See everything you missed at TailscaleUp.Read the recap →

Set up a self-hosted provider

Last validated:

Configure a self-hosted LLM server as a provider in Aperture so your team can access private models through your tailnet. This setup uses the OpenAI-compatible Chat Completions API. Aperture supports both /v1/chat/completions and /chat/completions paths. Common servers include llama.cpp, vLLM, and Ollama. Verify that your server supports the API features your client requires. For cloud-hosted providers, refer to set up an OpenAI-compatible provider.

Your client and selected provider must support the same API format. Refer to Supported providers and clients for available setup options and requirements.

Prerequisites

Before you begin, you need:

  • An Aperture gateway accessible from your device. Refer to get started with Aperture if you have not set this up.
  • A self-hosted LLM server reachable from the Aperture gateway, either locally or over your tailnet.

Configure the provider

Add your self-hosted server as a provider in your Aperture configuration:

{
  "providers": {
    "private": {
      "baseurl": "http://<self-hosted-server>:8080",
      "models": ["qwen3-coder-30b", "llama-3.1-70b"]
    }
  }
}

Replace <self-hosted-server> with the hostname or Tailscale IP address of your server. To find the correct model names, query the server's model list endpoint, typically GET /v1/models, and use the id field from the response.

In baseurl, localhost refers to the Aperture gateway, not your device. Use it only for a server reachable on the gateway itself. For a server on another device, use its tailnet hostname or Tailscale IP address.

Aperture appends the full incoming request path to baseurl. For /v1/chat/completions requests, omit a final /v1 from baseurl to avoid a doubled /v1/v1 path. Keep any earlier path prefix. Clients that send /chat/completions might need /v1 in baseurl instead. Refer to how Aperture builds upstream URLs for details.

Self-hosted providers use openai_chat compatibility and bearer authorization by default. Servers with an OpenAI-compatible Chat Completions API need no additional flags. For other API formats, set the matching compatibility flags.

If your server does not require authentication, omit the apikey field. If your server requires a key, add "apikey": "<your-key>" to the provider block.

Verify the provider

The best way to verify a connection to a specific model is to send a test request through the Models tab of the Aperture dashboard.

  1. Open the Aperture dashboard and select the Models tab.
  2. Find the model you want to test in the list of configured models. If the model is not listed, check your provider configuration and ensure the model name is correct.
  3. Select the Play icon to the left of the model name to send a test request. If the request succeeds, the icon changes to a green check mark. If it fails, the icon changes to a red "X".

This sends a request from your web browser to the tailnet to verify that Aperture can successfully route requests to the model through the configured provider and that your user account has the necessary permissions to access the model.

Next steps