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

# Supported Providers

> Connect OpenAI, Anthropic, Google, xAI, Groq, and Together AI via Bring Your Own Key.

MetrixLLM routes your requests to six major AI providers. You bring your own API keys — MetrixLLM never marks up model costs.

## Adding a provider key

<Steps>
  <Step title="Open Workspace Settings">
    In your workspace, go to **Settings → Providers**.
  </Step>

  <Step title="Add a provider">
    Click **Add Provider**, select the provider, and paste your API key from that provider's dashboard.
  </Step>

  <Step title="Save">
    Click **Save**. Your key is encrypted at rest immediately.
  </Step>
</Steps>

## Supported providers

| Provider        | Internal name | Example models                                                |
| :-------------- | :------------ | :------------------------------------------------------------ |
| **OpenAI**      | `openai`      | `gpt-4.1`, `gpt-4.1-mini`, `gpt-4o`, `gpt-4o-mini`, `o3-mini` |
| **Anthropic**   | `anthropic`   | `claude-sonnet-4-20250514`, `claude-3-5-haiku-20241022`       |
| **Google**      | `google`      | `gemini-2.0-flash`                                            |
| **xAI**         | `xai`         | `grok-3-mini-beta`                                            |
| **Groq**        | `groq`        | `llama-3.3-70b-versatile`                                     |
| **Together AI** | `together`    | `meta-llama/Llama-3.3-70B`, `Qwen/QwQ-32B`                    |

<Note>
  The **Internal name** is how MetrixLLM identifies the provider in routing rules, request logs, and response headers.
</Note>

## Custom providers

You can route requests to any **OpenAI-compatible endpoint** by adding a Custom Provider in the dashboard. This is useful for:

* Self-hosted models (e.g. vLLM, Ollama, LM Studio)
* Fine-tuned model endpoints
* Other providers with OpenAI-compatible APIs

Navigate to **Settings → Providers → Add Custom Provider** and enter the base URL of the endpoint.

## Next: connect your SDK

<Card title="Drop-in Endpoints →" icon="plug" href="/docs/drop-in-endpoints">
  See exactly what to change in your SDK to start routing through MetrixLLM.
</Card>