Mux with Nbility
Mux custom-provider support depends on the installed release. This guide applies when Providers / Models exposes an API key, base URL, and model ID together.
Configuration entry point
Open Settings → Providers / Models and add an OpenAI-compatible provider named Nbility. Save its connection details, then explicitly select the provider’s model in a new workspace or conversation.
Connection details
| Field | Value |
|---|---|
| Type | OpenAI Compatible / Chat Completions |
| Base URL | https://api.nbility.ai/v1 |
| API key | Dedicated token from Token management |
| Model ID | Exact ID from Models |
This table applies to a base URL field that appends /chat/completions. Follow the field documentation when a complete endpoint is requested; see Connection basics.
Verification and limits
A workspace can retain its previous model. If provider testing works but one workspace fails, inspect that workspace’s selection. Releases without an editable base URL cannot use this direct setup.
Send a short message in a new conversation and check the request and model in Usage logs. With no log, inspect the active provider and network first. With a failed request log, use the error guide.
References
Adapted and rewritten for Nbility from aicentos’s Mux guide, licensed under CC BY 4.0. Its account, plan, and proprietary service instructions do not apply here.