Mistral Medium 3.5

mistral-medium-3.5-128b 🇨🇭 Switzerland

Mistral Medium 3.5 di Mistral AI (aprile 2026), il suo modello aperto più forte: denso, 128 miliardi di parametri, legge immagini e usa strumenti. Bravo con il codice e con i compiti lunghi; così come lo serviamo risponde senza ragionare prima. Contesto di 262.144 token, pesi a 8 bit pubblicati da Mistral AI.

At a glance

Publisher	Mistral AI
Architecture	Dense, 128 billion parameters
Licence	Modified MIT
Precision	FP8, 8 bits (Mistral)
Context	262,144 tokens, prompt and answer together
Longest answer	`max_tokens` up to 8,192
Reads	Text and images
Calls tools	Yes
JSON schema	Yes
Reasons	No, as served: it answers straight away.
Runs in	🇨🇭 Switzerland
Status	Loaded: the first request answers without a start-up wait. Live state on Status.
Price	CHF 1,40 input · CHF 7,00 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-medium-3.5-128b",
    "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-medium-3.5-128b",
    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

Prompt and answer together stay within 262,144 tokens; beyond that the engine refuses the request with a 400 that says so.
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.