# AI models for Chat (Enterprise SaaS)

Tabnine offers different[ AI Models](/main/welcome/readme/ai-models.md) for Tabnine Chat. Tabnine Enterprise admins (in Tabnine SaaS) control which models are available to the users in their organization according to the organization. By default, only the *Tabnine Protected* model is available. The admin can enable other models:

* <img src="/files/Lf2tZyQjg67zx6POgI8X" alt="" data-size="line"> Claude 3.7 Sonnet (default)
* <img src="/files/Lf2tZyQjg67zx6POgI8X" alt="" data-size="line"> Claude 3.5 Sonnet
* <img src="/files/DCz39ycVVRJL3VHAt9tf" alt="" data-size="line"> GPT-4o
* <img src="/files/dtt4RiP0NeIsK4GV9ECD" alt="" data-size="line"> Command R+
* <img src="/files/2tVLxNq2lsCJ9Dgw5TTA" alt="" data-size="line">+ <img src="/files/dqGl5n1UhezEbYXxPdSK" alt="" data-size="line"> Tabnine + Mistral

{% hint style="info" %}
Tabnine's code completions only use the **Tabnine Universal code completions model,** which is both private and protected.
{% endhint %}

[Learn more](/main/welcome/readme/ai-models.md#tabnine-gives-you-the-insight-you-need-to-choose)

### Setting the available chat AI models

{% hint style="info" %}
If this functionality is not visible, we recommend contacting your dedicated account manager at Tabnine. They will assist you in setting the available chat AI models for your team.
{% endhint %}

1. Sign in to Tabnine's **Admin console**.
2. Go to the [**Models**](https://app.tabnine.com/profile/settings/models) page under **Settings.**
3. Enable the models you want for your team (you can select multiple) by toggling the switch.
4. The changes will take effect immediately, allowing your team's end users to choose from the available models.


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.tabnine.com/main/administering-tabnine/saas/enterprise-saas-team-admin/setting-the-available-ai-models-for-chat.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.