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

# Google Gemini

> Configure Google Gemini models in EnConvo

## Overview

Google's Gemini models offer multimodal capabilities, long context windows, and advanced reasoning features.

## Supported Models

| Model                     | Description        | Context |
| ------------------------- | ------------------ | ------- |
| **Gemini 3 Pro Preview**  | Latest generation  | 1M+     |
| **Gemini 2.5 Pro**        | Advanced reasoning | 1M+     |
| **Gemini 2.5 Flash**      | Fast and capable   | 1M+     |
| **Gemini 2.5 Flash Lite** | Lightweight        | 1M+     |
| **Gemini Pro**            | Balanced           | 32K     |

## Setup

<Steps>
  <Step title="Get API Key">
    1. Go to [Google AI Studio](https://aistudio.google.com)
    2. Sign in with your Google account
    3. Navigate to **API Keys**
    4. Create a new API key
  </Step>

  <Step title="Configure in EnConvo">
    1. Open **Settings** → **AI Provider**
    2. Select **Google Gemini AI**
    3. Go to **Credentials** module
    4. Enter your API key
  </Step>

  <Step title="Select Model">
    Choose your preferred model from the dropdown
  </Step>
</Steps>

## Configuration

| Setting         | Description           | Default              |
| --------------- | --------------------- | -------------------- |
| **Credentials** | API key configuration | Required             |
| **Model Name**  | Model to use          | Gemini 3 Pro Preview |
| **Temperature** | Creativity (0-2)      | None (0)             |

## Validate and Use

<Steps>
  <Step title="Validate credentials">
    Click **Validate** in the Google Gemini credential settings. If validation fails, confirm the API key was created in Google AI Studio and that the Google AI API is available for your account and region.
  </Step>

  <Step title="Refresh models">
    Reopen the model dropdown after validation. Model availability can vary by region, account, and preview access.
  </Step>

  <Step title="Test multimodal behavior">
    Send a short text prompt first. Then test image or long-context workflows only after the basic chat request succeeds.
  </Step>
</Steps>

<Note>
  Google AI API billing is separate from a Google One AI Premium or Gemini subscription. Use the Gemini subscription provider if you want to connect an existing consumer subscription.
</Note>

## Advanced Features

### Google Search Tool

Available for Gemini 2.5 models. Grounds responses with real-time web content.

<Note>
  Works with all languages and provides verifiable source citations.
</Note>

### URL Context Tool

Allows including URLs in requests for additional context. The model will access page content to inform responses.

### Show Thoughts

Enable to see the model's thinking process (available for Gemini 2.5+ and Gemini 3).

### Thinking Configuration

#### Gemini 3 Pro Preview

| Level    | Description    |
| -------- | -------------- |
| **Low**  | Basic thinking |
| **High** | Deep thinking  |

#### Gemini 2.5 Pro

| Level       | Tokens | Description    |
| ----------- | ------ | -------------- |
| **Auto**    | -      | Model decides  |
| **Minimal** | 128    | Quick thinking |
| **Low**     | 1,024  | Basic          |
| **Medium**  | 10,000 | Balanced       |
| **High**    | 30,000 | Deep reasoning |

#### Gemini 2.5 Flash / Flash Lite

| Level        | Tokens | Description   |
| ------------ | ------ | ------------- |
| **Disabled** | 0      | No thinking   |
| **Auto**     | -      | Model decides |
| **Minimal**  | 512    | Quick         |
| **Low**      | 1,024  | Basic         |
| **Medium**   | 10,000 | Balanced      |
| **High**     | 20,000 | Deep          |

## Pricing

Google offers generous free tiers. Check [Google AI Pricing](https://ai.google.dev/pricing).

| Model            | Input      | Output    |
| ---------------- | ---------- | --------- |
| Gemini 1.5 Pro   | \$1.25/1M  | \$5/1M    |
| Gemini 1.5 Flash | \$0.075/1M | \$0.30/1M |

## Best Practices

<AccordionGroup>
  <Accordion title="Leverage long context">
    Gemini's 1M+ token context is perfect for large documents
  </Accordion>

  <Accordion title="Use search grounding">
    Enable Google Search for up-to-date information
  </Accordion>

  <Accordion title="Multimodal tasks">
    Gemini excels at image analysis and visual reasoning
  </Accordion>
</AccordionGroup>

## Troubleshooting

<AccordionGroup>
  <Accordion title="Invalid API key">
    * Verify key in Google AI Studio
    * Check API is enabled
  </Accordion>

  <Accordion title="Region restrictions">
    * Some features may be limited by region
    * Check Google's availability docs
  </Accordion>
</AccordionGroup>