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

# Google GenAI Plugin

> Google Gemini models integration for elizaOS

## Features

* **Gemini models** - Access to Gemini Pro and Gemini Pro Vision
* **Multimodal support** - Process text and images
* **Embedding models** - Native embedding support
* **Safety settings** - Configurable content filtering

## Installation

```bash theme={null}
elizaos plugins add @elizaos/plugin-google-genai
```

## Configuration

### Environment Variables

```bash theme={null}
# Required
GOOGLE_GENERATIVE_AI_API_KEY=...

# Optional model configuration
# You can use any available Google Gemini model
GOOGLE_SMALL_MODEL=gemini-2.0-flash-001           # Default: gemini-2.0-flash-001
GOOGLE_LARGE_MODEL=gemini-2.5-pro-preview-03-25   # Default: gemini-2.5-pro-preview-03-25
GOOGLE_IMAGE_MODEL=gemini-1.5-flash               # For vision tasks
GOOGLE_EMBEDDING_MODEL=text-embedding-004         # Default: text-embedding-004

# Examples of other available models:
# GOOGLE_SMALL_MODEL=gemini-1.5-flash
# GOOGLE_LARGE_MODEL=gemini-1.5-pro
# GOOGLE_LARGE_MODEL=gemini-pro
# GOOGLE_EMBEDDING_MODEL=embedding-001
```

### Character Configuration

```json theme={null}
{
  "name": "MyAgent",
  "plugins": ["@elizaos/plugin-google-genai"]
}
```

## Supported Operations

| Operation          | Models                        | Notes              |
| ------------------ | ----------------------------- | ------------------ |
| TEXT\_GENERATION   | gemini-pro, gemini-pro-vision | Multimodal capable |
| EMBEDDING          | embedding-001                 | 768-dimensional    |
| OBJECT\_GENERATION | All Gemini models             | Structured output  |

## Model Configuration

The plugin uses three model categories:

* **SMALL\_MODEL**: Fast, efficient for simple tasks
* **LARGE\_MODEL**: Best quality, complex reasoning
* **IMAGE\_MODEL**: Multimodal capabilities (text + vision)
* **EMBEDDING\_MODEL**: Vector embeddings

You can configure any available Gemini model:

* Gemini 2.0 Flash (latest)
* Gemini 2.5 Pro Preview
* Gemini 1.5 Pro/Flash
* Gemini Pro (legacy)
* Any new models Google releases

## Safety Configuration

Control content filtering:

```typescript theme={null}
// In character settings
{
  "settings": {
    "google_safety": {
      "harassment": "BLOCK_NONE",
      "hate_speech": "BLOCK_MEDIUM_AND_ABOVE",
      "sexually_explicit": "BLOCK_MEDIUM_AND_ABOVE",
      "dangerous_content": "BLOCK_MEDIUM_AND_ABOVE"
    }
  }
}
```

## Usage Tips

1. **Multimodal** - Leverage image understanding capabilities
2. **Long Context** - Gemini 1.5 Pro supports up to 1M tokens
3. **Rate Limits** - Free tier has generous limits

## Cost Structure

* Free tier: 60 queries per minute
* Paid tier: Higher limits and priority access
* Embedding calls are separate from generation

## External Resources

* [Plugin Source](https://github.com/elizaos/eliza/tree/main/packages/plugin-google-genai)
* [Google AI Studio](https://makersuite.google.com)
* [API Documentation](https://ai.google.dev/docs)