Model picker
Every model ubc now serves appears in the Open WebUI model dropdown.
Open WebUI is a self-hosted chat front end. Add ubc now as an OpenAI connection and serve frontier models to your instance on a free daily budget.
Open WebUI treats ubc now as a standard OpenAI provider, so its core features work unchanged:
Every model ubc now serves appears in the Open WebUI model dropdown.
Responses stream token-by-token through the OpenAI-compatible route.
Run ubc now alongside your other OpenAI-style backends.
Mint a key at /api-keys. One key can back a whole Open WebUI instance, so treat it like a server secret.
In Open WebUI: Admin Settings → Connections → OpenAI API → add a connection. Set the API Base URL and key.
OPENAI_BASE_URL=https://ubcnow.ai/v1OPENAI_API_KEY=ubc_sk_…
Running in Docker? Set the connection through env vars instead of the UI.
OPENAI_API_BASE_URL=https://ubcnow.ai/v1OPENAI_API_KEY=ubc_sk_…
Save the connection, refresh models, and pick a ubc now model in a new chat.
Open WebUI populates its dropdown from the /models endpoint. Confirm it responds.
curl https://ubcnow.ai/v1/models \-H "Authorization: Bearer ubc_sk_…"
Open WebUI lists models from the /models route. Confirm the Base URL ends in /v1 (i.e. https://ubcnow.ai/v1) and that the key is valid, then hit the refresh icon.
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.
Point Open WebUI at ubc now and serve frontier models for free.