> ## Documentation Index
> Fetch the complete documentation index at: https://arivu.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Google Gemini

> Connect to Google Gemini for multimodal model support.

<Frame>
  <img src="https://mintcdn.com/arivu/piekGGEpY74vFGfF/images/gemini.png?fit=max&auto=format&n=piekGGEpY74vFGfF&q=85&s=84236cd1ca13fe190c0a2aceb3f4180a" alt="Google Gemini" width="1919" height="911" data-path="images/gemini.png" />
</Frame>

## Overview

Gemini is Google's most capable AI model series, seamlessly designed to be multimodal—understanding, operating across, and combining different types of information including text, code, audio, image, and video.

<CardGroup cols={2}>
  <Card title="Native Multimodality" icon="icons">
    Process images, video, and text inherently without patched tools.
  </Card>

  <Card title="Massive Context" icon="arrows-left-right">
    Gemini 1.5 Pro scales up to 1M or 2M context windows.
  </Card>
</CardGroup>

## Configuration

<Steps>
  <Step title="Get your Developer Key">
    Retrieve your key from [Google AI Studio](https://aistudio.google.com/).
  </Step>

  <Step title="Environment Variable">
    Export your key locally or configure your host:

    <CodeGroup>
      ```bash .env theme={null}
      GEMINI_API_KEY="AIzaSy..."
      DEFAULT_MODEL="gemini-1.5-pro"
      ```
    </CodeGroup>
  </Step>
</Steps>

<Note>For enterprise applications, Arivu can also interact with Vertex AI configurations using standard `GOOGLE_APPLICATION_CREDENTIALS`.</Note>