Tooling · Configuration

n8n

How do I use n8n with Onrup?

Create an OpenAI credential in n8n with your deployment base URL and Onrup key, then use the standard model nodes. No custom node is needed, because the credential accepts any compatible base URL.

A workflow automation tool with a visual editor, self-hostable, with language-model nodes built in.

Minimal working example

Credential: OpenAI API
  API Key   onrup_sk_...
  Base URL  https://serve.onrup.com/<tenant>/<deployment>/v1

Node: Basic LLM Chain -> Model: default

The thing that catches people out

Increase the node timeout before using a scale-to-zero endpoint. The default is short enough that a cold start reads as a workflow failure, and the retry then triggers another cold start.

Worth knowing

Workflow automation is bursty by nature, which makes scale-to-zero a good fit — provided the timeout accounts for it.
Automation output is excellent fine-tuning data: it is repetitive, structured and already reviewed.
Keep credentials in n8n’s credential store rather than in node parameters.

Other tooling

LiteLLM

A proxy and library that presents many model providers behind one OpenAI-compatible interface.

Open WebUI

A self-hosted chat interface that can connect to any OpenAI-compatible backend.

Continue

An open-source coding assistant extension for VS Code and JetBrains that can use any compatible model.

Start with the free tier

A magic link creates your account, your tenant and your first API key. No card until you ask for compute.

Get your API key Read the docs