AI Models
Control which AI models your organisation can use, set the defaults, and add custom models
Choose the AI models your organisation may use and set one default per category under Organisation → AI Models. The models sit in the tabs Language Models, Image Generation Models and Embedding Models. Each category always needs exactly one default.
Language models
Set the default
The dropdown at the top sets the default language model for the organisation. It is preselected for everyone when they start a new chat. Members with the permission Choose the AI model can switch to any other enabled model per chat. Disabled models never appear in the model picker.
The default can also be Auto: there is then no fixed organisation model, and members on Auto get a model picked per conversation. Premium models can be switched on for members but cannot be the organisation's default; the settings page explains why. If you choose a model marked as outdated, a warning first says that it is no longer recommended and offers its successor when there is one; you can still keep it.
Enable and disable models
Every model has a switch, and the counter, for example "8/20 activated", shows how many are on. Disabling a model removes it from the model picker for all members immediately. The default model cannot be disabled; choose a different default first. Hover over a model's price to see the cost of input and output per one million tokens.
The list is grouped by where the models are hosted:
| Group | Badge | Meaning |
|---|---|---|
| Hosted in EU | GDPR compliant | Data is processed within the EU |
| Hosted internationally | Not GDPR compliant | Data may be processed outside the EU. Check the provider's terms before enabling |
| Custom Models | Models your organisation added itself |
Models DeutschlandGPT recommends for most tasks carry the badge Recommended. If your organisation uses professional secrecy (§203), models without a covered provider are shown but cannot be enabled.
To enable or disable a model only for certain groups or users, open that group or user under Groups or Users and set the model's availability there.
If a Custom AI Application uses a specific model and that model is disabled, the application falls back to the organisation's default language model.
Add a custom model
Click Add Custom Model to connect a model through your own provider account. Choose the Provider, enter the Model ID and the credentials the provider needs, and switch on what the model supports: Supports Tool Calls, Vision (Image Analysis) and Supports Reasoning. Under Cost you can enter prices per one million tokens for internal cost attribution.
Custom models appear under Custom Models and can be edited or deleted there. Which provider fits and how to fill in the fields is explained under Custom models.
Image generation models
These work like language models: set a default and switch individual models on or off. The default model is used in Custom AI Applications and wherever images are generated without an explicit model choice. Members can pick a different model in their account preferences.
Enable a model in the group Hosted internationally only after checking your organisation's data-processing requirements.
Embedding models
Embedding models index uploaded files so document folders and integrations can be searched by meaning. One embedding model is active at a time.
Embeddings from different models do not fit together, so changing the embedding model re-indexes every document. Organisations rarely need to change this setting.