Open models, run by us in Germany
We run open-weight models only. Development, data storage and AI inference all happen in Germany.
- Qwen
- Gemma
- OpenAI
- Mistral
These are the openly published models of the providers named above, run by us – not their APIs. Your inputs never reach those providers.
Open weights, run in Germany
A model is, at bottom, a file of weights. Whoever published it does not decide where your data goes – whoever runs it does. That is why we run open models on infrastructure in Germany, instead of sending every request to somebody else’s API. Which models are available inside your instance is decided by your administrators, and a specific model can be pinned per agent.
Why we run open models only
An open model is published as a file of weights. Anyone who wants to use it downloads it and runs it on hardware they own or rent. That is the distinction that matters in data protection terms: whoever published the model does not decide where your data goes, whoever runs it does. At Intra AI that is us, in Germany.
The selection changes, the rule does not
Open models move quickly, and we swap the selection as soon as a better one appears – which is why this page names providers rather than version numbers. What does not change: open weights, run by us in Germany. Which models are available inside your instance is decided by your administrators, and a specific model can be pinned per agent.
What your documents pass through before a model answers
For document search your text is split into passages and turned into vectors that sit in your instance’s own database. The retrieved passages are then ordered by relevance. Open models do both, and we run them in Germany.
What this gives your data protection officer
For a record of processing activities it means one named processor per model endpoint rather than an open chain of AI vendors, and no transfer to the United States for AI inference. That your content is never used for training is a commitment we make contractually. The Article 28 GDPR data processing agreement, with the list of subprocessors, is available before you sign.
Frequently asked questions
Which AI models does Intra AI run?
Open-weight models only. The providers whose models are in the selection today are named above; which of them are available inside your instance is your administrators' decision. We deliberately leave version numbers off this page, because we keep the selection current as better models appear.
What does “open weights” mean?
The model’s trained parameters are published, so anyone can download them and run the model themselves. We run open-weight models only. That is a decision about how we operate, not a limit of the platform: an administrator can add a further provider at runtime.
Are my inputs sent to the providers of those models?
No. Those companies published the model weights; the models themselves are operated by us, in Germany. There is no connection to an API run by any of the providers named.
Where are the models run?
In Germany. Development, data storage and AI inference all happen here, on infrastructure we are accountable for.
Is my data used for training?
No. Neither we nor the subprocessors we use apply your content to train or retrain a model. We commit to that contractually.
Can we connect our own or other models?
Yes. An administrator can add a further provider with an OpenAI-compatible endpoint to your instance, including a model you run yourself. Our default is open models that we run in Germany; if you want to depart from that, talk to us first so we can work through what it means for your data processing agreement.
Which model suits you is a conversation, not a checkbox
Why we run open models only, and what that means for your documents, is set out above. Which one answers your questions best is something we work out together – including when the smaller one is enough.
Qwen, Gemma, OpenAI and Mistral are trademarks of their respective owners. They are named here solely to identify the models whose open weights we operate. No affiliation, sponsorship or endorsement by those companies is implied.