Integration · n8n

Automate with ubc now in n8n.

n8n's OpenAI credential takes a custom base URL. Point it at ubc now and call frontier models from any workflow on a free daily budget.

What works

Supported in n8n.

There are two ways to reach ubc now from n8n — pick whichever fits your workflow:

OpenAI node

Set a custom Base URL on the OpenAI credential and use the node as usual.

AI Agent node

Use the OpenAI Chat Model sub-node with the same ubc now credential.

HTTP Request node

Call /v1/chat/completions directly for full control over the payload.

Setup

Connect in a few steps.

Mint a ubc now key

Mint a key at /api-keys. In n8n it lives inside a credential, so it stays out of your workflow JSON.

Create an OpenAI credential

In n8n: Credentials → New → “OpenAI”. Set the API key, then expand options and override the Base URL.

ubc now connection
OPENAI_BASE_URL=https://ubcnow.ai/v1
OPENAI_API_KEY=ubc_sk_…

Use it in a node

Drop in an OpenAI (or AI Agent) node, select the credential, and set the model to an id from /v1/models.

Prefer raw HTTP? Use a Request node

For full control, skip the credential and POST directly.

HTTP Request node
POST https://ubcnow.ai/v1/chat/completions
Header Authorization: Bearer ubc_sk_…
Header Content-Type: application/json
Body { "model": "<model-id>",
"messages": [{"role":"user","content":"={{ $json.prompt }}"}] }
Examples

Copy, paste, run.

List models to fill the model field

Whether you use the OpenAI node or HTTP, the model must be a real ubc now id.

List the models ubc now serves
curl https://ubcnow.ai/v1/models \
-H "Authorization: Bearer ubc_sk_…"
Troubleshooting

If something's off.

The OpenAI node ignores my base URL

The Base URL override lives under the credential's options, not the node. Edit the credential and make sure the override field holds the /v1 URL.

401 Unauthorized

Your key must be an active ubc now key (it starts with ubc_sk_). Mint or re-mint one at /api-keys, and make sure it is sent as a Bearer token, not pasted into a username field.

402 / budget exhausted

You have spent your daily token allowance. It resets at 00:00 UTC. Image and chat usage both draw from the same daily pool.

Model not found

Use an exact model id from https://ubcnow.ai/v1/models — copy it verbatim. ubc now does not alias OpenAI model names like "gpt-4o"; pick one of the models it actually serves.

Put frontier models in your workflows.

Mint a key, set the base URL on an n8n credential, and automate.