Tooling · JSON

Continue

How do I use Continue with Onrup?

Add your deployment as an openai provider in the Continue config with your base URL. A model fine-tuned on your own codebase conventions gives suggestions that match your code rather than generic ones.

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

Minimal working example

{
  "models": [
    {
      "title": "Onrup code model",
      "provider": "openai",
      "model": "default",
      "apiBase": "https://serve.onrup.com/<tenant>/<deployment>/v1",
      "apiKey": "onrup_sk_..."
    }
  ]
}

The thing that catches people out

Use an always-warm endpoint for anything interactive. A coding assistant that pauses for a cold start mid-keystroke will be uninstalled within a day, whatever its suggestion quality.

Worth knowing

Autocomplete and chat can point at different deployments — a small fast model for completions, a larger one for chat.
Accepted suggestions are training data for the next iteration.
Keep the key out of a config file that gets committed.

Other tooling

LiteLLM

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

n8n

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

Open WebUI

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

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