Kilo with Nbility
This page covers Kilo’s graphical provider settings. See Kilo Code for the VS Code extension and Kilo CLI for terminal configuration.
Configuration entry point
In Settings → Providers, add a Custom provider with ID nbility and OpenAI Compatible / Chat Completions. Add the model, set its actual Context Window and Max Output Tokens, and select it for the current task.
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
If discovery fails, add the model manually. Saving a provider does not verify its context limits; check compaction and tool calls before long tasks.
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 Kilo guide, licensed under CC BY 4.0. Its account, plan, and proprietary service instructions do not apply here. See the client’s official documentation.