> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://help.sigmacomputing.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://help.sigmacomputing.com/_mcp/server.

# Configure AI column admin settings (Beta)

> Set monthly token limits in Sigma to control AI column usage costs and manage organization-wide AI spending for AI columns.

> **Note**
>
> This documentation describes one or more public beta features that are in development. Beta features are subject to quick, iterative changes; therefore the current user experience in the Sigma service can differ from the information provided in this page.
>
> This page should not be considered official published documentation until Sigma removes this notice and the beta flag on the corresponding feature(s) in the Sigma service. For the full beta feature disclaimer, see [Beta features](/docs/sigma-product-releases#beta-features).

Admins can configure [AI column](/docs/create-ai-columns) settings, such as monthly token usage limits and the models available to their organization.

This document covers how to [configure token usage limits for individual connections](#configure-token-usage-limits) and how to [configure the models available to your organization's users](#configure-ai-column-model-options) when creating AI columns. For more information on AI columns, see [Create AI columns](/docs/create-ai-columns).

> **Note**
>
> The use of AI features is subject to the following [disclaimer](/docs/notice-for-enabling-ai-enabled-features-in-sigma).

## User requirements

You must be assigned the Admin [account type](/docs/create-and-manage-account-types).

## Configure token usage limits

You can set monthly token usage limits for individual connections to limit AI column usage costs. Usage from all users in your organization counts toward these limits. If no token limit is set, the default limit is 10 million tokens per connection per month.

> **Warning**
>
> Token usage limits are enforced based on usage estimates and are not exact. Actual consumption may exceed the limit. Usage estimates do not account for varying costs by model. Check your data platform for the most accurate information on usage and cost.

To configure token usage limits for AI columns:

1. Go to **Administration** > **AI settings**.

2. Select the **AI columns** tab.

3. In the **Connection AI token limits** section, select **Edit**.

   > **Info**
   >
   > Only connections that you can create AI columns on are displayed. See [Create AI columns](/docs/create-ai-columns#system-and-user-requirements) for more information on connection requirements.

4. Edit your desired **Token limit per month**, then press **Enter** on your keyboard.

5. Select **Save**.

## Configure AI column model options

You select what models are available to your organization's users when creating AI columns. The models you select become available to users when they create AI columns.

By default, the following models are available for users to select from when they create an AI column:

* Claude Haiku 4.5
* Claude Sonnet 4.5
* OpenAI GPT-5.2

To edit the AI column model options available to your organization's users:

1. Go to **Administration** > **AI settings**.
2. Select the **AI columns** tab.
3. In the **Connection AI token limits** section, select **Edit**.
4. Open the **Models** dropdown, and search for and select your desired models. See [Supported models](#supported-models) for a list of supported models.
5. Select **Save**.

### Supported models

The following models are supported for creating AI columns:

#### For AI columns created on Snowflake connections

* Claude Haiku 4.5
* Claude Sonnet 4.5
* GPT-5.2
* Claude Sonnet 5
* Claude Sonnet 5.5
* GPT-5.4
* GPT-5.4 mini

#### For AI columns created on Databricks connections

* Claude Haiku 4.5
* Claude Sonnet 4.5
* GPT-5.2
* Claude Sonnet 4.6
* GPT-5.4 mini