> ## Documentation Index
> Fetch the complete documentation index at: https://vlyai-1c28d863.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Google AI (Gemini)

> Google's Gemini models. Strong on multimodal (vision, audio), long context, and code.

[Google AI's Gemini](https://ai.google.dev) models. Multimodal-first design — image, audio, video input alongside text.

<Note>
  Full walkthrough being written.
</Note>

## When to pick

* You need vision capabilities (image analysis, OCR).
* Audio input is a primary feature.
* You want very long context (1M+ tokens).

## Setup

`GOOGLE_AI_API_KEY` in vly secrets. Use `@google/generative-ai` SDK from a Convex action.

## Models

| Model | Use for |
| - | - |
| gemini-2.5-pro | Maximum capability |
| gemini-2.5-flash | Fast, cheap |

## Related

<CardGroup cols={3}>
  <Card title="OpenAI" icon="sparkles" href="/integrations/openai">
    Comparison.
  </Card>

  <Card title="Anthropic" icon="brain" href="/integrations/anthropic">
    Comparison.
  </Card>

  <Card title="Gemini CLI agent" icon="sparkles" href="/features/agents/gemini-cli">
    The vly agent powered by Gemini.
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.