# Workspace Tokens

{% hint style="danger" %}
Do not share Workspace tokens.
{% endhint %}

To access the AI Hub with PySDK, you'll need to create a Workspace token with the AI Hub. You can create Workspace tokens only if your account is part of a Workspace.

If you plan to use PySDK fully offline, or you plan to use models available in public Model Zoos, you don't need to create Workspace tokens.

Workspace tokens allow you to:

* Run cloud inference on models in public Model Zoos.
* Access to models in the Workspace Model Zoos for local and AI server inference.
* Run cloud inference on models in Workspace Model Zoos.

## Creating and managing tokens

<figure><img src="/files/c2PyU6p5eDWwdo8is7mP" alt="AI Hub Tokens interface."><figcaption><p>AI Hub Tokens interface.</p></figcaption></figure>

To create or manage tokens, navigate to [Workspace tokens](https://hub.degirum.com/workspace-tokens?utm_source=docs.degirum.com\&utm_medium=site\&utm_campaign=ai-hub-workspaces-workspace-tokens) in the AI Hub. You'll be able to:

* Generate new tokens: Click the **Generate Workspace Token** button, then set a description and expiration date for the token.
* View partial token keys: The Tokens interface will display part of the token key for existing tokens. You will not be able to view the entire token key through the interface.
* Copy token keys: Click the copy action button to the right of the token key to copy the token key.
* Delete tokens: Click the delete action button to the right of the token key to delete the key. A confirmation popup will appear to confirm if you want to delete the key.

If you have [PySDK ](https://docs.degirum.com/pysdk)installed, you may also use a PySDK CLI helper to manage tokens easily over a terminal. [Click here](https://docs.degirum.com/pysdk/user-guide-pysdk/command-line-interface#manage-ai-hub-tokens) for more information about the PySDK CLI helper.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.degirum.com/ai-hub/workspaces/workspace-tokens.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
