Mistral Small 3.2 24B

mistral-small-3.2-24b 🇮🇹 Italy

Mistral Small 3.2 di Mistral AI (giugno 2025): denso da 24 miliardi di parametri, segue bene le istruzioni e usa gli strumenti. Solo testo. Contesto di 32.768 token, pesi a 8 bit pubblicati da Red Hat AI. Gira su una RTX 5090 a Varese.

At a glance

Precision	Versione a 8 bit (FP8) pubblicata da Red Hat AI
Longest answer	`max_tokens` up to 32,768
Reads	Text
Calls tools	Not tried yet
JSON schema	Not tried yet
Reasons	No, as served: it answers straight away.
Runs in	🇮🇹 Italy
Status	Loaded: the first request answers without a start-up wait. Live state on Status.
Price	`mistral-small-3.2-24b@rtx5090`: € 0,172500 input · € 0,480000 output , per million tokens, excluding VAT. All prices

Use it

curl https://api.ai-tokens.it/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral-small-3.2-24b",
    "messages": [{"role": "user", "content": "Summarise in one line: the meeting moves to Thursday at 10."}]
  }'

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.ai-tokens.it/v1", api_key=os.environ["API_KEY"])
answer = client.chat.completions.create(
    model="mistral-small-3.2-24b",
    messages=[{"role": "user", "content": "Summarise in one line: the meeting moves to Thursday at 10."}],
)
print(answer.choices[0].message.content)

More in Quickstart and Chat completions.

Limits

Text only: a request with an image gets a 400.
A request goes only to the zones your key allows; if the model has no machine there now, a 503 names the zones. It is never sent elsewhere.