TavernAI with Nbility
TavernAI and SillyTavern are different projects, with varying OpenAI settings across releases and forks. Confirm custom endpoint support in your version first.
Configuration entry point
Open API Settings / AI Configuration and select OpenAI Chat Completions. If an editable API Endpoint is available, enter the service prefix according to its field documentation and select the model for the current character session.
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
Older releases may have fixed models or endpoints; replacing the key is insufficient. If the field requests a full request URL, use https://api.nbility.ai/v1/chat/completions; if it appends the path, use the /v1 prefix below.
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 TavernAI guide, licensed under CC BY 4.0. Its account, plan, and proprietary service instructions do not apply here. See the client’s official documentation.