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

# Providers | AI Router

> Connect LLM providers to the AI Router by adding your API keys and endpoints. Supports OpenAI, Anthropic, Google, AWS, and 20+ other providers.

In this guide, we will see how key management works in the **AI Router** and how you can integrate your own API keys from your LLM providers.

## Setting up an API key

To set up your own API Key, head to the **AI Router** and to the **Providers** section.

Choose the provider you wish to set an API key for and press **Connect**, then select **Setup your own API Key**

<Frame caption="Configure your API integration based on the criteria set by the provider.">
  <img src="https://mintcdn.com/orqai/HoEQFybclS_NnUdX/images/router-providers-aws-bedrock.png?fit=max&auto=format&n=HoEQFybclS_NnUdX&q=85&s=35458d72c1002d58a1ad412ae7acb586" alt="Providers 1225" width="1483" height="1047" data-path="images/router-providers-aws-bedrock.png" />
</Frame>

## Supported Providers

<Card title="Browse all supported providers" icon="plug" href="/docs/integrations/providers/overview">
  View the full list of LLM providers you can connect to the **AI Router**, including OpenAI, Anthropic, Google, AWS Bedrock, and more.
</Card>

## Having Multiple API Keys

You can decide to configure multiple API for a single provider, to do so, select **Add a new API key**.

### Benefits of using multiple API Keys

#### Credential Failure

Having a different API key available to use models can be useful in case one becomes invalid or for instance runs out of credit. Having an extra key configured on a fallback model can make sure you respond in all cases.

#### Multiple Environments

In case you have multiple API keys used for different purposes, this lets you organize your models to use the credentials dedicated to the correct environment.

### Using a specific API key in model configuration

Once your API keys are configured within the **Providers** panel, you can select which key to use within [Playground](/docs/playground/overview), [Experiment](/docs/experiments/overview), [Deployment](/docs/deployments/overview), and [Agent](/docs/agents/build). This applies to any model, including fallback models.

<Frame caption="Walkthrough of choosing a default API key and selecting it within a Deployment's variant fallback.">
  <img src="https://mintcdn.com/orqai/AAIZKa2VuHhSrlzH/images/multi-api-key-provider.gif?s=d024b68c3ebc3ed3ea6fc57fd3a62d92" alt="Multi API Key Provider" width="800" height="384" data-path="images/multi-api-key-provider.gif" />
</Frame>

## Why use your own API Keys

For **production** workloads, we highly recommend that you use your own **API keys** and **Endpoints**.

This is because the keys and providers will have different **rate limits**, which you can hit when using our shared key. If you're using your own API keys or endpoint, you have full control over those limits.

Another important reason is **costs and control**. Having set up your own API key, the **billing** will be handled by the provider itself, allowing you to configure your limits.