Kerux
Sign in
PricingCompareCalculatorBlogAlready a customer?
Setup · about 2 minutes

Connect your AI to Kerux

Kerux answers tickets with an AI key you bring — so you pay your provider directly, never a markup. There are two ways to do it. Pick one.

Recommended · easiest

A cloud API key

From your preferred provider. Works with Kerux right away — best for almost everyone.

Advanced · private

A local open-source model

Runs on your own machine — nothing leaves your network. A little more setup.

Option 1

Use a cloud API key

Same steps on Mac, Windows, and Linux — it all happens in your browser.

  1. 1
    Create an account with an AI provider

    Pick your preferred LLM provider — several offer a free tier, so your AI can start at $0. Sign up (no card needed for most free tiers).

  2. 2
    Open the API keys section

    In your provider's dashboard, find the area labelled API keys (sometimes under Settings or Developer).

  3. 3
    Create a key and copy it

    Generate a new key, name it “Kerux”, and copy it right away — most providers show it only once. Lost it? Just create another.

That's itPaste the key into Kerux (below) and your AI is live. On a provider's free tier your AI responses can cost $0 — free tiers are rate-limited, so very high volume eventually needs a paid key, still billed by your provider at cost and never marked up by us.
Option 2

Run a local open-source model

Free and fully private — the AI runs on your own computer.

  1. 1
    Install a local model runner

    Tools like Ollama let you run open-source models on your own machine. Download it for your OS below.

    macOS
    Download the installer from your runner's site, open it, and move the app to Applications. Launch it once.
    Windows
    Download the Windows installer and run it — it sets everything up for you.
    Linux
    Most runners offer a one-line install script you paste into a terminal.
  2. 2
    Download an open-source model

    Pull a model of your choice — popular open ones include Llama, Mistral, and Qwen. A smaller model is a fast, capable starting point.

  3. 3
    It now serves locally

    The runner exposes an OpenAI-compatible endpoint on your machine — that's the address Kerux connects to.

Good to knowKerux runs in the cloud, so it can't reach a model on your computer's local network directly. To use a local model with hosted Kerux, expose the runner at a secure public address (a tunnel or a small server), then point Kerux at it. If that sounds like a lot, the cloud API key above is the simpler path — and just as free.

Paste your key into Kerux

  1. 1. Go to Settings → AI Training.
  2. 2. Choose your AI provider.
  3. 3. Paste your key and click Save — it's encrypted, never shown in your browser.
  4. 4. Pick a model, then send a test ticket and watch it reply.
Start free — bring your own key