> For the complete documentation index, see [llms.txt](https://docs.blockbrain.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.blockbrain.ai/for-admins/ai-models.md).

# AI Models

Decide which AI models your organization uses, and what happens when a model is not available.

{% hint style="info" %}
You need the Admin role to manage AI Models.
{% endhint %}

#### Where to find it

In the Admin Panel, go to **AI Models**. The page lists every model available to your organization, with a search field above the table.

<figure><img src="https://3232460952-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIabFtGTeQzwfWCzp8vd6%2Fuploads%2FflDiH5nIrQbLXvMGonb8%2Fc-ai-models-table.jpg?alt=media&amp;token=af5070cf-6a66-4df6-b421-024813bd5c07" alt=""><figcaption></figcaption></figure>

| Column       | What it shows                                                                                           |
| ------------ | ------------------------------------------------------------------------------------------------------- |
| **Enable**   | Whether the model is switched on for your organization                                                  |
| **Name**     | The model name, its technical name, and what it can do (for example Tool calls, Reasoning, Image input) |
| **Provider** | Where the model runs, for example Anthropic on Vertex, Bedrock or STACKIT                               |
| **Region**   | Where your data is processed, for example EU or US                                                      |
| **Fallback** | The models used when this model is not available                                                        |
| **Actions**  | Opens the fallback settings                                                                             |

Newer models are listed first. Models with the same name from different providers are shown next to each other, so you can compare them.

#### Switch a model on or off

**To switch a model on:**

1. Find the model in the list.
2. Turn on the switch in the **Enable** column.

The model is now available to the people in your organization, for example in the model selection of a chat, a bot or an agent.

{% hint style="warning" %}
Once a model is switched on and in use, it cannot be switched off again. When a model goes away, Blockbrain retires it and names a replacement, so chats, bots and agents keep working. See [When a Model Is Retired](https://docs.blockbrain.ai/for-users/all-about-llms/when-a-model-is-retired.md).
{% endhint %}

#### Set a fallback chain

A fallback chain lists the models Blockbrain uses when a model does not answer, for example during a provider outage. The models are tried in order.

**To set a fallback chain:**

1. Click **Fallback** in the row of the model.
2. Pick the models to fall back to, in order. The first one you pick is tried first.
3. Click **Save**.

To remove all fallbacks of a model, open **Fallback**, untick every model and click **Save**. The model then has no fallback.

The **Fallback** column shows your own chain. **Platform default** means the model uses the chain Blockbrain set up for it.

{% hint style="info" %}
A fallback may not send data to a wider region than the model it replaces. For example, a model processed in the EU can only fall back to models processed in the EU.
{% endhint %}

#### Change history

Below the list you find the history of changes to your models: which model was made available, switched on or off, and when.

#### Auto routers

At the bottom of the page you can build your own auto router. See [Build Your Own Auto Router](https://docs.blockbrain.ai/for-admins/ai-models/build-your-own-auto-router.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.blockbrain.ai/for-admins/ai-models.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
