Catalogue
Models catalog
What we can serve you: what is already loaded, what we start on request, and where each model runs.
Ready to use
Already loaded: the first request answers without a start-up wait. There are 2. Each one lists its zones: groups of machines, each in one country, with a declared owner. A request never leaves the zones allowed for your key, and so never leaves their countries.
Apertus 70B
apertus-70b-instruct
The model of the Swiss AI Initiative — EPFL, ETH Zurich and CSCS. It speaks Italian, German, French, English and Romansh. Bigger and slower than Gemma: try it for a second opinion.
Precision: Versione compressa a 4 bit pubblicata da Red Hat, a partire dai pesi ufficiali di swiss-ai
Gemma 4 26B
gemma-4-26b
The default: it answers in a few seconds. It reads images as well as text, so it is useful for photos of documents, scans and screenshots, and it is good at extracting structured data from free text.
Precision: Versione compressa a 8 bit pubblicata da Red Hat, a partire dai pesi ufficiali di Google
If you need a model that is not listed
Ask us. Any open-weight model that fits the capacity we have can be added: it is a mechanical operation, not a project. The list above is what we serve today, not the limit of what we can serve.
What we do not do is resell the closed models of OpenAI or Anthropic: we could not run them ourselves, so we could not make any of the commitments we make on everything else.
Write to segreteria@itsincom.it.
Audio
Transcription with whisper-1 and whisper-1-hd; speech with the voices
paola and riccardo in Italian, amy and ryan in
English, thorsten in German, siwis in French. OpenAI voice names are
accepted as synonyms. Details in Audio API.