Skip to main content

​
Prerequisites

Before you can configure Claude Desktop to use the Connect AI LLM Gateway, you must register a provider, create a routing rule, create a project, and issue a virtual key. See LLM Gateway for details.
A Connect AI Personal Access Token (PAT) is not accepted by the LLM Gateway. Only a virtual key authenticates requests.

​
Configure Claude Desktop

1
Open Claude Desktop.
2
In the application menu, enable Developer Mode by selecting Help > Troubleshooting > Enable Developer Mode (Windows and macOS).
3
Quit and relaunch Claude Desktop.
4
In the menu bar, select Developer > Configure Third Party Inference > Gateway.
5
Select Gateway for where Claude Desktop sends inference requests.
6
Configure the gateway connection as follows:
7
Click Apply Changes, then click Save & Restart.
Claude Desktop routes all requests through the Connect AI LLM Gateway. The gateway selects the provider and model based on your project’s routing rule.
Last modified on October 2, 2026