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

# Virtual Keys

> Virtual Keys have been migrated to Model Catalog - learn about the new system

<Warning>
  **Virtual Keys have been migrated to Model Catalog**

  The Virtual Keys feature has been upgraded to the **Model Catalog** system, which provides better governance, centralized management, and model-level controls. The core concept remains the same - one Portkey API key gives you access to multiple providers and models.

  [Learn more about Model Catalog →](/product/model-catalog)
</Warning>

## What Changed?

The Virtual Keys feature has evolved into the **Model Catalog** system. Here's what you need to know:

### Core Concept (Still the Same)

* ✅ **One Portkey API key** → Access **multiple providers** → Use **hundreds of models**
* ✅ Provider credentials stored securely, never exposed in code
* ✅ Centralized management and governance

### What's New in Model Catalog

* **Organization-level management**: Share credentials across workspaces
* **Better governance**: Fine-grained budgets, rate limits, and model allow-lists
* **Simpler usage**: Just use `model="@provider-slug/model-name"` format
* **Enhanced security**: Improved credential management and access controls

## Migration Guide

If you're currently using Virtual Keys, see our step-by-step migration guide:

<Card title="Migration Guide" icon="arrow-right" href="/support/upgrade-to-model-catalog">
  Step-by-step guide to migrate from Virtual Keys to Model Catalog
</Card>

## Quick Start with Model Catalog

1. **Add a Provider**: Go to [Model Catalog](https://app.portkey.ai/model-catalog) → Add Provider
2. **Use in Code**: Use the `@provider-slug/model-name` format in your requests
3. **Manage Access**: Set budgets, rate limits, and model access controls

```python theme={"system"}
from portkey_ai import Portkey

portkey = Portkey(api_key="PORTKEY_API_KEY")

# Use Model Catalog providers
response = portkey.chat.completions.create(
    model="@openai-prod/gpt-4o",  # Provider slug + model name
    messages=[{"role": "user", "content": "Hello!"}]
)
```

## Related Resources

<CardGroup cols={2}>
  <Card title="Model Catalog" icon="sparkles" href="/product/model-catalog">
    Complete guide to Model Catalog features
  </Card>

  <Card title="Integrations" icon="key" href="/product/model-catalog/integrations">
    Managing credentials across workspaces
  </Card>

  <Card title="Migration Guide" icon="arrow-right" href="/support/upgrade-to-model-catalog">
    Step-by-step migration from Virtual Keys
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/inference-api/config-object">
    Config object reference for Model Catalog
  </Card>
</CardGroup>