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

# Providers quick start

> Connect an inference provider and make one of its models available in Studio.

Use a provider to make an OpenAI-compatible inference endpoint available for routing, relabeling, and evaluations.

<Note>
  Before you begin, you need the provider's API base URL, an API key, and at least one model ID exposed by that endpoint. You can skip provider registration when you only use the built-in `wandb-inference` provider.
</Note>

<Steps>
  <Step title="Open provider settings">
    In Studio, open the entity menu and select **Providers**. Provider configuration applies to the selected W\&B entity.
  </Step>

  <Step title="Register the provider">
    In **Add provider**, enter a lowercase provider name, the OpenAI-compatible API base URL, and the API key. Then select **Add provider**.

    Studio encrypts the API key before storage and publishes hosted provider changes asynchronously.
  </Step>

  <Step title="Wait for the provider to become available">
    Expand the provider and confirm that its deployment status is **Applied** at the current revision.
  </Step>

  <Step title="Enable a model">
    In the provider's model list, enable a known model or add the exact model ID exposed by the endpoint. Add input and output pricing if you want Studio to estimate costs.

    The model now appears in Studio model selectors as `{provider}/{model}`.
  </Step>
</Steps>

<Card title="Provider behavior and API options" href="/model-distillation/studio/providers" arrow="true">
  Learn how to rotate credentials, manage models, and delete a provider safely.
</Card>