Skip to main content
A private AI Gateway resource exposes an AI API only to devices connected with the Pangolin client. Nothing is reachable from the public internet. Unlike public AI Gateway, the gateway does not check a virtual API key. Identity comes from the active client connection. This page covers how the resource works: reachability, access, and what you attach. Providers, model routing, the catalog, and client setup live in AI Gateway.

​
How It Works

  1. You create a private resource with type AI Gateway on a Newt site and attach one or more org-level providers.
  2. You grant users, roles, or machines access, the same as any other private resource.
  3. The user connects with the Pangolin client. The machine running the AI client must be on that tunnel.
  4. The agent calls the resource URL. Pangolin attributes the call to the connected user and proxies to the selected provider.
Clients still need a value in the API key field. Use the literal string none. Deleting the field usually breaks the client.

​
Providers, Not Destinations

Private AI Gateway resources attach providers on the resource’s AI Gateway tab. They do not use a host or CIDR destination as the model backend. Cloud APIs are called from Pangolin. Custom providers can use Site Targets when the model server is on a site network. Private resources, including this type, can only be created on Newt sites.

​
Authentication and Access Rules

Access is the private resource model: grant users, roles, or machines explicitly. See Private Authentication. When the connected client maps to a user, Pangolin forwards that identity upstream as Remote-* headers.

​
More Than One Resource

Give different users and roles their own providers with more than one AI Gateway resource. Distinct hostnames are the usual approach. Unlike other private resource types, they can also share a FQDN because they all route to the gateway inside Pangolin. See Multiple Gateway Resources.

​
Compared to Public AI Gateway

For providers, model routing, and connecting Claude Code, Codex, and other clients, see AI Gateway.