Guides

n8n

Use Scalaix models in n8n's AI nodes, and call published endpoints with the HTTP Request node.

Models in AI nodes

In n8n, open Credentials and create an OpenAI credential.
Set API Key to your Scalaix key (sx_...).
Set Base URL to https://www.scalaix.com/v1.
Save. n8n tests the credential by listing models, which Scalaix answers with the models your key may use.

In an AI Agent or Basic LLM Chain, add an OpenAI Chat Model sub-node with that credential and pick a model, or type an id such as claude-3-5-haiku-latest or auto.

Each workflow can use its own key, so you can cap it with a monthly budget and see it separately in Usage.

Published endpoints

Use an HTTP Request node:

Setting	Value
Method	`POST`
URL	`https://www.scalaix.com/acme/support/classify-ticket`
Authentication	Generic credential type: Header Auth, name `Authorization`, value `Bearer sx_...`
Send Body	JSON

Body, using fields from an earlier node:

{
  "inputs": {
    "ticket": {
      "subject": "{{ $json.subject }}",
      "body": "{{ $json.body }}"
    }
  }
}

The node's output has data with your endpoint's fields, so the next node can use {{ $json.data.category }}.

Turn on Retry On Fail in the node's settings to retry 429 and 5xx responses.