$0.10$0.312131K131K
ovhcloud$0.10$0.31131K131K
scaleway$0.15$0.35128K33K
scaleway · scaleway$0.15$0.35128K33K
nano-gpt$0.20$0.40$0.10128K16K
greenpt$0.228$0.456128K33K
berget$0.33$0.3332K8K

Price history

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

DateHostField$/M
2026-09-02openrouterInput$0.075
2026-09-06openrouterInput$0.075
2026-09-02openrouterOutput$0.20
2026-09-06openrouterOutput$0.20

Other listings of this model

same model, different key

More from Mistral

most-hosted first