Apertus 70B

apertus-70b-instruct 🇮🇹 Italy

The Swiss model. It speaks Italian, German, French, English and Romansh. Bigger and slower than Gemma: try it for a second opinion. Context of 16,384 tokens, 4-bit weights (w4a16) by Red Hat. Runs on NVIDIA L40S, in Italy. In service.

At a glance

Publisher	Swiss AI Initiative (EPFL, ETH Zurich, CSCS)
Architecture	Dense, 70 billion parameters
Licence	Apache 2.0
Precision	4 bits, w4a16 (Red Hat), version 2509
Context	16,384 tokens, prompt and answer together
Longest answer	`max_tokens` up to 32,768
Reads	Text
Calls tools	No
JSON schema	Yes
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.

Use it

curl https://api.ai.itsincom.org/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "apertus-70b-instruct",
    "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.itsincom.org/v1", api_key=os.environ["API_KEY"])
answer = client.chat.completions.create(
    model="apertus-70b-instruct",
    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 16,384 tokens; beyond that the engine refuses the request with a 400 that says so.
Served without tool calling: a request with tools gets a 400 that names the models that have it.
Text only: a request with an image gets a 400.
Served at 4 bits, which makes it faster and fits our machines; we write the precision of every model.
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.