ZCode with Nbility
ZCode integration depends on whether your release exposes an editable OpenAI-compatible endpoint. Check its provider settings and release documentation first.
Configuration entry point
Open model / AI settings and choose Custom OpenAI / OpenAI Compatible. Add the Nbility address, a dedicated token, and the exact model ID. Run Verify if available, then select the model for the current 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
Display names can be customized, but Model ID must be recognized by the gateway. A fixed-provider release without a URL field cannot be made compatible by renaming a model; see Kilo Code.
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.