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

# Models

In **Models**, you choose which AI models workspace users can access and which one is the default.

Here are the available features:

### Browse the tabs <a href="#browse-the-tabs" id="browse-the-tabs"></a>

The page is organized into the following tabs:

* **Models:** models available in the workspace.
* **Routing:** model routing rules.
* **Video:** video generation models.

At the top of the **Models** tab, you'll see the number of active models out of the total (e.g., **23 of 29 models active**) and when the catalog was last synced.

### Your brand's model family <a href="#your-brands-model-family" id="your-brands-model-family"></a>

The first section lists the Astro family models, shown under your workspace's brand name. These models are always on and appear first for users.

{% hint style="info" %}
Family models show the **Always available** indicator and can't be turned off.
{% endhint %}

### Partner models <a href="#partner-models" id="partner-models"></a>

The **Partner models** section lists models from other providers, such as OpenAI, Anthropic, Google, and xAI. Their availability depends on the catalog.

To turn a partner model on or off, click the **Active** toggle next to it.

### Model details <a href="#model-details" id="model-details"></a>

Each model shows the following information:

* **Name and badges:** the model name and badges such as **Best AI**, **Featured**, **Default**, and **Available**.
* **Provider and identifier:** the company behind the model and its technical identifier (for partner models).
* **Context:** the maximum number of tokens the model can process in a conversation (e.g., **1M context**).
* **Content types:** the content the model accepts, such as **Text**, **Images**, **Files**, **Audio**, and **Video**, plus **Tool calling**.
* **Supported features:** Astro features the model supports, such as **Web search**, **File search**, **Code**, **Artifacts**, and **Documents**.

### Set the default model <a href="#set-the-default-model" id="set-the-default-model"></a>

To set the model used by default in the workspace, click **Set as default** next to the model. The model then shows the **Default** badge.

### Add a model <a href="#add-a-model" id="add-a-model"></a>

To add a new model from the catalog, follow these steps:

1. At the top of the **Models** tab, click **+ Add model**.
2. In the **Search by name or provider** field, enter the model or provider name.
3. Check each result's provider, context, and content types.
4. Click **+ Add** next to the model you want.
5. Click **Close** to finish.

The new model appears under **Partner models**, with its icon and capabilities.


---

# 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.skyone.cloud/english/admin/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.
