OpenAI node
Set a custom Base URL on the OpenAI credential and use the node as usual.
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.
There are two ways to reach ubc now from n8n — pick whichever fits your workflow:
Set a custom Base URL on the OpenAI credential and use the node as usual.
Use the OpenAI Chat Model sub-node with the same ubc now credential.
Call /v1/chat/completions directly for full control over the payload.
Mint a key at /api-keys. In n8n it lives inside a credential, so it stays out of your workflow JSON.
In n8n: Credentials → New → “OpenAI”. Set the API key, then expand options and override the Base URL.
OPENAI_BASE_URL=https://ubcnow.ai/v1OPENAI_API_KEY=ubc_sk_…
Drop in an OpenAI (or AI Agent) node, select the credential, and set the model to an id from /v1/models.
For full control, skip the credential and POST directly.
POST https://ubcnow.ai/v1/chat/completionsHeader Authorization: Bearer ubc_sk_…Header Content-Type: application/jsonBody { "model": "<model-id>","messages": [{"role":"user","content":"={{ $json.prompt }}"}] }
Whether you use the OpenAI node or HTTP, the model must be a real ubc now id.
curl https://ubcnow.ai/v1/models \-H "Authorization: Bearer ubc_sk_…"
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.
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.
You have spent your daily token allowance. It resets at 00:00 UTC. Image and chat usage both draw from the same daily pool.
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.
Mint a key, set the base URL on an n8n credential, and automate.