> For the complete documentation index, see [llms.txt](https://cortex-docs.paloaltonetworks.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://cortex-docs.paloaltonetworks.com/cortex-cloud-runtime-security/get-started/agentic-ai-in-cortex-cloud/ai-hub.md).

# AI Hub

Understand regional model availability, data residency boundaries, and key operational changes when opting into cross-region frontier AI models in Cortex Cloud.

### Overview and regional availability

Model availability, processing routes, and configuration options in Cortex Cloud depend on tenant region and LLM feature status. While EU and US tenants have direct native access to advanced frontier models, Palo Alto Networks provides tenants in all other regions the option to access these same models through the AI Hub. The AI Hub processes requests in either the EU or US region.

| **Region Type**         | **Eligible Regions**                                                                                                                  | **Available Processing Path**                 | **Local Model Option**                                                                                                                                                                                                                                                                                                                     |
| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Native Regions          | United States (US), Europe (EU)                                                                                                       | Local regional data centers                   | Included natively                                                                                                                                                                                                                                                                                                                          |
| Supported Local Regions | Australia (AU), Canada (CA), France (FR), Germany (DE), India (IN), Japan (JP), Singapore (SG), South Korea (KR), United Kingdom (UK) | AI Hub (routes to US or EU). Requires opt-in. | Available upon request through Customer Support. Existing tenants can continue using local model option. Customers using local or self-hosted models may experience limited LLM functionality. Full feature availability, performance, and updates are optimized for and guaranteed only on Palo Alto Networks' cloud-hosted environments. |
| All Other Regions       | All other tenant locations                                                                                                            | AI Hub (routes to US or EU). Requires opt-in. | Not available                                                                                                                                                                                                                                                                                                                              |

{% hint style="info" %}
**NOTE:** The option to access agentic capabilities through the AI Hub requires data that is strictly necessary to execute active prompts (for example, prompt text, attached document contents, and generated LLM responses) to be routed cross-region to the selected EU or US region.
{% endhint %}

### Operational impact

Before enabling cross-region processing, you must consent to the following system changes and data scope boundaries:

* **Permanent transition**: Transitioning a tenant to the AI Hub is permanent and irreversible. After cross-region processing is enabled, you cannot revert to a local model configuration. If you choose local models, you can later change to the AI Hub.
* **Legacy Gemini 2.5 flash chat history**: Upgrading via AI Hub from Gemini 2.5 flash keeps your prior chat history in read-only mode. Past conversations remain available for review, but they can no longer receive new prompts.
* **Active data versus stored data boundaries**: Only data strictly necessary to execute active prompts (for example, prompt text, attached document contents, and generated LLM responses) is routed cross-region to the selected EU or US region. All other customer data, including user profile databases, inactive stored files, and system audit logs, remain strictly within your local residency region.
* **Cortex Advanced Email Security excluded**: In supported local regions, Cortex Advanced Email Security assets and data remain processed strictly within the local region. \[Applies only to users with Cortex Advanced Email Security License]
* **Per-Tenant scope**: The opt-in applies strictly to the current tenant.
* **Ongoing control**: You can turn off access to these models at any time by disabling the LLM capabilities in your tenant. Disabling access stops future cross-region processing, but cannot retroactively delete or reverse data already processed. Re-enabling the toggle restores access under the original consent.
* **Local model availability and vendor dependency**: Model availability, regional routing, and processing terms are subject to underlying vendor availability and their respective terms of service. Customers using local or self-hosted models may experience limited LLM functionality. Full feature availability, performance, and updates are optimized for and guaranteed only on Palo Alto Networks' cloud-hosted environments.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

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

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://cortex-docs.paloaltonetworks.com/cortex-cloud-runtime-security/get-started/agentic-ai-in-cortex-cloud/ai-hub.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
