Documentation / Integrations

Google Gemini

Connects Gemini models for answer-engine sampling. Gemini answers are captured separately from Google AI Overview and Google AI Mode, which come from search results.

Set up

1. Open Integrations in the navigation for your role.
2. Choose Add integration, then select Google Gemini.
3. Enter API key; Model name; Requests per minute (default 300).
4. Choose Connect. Helm tests the connection before it saves the integration.

If the test fails, you can choose Save without verifying. The integration is then saved with an error status until you fix it.

What the screen shows

The form matches the other LLM providers: an API key, an exact model identifier and a request limit that defaults to 300 per minute.

Notes

• Google AI Overview and Google AI Mode are captured from Google search results, not through this connection.
• Gemini answers feed the per-LLM views in AI Visibility.

Last updated 26 October 2026