# Gemini + Google Search grounding

The Gemini API with Google Search grounding turned on. Citations come from the grounding metadata.

## Why measure it

Shows how Google's model answers with Google's index behind it, through an API you can run on a schedule.

## Ask it

```bash
llmentions ask "best crm for startups" --brand Acme --engines gemini -n 5
```

Over MCP, pass `engines: ["gemini"]` to `ai_answers` or `visibility_run`. Over REST, `"engines": ["gemini"]` on `POST /v1/ai/answers`.

Every answer is labelled `source: "api"`. Set `web_search: false` for a parametric probe (`source: "parametric"`): what the model knows without searching, at $0.005 per answer.

## Price

$0.05 per answer. Failed answers are refunded, and test keys are free. See [Pricing](/pricing/).

Read how we sample, label and compare engines in [Methodology](/docs/methodology/).

---
https://llmentions.com/engines/gemini/
