# Google Gemini

Connect your Google AI account to use Gemini models for the assistant, prompts, and AI rules.

{% hint style="info" %}
You need a **Google AI Studio** API key, not a Google Cloud Vertex AI key. Google AI Studio is the consumer/developer API for Gemini.
{% endhint %}

## Setup

{% stepper %}
{% step %}
**Get your Google AI API key**

Go to [Google AI Studio](https://aistudio.google.com/) and sign in with your Google account.

Click **Get API key** and create a new key. Copy it somewhere safe.
{% endstep %}

{% step %}
**Add the integration in Missive**

In Missive, go to **Settings** > **Integrations** > click **Add integration** > search for **Gemini** and click **Add to Missive**.

Enter your **API key** and click **Add**.
{% endstep %}

{% step %}
**Share with your team (optional)**

To let your team use AI features, share the integration:

Go to **Settings** > **Integrations** > **Gemini** and click **Share integration** at the top.

{% hint style="warning" %}
Shared integrations mean everyone uses the same API key. All usage bills to your Google AI account.
{% endhint %}
{% endstep %}

{% step %}
**Restrict available models (optional)**

By default, all models are available to your team. To limit which models they can choose in the Assistant:

Go to **Settings** > **Integrations** > **Gemini** and scroll to **Models**.

Select the models you want to make available. Choosing **All models** automatically includes any future models. Deselecting specific models prevents your team from using them.
{% endstep %}
{% endstepper %}

## Available models

### Assistant models

| Model                 | Best for                                            | Speed    | Quality |
| --------------------- | --------------------------------------------------- | -------- | ------- |
| Gemini 2.5 Pro        | Complex reasoning, long-context analysis            | Moderate | Highest |
| Gemini 2.5 Flash      | Most daily tasks, good balance of speed and quality | Fast     | Good    |
| Gemini 2.5 Flash Lite | Quick tasks, lowest cost                            | Fastest  | Basic   |

For drafting customer-facing email replies, Gemini 2.5 Pro gives the best results. Gemini 2.5 Flash is great for most daily tasks, and its large context window handles very long threads well.

### Rule models

| Model            | Description                                               |
| ---------------- | --------------------------------------------------------- |
| Gemini 2.5 Flash | Fast, cost-effective for classification and routing tasks |

## Data privacy

Google's data handling depends on whether you are on the free or paid tier:

* **Free tier (unpaid quota):** Google uses your prompts and responses to improve its products and train models. Human reviewers may read your data. Do not submit sensitive or confidential information on the free tier.
* **Paid tier (billing account active):** Google does **not** use your prompts or responses to improve products. Data is logged for a limited period only to detect policy violations.

To use the paid tier, make sure your Google AI Studio account is linked to a Google Cloud project with an active billing account.

For full details, see the [Gemini API terms of service](https://ai.google.dev/gemini-api/terms).

## Cost and usage

Google AI offers a free tier with usage limits, and a paid tier for higher volume. A token is roughly 3/4 of a word. Check [Google AI pricing](https://ai.google.dev/pricing) for current rates.

Reading a 10-email thread and drafting a reply typically uses 2,000 to 4,000 tokens. At that rate, even heavy daily use of the assistant stays well under a dollar per day with Gemini 2.5 Flash.

### Managing costs

* **Use the best model for manual tasks.** When you trigger AI yourself (drafting a reply, asking the assistant a question), the cost per interaction is negligible. Use Gemini 2.5 Pro for the best results.
* **Use Flash for AI rules.** Rules run automatically on every matching message, so costs add up. Gemini 2.5 Flash is fast and cheap for classification and routing.
* **Monitor usage** in the [Google AI Studio console](https://aistudio.google.com/).
* The free tier may be sufficient for small teams with light usage.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://missiveapp.com/docs/ai/setup/gemini.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.