---
title: Google Gemini connector and action
description: The Google Gemini connector uses axios to send a POST request to Google Gemini. You can create connectors in Stack Management > Connectors.  For example:...
url: https://docs-v3-preview.elastic.dev/elastic/kibana/pull/280898/reference/connectors-kibana/gemini-action-type
products:
  - Kibana
applies_to:
  - Elastic Cloud Serverless: Deprecated
  - Elastic Stack: Planned for deprecation
---

# Google Gemini connector and action
The Google Gemini connector uses [axios](https://github.com/axios/axios) to send a POST request to Google Gemini.
<important applies-to="Elastic Cloud Serverless: Deprecated, Elastic Stack: Planned for deprecation">
  This connector is deprecated and is being progressively removed from the create connector UI. Existing connectors and their rule actions continue to work.For new AI integrations, use Elasticsearch inference endpoints. Migrate existing LLM connectors and related rule actions before the future removal.
</important>


## Create connectors in Kibana

You can create connectors in **Stack Management > Connectors**.  For example:
![Google Gemini connector](https://docs-v3-preview.elastic.dev/elastic/kibana/pull/280898/reference/images/gemini-connector.png)


### Connector configuration

Google Gemini connectors have the following configuration properties:
<definitions>
  <definition term="Name">
    The name of the connector.
  </definition>
  <definition term="API URL">
    The Google Gemini request URL.
  </definition>
  <definition term="Project ID">
    The project which has Vertex AI endpoint enabled.
  </definition>
  <definition term="Region">
    The GCP region where the Vertex AI endpoint enabled.
  </definition>
  <definition term="Default model">
    The GAI model for Google Gemini to use. Current support is for the Google Gemini models.
    - <applies-to>Elastic Cloud Serverless: Generally available</applies-to> Defaults to `gemini-2.5-pro`.
    - <applies-to>Elastic Stack: Generally available since 9.1</applies-to> Defaults to `gemini-2.5-pro`.
    - <applies-to>Elastic Stack: Generally available since 9.0</applies-to> Defaults to `gemini-1.5-pro-002`.
      The model can be set on a per request basis by including a "model" parameter alongside the request body.
  </definition>
  <definition term="Credentials JSON">
    The GCP service account JSON file for authentication.
  </definition>
</definitions>


## Test connectors

You can test connectors as you're creating or editing the connector in Kibana. For example:
![Google Gemini params test](https://docs-v3-preview.elastic.dev/elastic/kibana/pull/280898/reference/images/gemini-params.png)

The Google Gemini actions have the following configuration properties.
<definitions>
  <definition term="Body">
    A stringified JSON payload sent to the Google Gemini invoke model API. For example:
    ```text
    {
      body: JSON.stringify({
            contents: [{
                role: user,
                parts: [{ text: 'Hello world!' }]
            }],
            generation_config: {
                temperature: 0,
                maxOutputTokens: 8192
            }
      })
    }
    ```
  </definition>
  <definition term="Model">
    An optional string that overwrites the connector's default model.
  </definition>
</definitions>


## Connector networking configuration

Use the [Action configuration settings](/elastic/kibana/pull/280898/reference/configuration-reference/alerting-settings#action-settings) to customize connector networking configurations, such as proxies, certificates, or TLS settings. You can set configurations that apply to all your connectors or use `xpack.actions.customHostSettings` to set per-host configurations.