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

# AI & LLM Configuration

> How to connect your own Large Language Model (LLM) API keys.

Prezence AI leverages the power of Large Language Models (LLMs) for features like AI-assisted messaging and content analysis. While we provide a default AI model, you have the option to connect your own API keys from providers like OpenAI, Anthropic, or Google.

## Why Bring Your Own Key?

* **Control Your Costs**: Pay your provider directly for your usage.
* **Choose Your Preferred Model**: Use the specific model that you find works best for your needs (e.g., GPT-4, Claude 3).
* **Higher Rate Limits**: Benefit from any higher rate limits associated with your personal or business account.

## How to Add Your API Key

1. **Navigate to Settings**: Go to **Settings** > **LLM Configuration**.
2. **Select Your Provider**: Choose the LLM provider you want to use from the dropdown menu.
3. **Enter Your API Key**: Paste your API key into the secure input field.
4. **Save and Test**: Click **"Save & Test Connection"**. Prezence AI will make a small test call to ensure the key is valid and working.

<Warning>
  Your API keys are stored securely and encrypted. Never share your API keys publicly.
</Warning>

## Video Tutorial: Setting Up LLM Configuration

<iframe className="w-full aspect-video rounded-xl" src="https://www.loom.com/embed/eb57ee85b1b9418a98fd8dbb1c132da5" title="Setting Up LLM Configuration Video Tutorial" frameBorder="0" allowFullScreen />

### Cost-Effective LLM Options

The video demonstrates how to set up your LLM configuration with a focus on cost-effectiveness:

1. **Available LLM Providers**:
   * OpenAI
   * Anthropic
   * Open Router (recommended for cost efficiency)

2. **Why Choose Open Router**:
   * Access to multiple models (including Anthropic, Claude, etc.) through a single API
   * Pay-as-you-go pricing with minimal markup (approximately 6%)
   * Access to more affordable models like Maverick/Llama

3. **Cost Examples**:
   * Using cost-effective models can keep expenses very low (e.g., less than \$1/week with regular usage)
   * Pricing comparison: Maverick costs approximately 15¢ per million input tokens and 60¢ per million output tokens
   * More expensive models like Claude might cost roughly 10x more

4. **Getting Started**:
   * Create an account with your preferred provider
   * Generate an API key
   * Add the key to your Prezence AI settings

This configuration allows Prezence AI to use your preferred LLM for lead scoring, message generation, and other AI-powered features.