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

# Prerequisites

> Set up your environment, API key, and dependencies before using the Serverless Inference service through the API or UI.

This page lists the accounts, credentials, and tools you must set up before you can call the Serverless Inference service from the API or the UI. Complete every item in the following sections so that later requests authenticate successfully and route to a valid project.

<Tip>
  Before you start, review the [usage information and limits](/inference/usage-limits/) to understand costs and restrictions.
</Tip>

## Set up your W\&B account and project

You must have the following items to access Serverless Inference:

1. **A W\&B account.** Sign up at [W\&B](https://app.wandb.ai/login?signup=true).

2. **A W\&B API key.**

   To create an API key, select the **Personal API key** or **Service Account API key** tab for details.

   <Tabs>
     <Tab title="Personal API key">
       To create a personal API key owned by your user ID:

       1. Log in to W\&B, click your user profile icon, then click **User Settings**.
       2. Click **Create new API key**.
       3. Provide a descriptive name for your API key.
       4. Click **Create**.
       5. Copy the displayed API key immediately and store it securely.
     </Tab>

     <Tab title="Service account API key">
       To create an API key owned by a service account:

       1. Navigate to the **Service Accounts** tab in your team or organization settings.
       2. Find the service account in the list.
       3. Click the **action (<Icon icon="ellipsis" iconType="solid" />)** menu, then click **Create API key**.
       4. Provide a name for the API key, then click **Create**.
       5. Copy the displayed API key immediately and store it securely.
       6. Click **Done**.

       You can create multiple API keys for a single service account to support different environments or workflows.
     </Tab>
   </Tabs>

   <Warning>
     The full API key is only shown once at creation time. After you close the dialog, you cannot view the full API key again. Only the key ID (first part of the key) is visible in your settings. If you lose the full API key, you must create a new API key.
   </Warning>

   For secure storage options, see [Store API keys securely](/platform/app/settings-page/user-settings/#store-and-handle-api-keys-securely).

3. **A W\&B project.** Create a project in your W\&B account to track usage.

After you complete these three items, you have a W\&B identity that can authenticate to the Inference API and a project that records your usage.

## Set up your environment for Python

If you plan to call the Inference API from Python, set up the following in addition to the general requirements:

1. Complete the general requirements in the preceding section.

2. Install the required libraries:

   ```bash theme={null}
   pip install openai weave
   ```

<Note>
  **Note**

  The `weave` library is optional but recommended. It lets you trace your LLM applications. Learn more in the [Weave Quickstart](/models/quickstart/).
</Note>

## Next steps

With your account, API key, project, and optional Python environment in place, you're ready to start sending requests. Continue with one of the following resources:

* Check the [API reference](/inference/api-reference/) to learn about available endpoints.
* Try the [usage examples](/inference/examples/) to see the service in action.
* Use the [UI guide](/inference/ui-guide/) to access models through the web interface.