Catalogue
Models catalogue
What we can serve you: what is already loaded, what we start on request, and the country where each model runs.
Compare
The chat models we serve now, with the values we serve: context in tokens, prompt and answer together; the longest answer is max_tokens up to 8,192 on every model. Choose what you need:
All countries 🇨🇭 Switzerland Calls tools Reads images Reasons
| Model | Runs in | Context | Tools | Images | Reasons | CHF / 1M in · out |
|---|---|---|---|---|---|---|
| No model matches. Show all. | ||||||
«—» means not tried yet. Every value comes from our engines or from a request through the API, not from the publisher's card.
Ready to use
Already loaded: the first request answers without a start-up wait. There are 7. Each one lists the countries where it runs. A request never leaves the zones allowed for your key — groups of machines, each in one country — and so never leaves their countries.
apertus-70b-instruct
The Swiss model of the Swiss AI Initiative — EPFL, ETH Zurich and the Swiss National Supercomputing Centre. It speaks Italian, German, French, English and Romansh. The default choice for conversation and for answers about your documents.
Precision: 4 bits, w4a16 (Red Hat), version 2509 · Everything about it
CHF 1.00 input · CHF 3.00 output, per million tokens
gemma-4-26b
It reads images as well as text: useful for photos of documents, scans and screenshots. Good at returning structured data from free text, such as extracting fields from a contract or an invoice.
Precision: FP8, 8 bits (Red Hat) · Everything about it
CHF 0.30 input · CHF 0.60 output, per million tokens
qwen2.5:32b
The most capable of the mid-size models: suited to questions that need several steps of reasoning, not just rewording. Recommended for analysing and summarising complex documents.
Precision: 4 bits (Ollama) · Everything about it
CHF 0.30 input · CHF 0.90 output, per million tokens
qwen2.5:14b
A good balance of quality and speed. The right choice for volume: classification, summaries, first drafts, answers to frequent questions.
Precision: 4 bits (Ollama) · Everything about it
CHF 0.15 input · CHF 0.45 output, per million tokens
qwen2.5:1.5b
A light, very fast model, for simple and repetitive tasks where response time matters more than nuance.
Precision: 4 bits (Ollama) · Everything about it
CHF 0.05 input · CHF 0.10 output, per million tokens
bge-m3
Turns a text into a numerical representation that lets you search by meaning instead of exact words. It is the engine of the search in your documents. It works on texts in different languages, even mixed.
CHF 0.12 per million input tokens
bge-reranker-v2-m3
A second pass over the results of a search: it rereads the candidates together with the question and reorders them by actual relevance. It brings the right answer to the top, not just the one that looks most like the words searched for.
Not charged
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 support@siati.ai.
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.