> ## Documentation Index
> Fetch the complete documentation index at: https://www.notifuse.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Google Gemini

> Configure Google Gemini to power blog content creation and email generation in Notifuse.

![Google Gemini](https://www.notifuse.com/docs/assets/integrations/gemini.svg)

The Google Gemini integration enables AI-powered features across Notifuse using Google's Gemini models. This integration powers the [AI assistant](https://www.notifuse.com/docs/features/ai-assistant.md) for blog content creation, email design and web analytics.

## Configuration

Navigate to **Settings** → **Integrations**, click **Add integration**, then choose **Google Gemini** under **AI assistant**.

### Form Fields

| Field       | Description                                        | Example                  |
| ----------- | -------------------------------------------------- | ------------------------ |
| **API Key** | Your Gemini API key (Gemini Developer API)         | `AIza...`                |
| **Model**   | Pick a suggested model or type any Gemini model ID | `gemini-3.1-pro-preview` |

The **Model** field is a free-text input with suggestions, so you can enter any current Gemini model ID without waiting for a Notifuse update.

### Recommended Model

| Model              | Description                                                           | $ Pricing (per MTok)  |
| ------------------ | --------------------------------------------------------------------- | --------------------- |
| **Gemini 3.1 Pro** | Most capable model — recommended for the AI agent's structured output | $2 input / $12 output |

> [!WARNING]
>
> The AI agent generates structured MJML email templates and full blog posts with HTML formatting. Only capable models such as **Gemini Pro** are smart enough to produce correct output. Lighter **Flash** / **Flash-Lite** models often generate broken templates or malformed content, so they are not recommended for the agent.

## Features Enabled

Once configured, the Google Gemini integration enables the following AI-powered features:

### Blog AI Agent

The AI agent can assist with blog content creation:

| Feature              | Description                                                                 |
| -------------------- | --------------------------------------------------------------------------- |
| **Write blog posts** | Generate complete blog articles based on topics or brief descriptions       |
| **SEO optimization** | Automatically generate SEO-friendly meta titles, descriptions, and keywords |
| **Content editing**  | Improve, expand, or summarize existing content                              |

### Email Editor AI

Generate emails automatically using AI:

| Feature                | Description                                             |
| ---------------------- | ------------------------------------------------------- |
| **Email generation**   | Create email content from prompts or descriptions       |
| **Subject lines**      | Generate compelling subject lines for better open rates |
| **Content variations** | Create multiple versions for A/B testing                |

### Web Analytics Assistant

Answer questions about your website traffic with the [Web Analytics assistant](https://www.notifuse.com/docs/web-analytics/ai-assistant.md):

| Feature                 | Description                                                     |
| ----------------------- | --------------------------------------------------------------- |
| **Ask about traffic**   | Query sessions, pages, sources and goals in plain language      |
| **Period summaries**    | A written analysis of what moved, against the comparison period |
| **Drive the dashboard** | Change the period, apply filters, or open an Explore report     |

## Enhanced with Firecrawl

The Google Gemini AI agent can be enhanced by adding the [Firecrawl integration](https://www.notifuse.com/docs/integrations/firecrawl.md). This gives the AI agent web access capabilities:

| Capability               | Description                                           |
| ------------------------ | ----------------------------------------------------- |
| **Web research**         | Search the web for current information and trends     |
| **URL scraping**         | Extract content from specific web pages for reference |
| **Competitive analysis** | Research competitor content and strategies            |
| **Fact verification**    | Verify claims against current web sources             |

When Firecrawl is configured, the following tools become available to the AI agent:

| Tool         | Description                                       |
| ------------ | ------------------------------------------------- |
| `scrape_url` | Scrapes a URL and returns its content as markdown |
| `search_web` | Searches the web and returns relevant URLs        |

## Prerequisites

Before configuring Google Gemini:

1. **Google AI Studio Account**: Create an account at [aistudio.google.com](https://aistudio.google.com)
2. **API Key**: Generate an API key from [Google AI Studio](https://aistudio.google.com/apikey)
3. **Quota / Billing**: Ensure your project has sufficient quota or billing enabled for the chosen model

## Usage Notes

> [!NOTE]
>
> API calls to Gemini count toward your Google AI usage. Monitor your usage in [Google AI Studio](https://aistudio.google.com) to manage costs.

> [!NOTE]
>
> The assistant panel shows a running cost for the Gemini models Notifuse has prices for. A model ID it does not recognise still works, but the conversation cost reads `$0.0000` — check Google AI Studio for what you actually spent.

> [!TIP]
>
> Preview models such as `gemini-3.1-pro-preview` evolve over time. If a model ID is rejected, check the current list in the [Gemini API models documentation](https://ai.google.dev/gemini-api/docs/models) and enter it in the **Model** field.
