> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://www.glideapps.com/docs/automation/integrations/google-gemini/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://www.glideapps.com/_mcp/server.

# Google Gemini

> Connect Google Gemini to Glide.

The Google Gemini integration integrate's Google's Gemini AI model directly into Glide apps. Gemini is a generative AI tool built on large language models. [You can read more about Gemini and the available models here.](https://ai.google.dev/gemini-api/docs/models/gemini)

> **Don't see the Gemini integration?**
>
> You may need to upgrade your plan. [Browse Glide's plans and find the right fit for you.](https://www.glideapps.com/pricing)

## Adding the Integration

To add the integration, you'll first need a Google account with access to the Gemini web app. If you have a Workspace account, you may not have access. [You can review the different types of access from Google here.](https://support.google.com/gemini/answer/13278668?hl=en)

Once you have created an API key in [Google AI Studio](https://aistudio.google.com/), you can add the integration to your Glide app.

#### Google Gemini - Arcade 1

In Glide, click the Settings icon in the upper-right corner.

Navigate to the **Integrations** tab and then select **Google Gemini**.

Click the **Add to app** button.

Paste the API key you want to use from Google AI Studio.

Click away to exit the configuration.

## Generate Text

The **Generate Text** feature will generate a text output in response to a message input. You can also enable [Gemini's code execution ability](https://ai.google.dev/gemini-api/docs/code-execution?lang=python) in the advanced configuration settings.

The feature can be configured as a column in the [Data Editor](/docs/getting-started/introduction-to-the-data-editor) or as an action in the [Layout](/docs/getting-started/intro-to-layout#layout-editor) or [Workflow Editor](/docs/getting-started/introduction-to-workflows#the-workflow-editor).

#### Data Editor

#### Google Gemini - Arcade 2

In the Data Editor, open the table you want to edit.

Add a new column by clicking the (**+**) plus symbol to the right of the table.

Give the column a name.

For type, search for **Generate Text** or navigate to **Integrations → Google Gemini → Generate Text.**

* Note that there are other integrations that have a Generate Text feature. Make sure to pick the correct one.

Select a source for the input **Message** or enter a custom value.

Choose a Gemini model.

Select **Save**.

There are optional advanced settings you can also configure. **Max Tokens** will limit the maximum number of tokens generated. Adjusting the **Temperature** will change the randomness or variability of each response. Enabling **Code Execution** will leverage [Gemini's ability to execute code.](https://ai.google.dev/gemini-api/docs/code-execution?lang=python)

#### Layout Editor

#### Google Gemini - Arcade 3

Create a column in your data to house the generated result.

Click on the plus (**+**) sign in the **Component** panel to add a new component that supports actions, or select an existing component to add an action.

In the **General** tab on the right side of the Layout Editor, navigate to the **Actions** section and search for **Generate Text** or navigate to **Integrations → Google Gemini → Generate Text.**

* Note that there are other integrations that have a Generate Text feature. Make sure to pick the correct one.

Choose an icon.

Name the action.

Select a source for the input **Message** or enter a custom value.

Choose a Gemini model.

Choose where to store the generated results.

Click away to exit the configuration.

There are optional advanced settings you can also configure. **Max Tokens** will limit the maximum number of tokens generated. Adjusting the **Temperature** will change the randomness or variability of each response. Enabling **Code Execution** will leverage [Gemini's ability to execute code.](https://ai.google.dev/gemini-api/docs/code-execution?lang=python)

#### Workflow Editor

#### Google Gemini - Arcade 4

Create a column in your data to house the generated result.

Select the (**+**) plus symbol or the **+ New Workflow** button and choose a trigger.

Search for **Generate Text** or navigate to **Integrations → Google Gemini → Generate Text.**

* Note that there are other integrations that have a Generate Text feature. Make sure to pick the correct one.

Select a source for the input **Message** or enter a custom value.

Choose a Gemini model.

Choose where to store the generated results.

Click away to exit the configuration.

There are optional advanced settings you can also configure. **Max Tokens** will limit the maximum number of tokens generated. Adjusting the **Temperature** will change the randomness or variability of each response. Enabling **Code Execution** will leverage [Gemini's ability to execute code.](https://ai.google.dev/gemini-api/docs/code-execution?lang=python)

To learn more generally about Integrations in Glide, including how they affect your app's usage, check out our [Introduction to Integrations](/docs/automation/integrations).

## Frequently Asked Questions

#### Don't see the Gemini integration?

You may need to upgrade your plan. [Browse Glide's plans and find the right fit for you](https://www.glideapps.com/pricing).

#### What does Google charge to use Gemini?

[Google has tiered pricing for use of Gemini.](https://ai.google.dev/gemini-api/docs/pricing)

#### How many updates does the Gemini integration use?

Each run of the integration will use 1 update.

> Connect Google Gemini to Glide.