> For the complete documentation index, see [llms.txt](https://docs.tabnine.com/main/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.tabnine.com/main/administering-tabnine/managing-your-team/settings/models-settings.md).

# Models

{% hint style="warning" %}
The following models will no longer be supported after version 6.2.0 (mid-May):

* Tabnine-protected
* Gemma 3 or lower
* Qwen 2.5 or lower

Accounts that use these models wont be able to upgrade to this version
{% endhint %}

Tabnine provides various [AI models](/main/welcome/readme/ai-models.md) for Tabnine Chat. Tabnine Enterprise admins can connect Tabnine to their internal endpoints to enrich the Tabnine Chat experience for users. This allows administrators to integrate their company's private LLM instances, making them accessible to the engineering team directly within Tabnine.

{% hint style="info" %}
**Note**

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

### Private Model Endpoints Supported by Tabnine

{% hint style="info" %}
**Note**

The list of supported models is updated frequently as new models become available.
{% endhint %}

Currently, Tabnine supports the following model providers for private endpoint connections:

<table><thead><tr><th width="61.4912109375"></th><th width="171.7060546875">Model</th><th width="101.4326171875">Bedrock</th><th width="100.5">GCP Vertex AI</th><th width="101.037109375">Azure</th><th width="101.359375">OpenAI</th><th>OpenAI-Compatible</th></tr></thead><tbody><tr><td><img src="/files/ehKb26kkI3TCh6niNuXg" alt="" data-size="original"></td><td>Claude 4.8 Opus</td><td>✓</td><td>✓</td><td></td><td></td><td></td></tr><tr><td><img src="/files/ehKb26kkI3TCh6niNuXg" alt="" data-size="original"></td><td>Claude 4.7 Opus</td><td>✓</td><td>✓</td><td></td><td></td><td></td></tr><tr><td><img src="/files/KIxcWuNTeFglIToJ1TOO" alt=""></td><td>Claude 4.6 Sonnet</td><td>✓</td><td>✓</td><td></td><td></td><td></td></tr><tr><td><img src="/files/KIxcWuNTeFglIToJ1TOO" alt=""></td><td>Claude 4.6 Opus</td><td>✓</td><td>✓</td><td></td><td></td><td></td></tr><tr><td><img src="/files/KIxcWuNTeFglIToJ1TOO" alt=""></td><td>Claude 4.5 Sonnet</td><td>✓</td><td>✓</td><td></td><td></td><td></td></tr><tr><td><img src="/files/KIxcWuNTeFglIToJ1TOO" alt=""></td><td>Claude 4.5 Opus</td><td>✓</td><td>✓</td><td></td><td></td><td></td></tr><tr><td><img src="/files/KIxcWuNTeFglIToJ1TOO" alt=""></td><td>Claude 4.5 Haiku</td><td>✓</td><td>✓</td><td></td><td></td><td></td></tr><tr><td><img src="/files/KIxcWuNTeFglIToJ1TOO" alt=""></td><td>Claude 4 Sonnet</td><td>✓</td><td>✓</td><td></td><td></td><td></td></tr><tr><td><img src="/files/aZE3dBcLf9McsmRjtFlC" alt="" data-size="original"></td><td>Gemini 3.5 Flash</td><td></td><td>✓</td><td></td><td></td><td></td></tr><tr><td><img src="/files/aZE3dBcLf9McsmRjtFlC" alt="" data-size="original"></td><td>Gemini 3.1 Pro</td><td></td><td>✓</td><td></td><td></td><td></td></tr><tr><td><img src="/files/4dtgR6lZK2KdD0FKnJE8" alt=""></td><td>Gemini 3.0 Pro</td><td></td><td>✓</td><td></td><td></td><td></td></tr><tr><td><img src="/files/4dtgR6lZK2KdD0FKnJE8" alt=""></td><td>Gemini 2.5 Flash</td><td></td><td>✓</td><td></td><td></td><td></td></tr><tr><td><img src="/files/4dtgR6lZK2KdD0FKnJE8" alt=""></td><td>Gemini 2.5 Pro</td><td></td><td>✓</td><td></td><td></td><td></td></tr><tr><td><img src="/files/4gJScAlARvPyXM5W30xY" alt="" data-size="original"></td><td>GPT-5.5</td><td></td><td></td><td>✓</td><td>✓</td><td></td></tr><tr><td><img src="/files/MfGCArjNflkE2vlMbv1D" alt=""></td><td>GPT-5.4</td><td></td><td></td><td>✓</td><td>✓</td><td></td></tr><tr><td><img src="/files/MfGCArjNflkE2vlMbv1D" alt=""></td><td>GPT-5.3 Codex</td><td></td><td></td><td>✓</td><td>✓</td><td></td></tr><tr><td><img src="/files/MfGCArjNflkE2vlMbv1D" alt=""></td><td>GPT-5.2 Codex</td><td></td><td></td><td>✓</td><td>✓</td><td></td></tr><tr><td><img src="/files/MfGCArjNflkE2vlMbv1D" alt=""></td><td>GPT-5.2</td><td></td><td></td><td>✓</td><td>✓</td><td></td></tr><tr><td><img src="/files/MfGCArjNflkE2vlMbv1D" alt=""></td><td>GPT-5</td><td></td><td></td><td>✓</td><td>✓</td><td></td></tr><tr><td><img src="/files/MfGCArjNflkE2vlMbv1D" alt="" data-size="original"></td><td>GPT-4o</td><td></td><td></td><td>✓</td><td>✓</td><td></td></tr><tr><td><img src="/files/31ub9jAlMwkkkNctGS1t" alt="" data-size="original"></td><td>Devstral-Small-2-24B-Instruct-2512</td><td></td><td></td><td></td><td></td><td>✓</td></tr><tr><td><img src="/files/31ub9jAlMwkkkNctGS1t" alt="" data-size="original"></td><td>Devstral-2-123B-Instruct-2512**</td><td></td><td></td><td></td><td></td><td>✓</td></tr><tr><td><img src="/files/Q3WcyouKrls19ukiF0ma" alt=""></td><td>MiniMax 2.7</td><td></td><td></td><td></td><td></td><td>✓</td></tr><tr><td><img src="/files/UBFtbvBdHr6XVc2eZfAv" alt="" data-size="original"></td><td>Qwen-3-Coder-480B-A35B-Instruct</td><td></td><td></td><td></td><td></td><td>✓</td></tr><tr><td><img src="/files/UBFtbvBdHr6XVc2eZfAv" alt="" data-size="original"></td><td>Qwen-3-30B <strong>(Chat only)</strong></td><td></td><td></td><td></td><td></td><td>✓</td></tr></tbody></table>

{% hint style="info" %}
\*This list changes frequently\
\
\*\*Devstral 2 (123B parameters) is operating under a modified MIT license. If your organization's global consolidated monthly revenue is exceeding $20 million, utilizing this model requires Devstral's permission.
{% endhint %}

#### Integration Requirements for Models

<img src="/files/JjlvZ4gytknQyFjFLGaJ" alt="" data-size="line"> **Amazon Bedrock:** Region, Access Key ID, Secret Access Key | [Learn more](https://aws.amazon.com/bedrock/)

<img src="/files/vtIiXM8aZFF93VNhRrGS" alt="" data-size="line"> **Azure:** Azure endpoint, Key, Deployment ID | [Learn more](https://learn.microsoft.com/en-us/azure/machine-learning/how-to-configure-private-link?view=azureml-api-2\&tabs=cli)

<img src="/files/DCz39ycVVRJL3VHAt9tf" alt="" data-size="line"> **OpenAI:** Key, OpenAI endpoint | [Learn more](https://platform.openai.com/docs/overview)

<img src="/files/DCz39ycVVRJL3VHAt9tf" alt="" data-size="line"> **OpenAI-Compatible:** Llama endpoint, OpenAICompatible Model name

<img src="/files/xX00gXsOROwqy4N2ZJz4" alt="" data-size="line"> **Google Vertex AI:** Region, Project ID, Service Account | [Learn more](https://cloud.google.com/vertex-ai/docs)

### Viewing and setting up the available models

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

Admins manage the available chat models for their accounts and set up private endpoints for chat models:

1. Sign in to the Tabnine console as an admin.
2. Go to the **Models** page under **Settings:**

<figure><img src="/files/Mp6RZD0N3nMVG9D1pUNh" alt=""><figcaption></figcaption></figure>

3. Toggle a model on and enter the relevant provider settings for your private endpoint.

<figure><img src="/files/hvWv2mfx0wtZXKBUQQw2" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/g8C2RqlL1HzTkdoj5m9R" alt=""><figcaption></figcaption></figure>

### Setting the default chat model

Admins can set a model as the account's default chat model. The account default model is the default chat model for the account users. However, users can still switch to any other available model.

Change the account default model by expanding a specific model and toggling **Set as default.**

<figure><img src="/files/pMevV2BxP253DdC92Du8" alt=""><figcaption></figcaption></figure>

Change the account default model by expanding a specific model and toggling **Set as default.**


---

# 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 dynamically by asking a question.

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

```
GET https://docs.tabnine.com/main/administering-tabnine/managing-your-team/settings/models-settings.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.