Three steps to your first request
- Get a BetterToken API key and choose a Model ID in the model plaza.
- Select OpenAI Compatible in Kilo Code, then enter the API key,
https://bettertoken.ai/v1, and Model ID. - Save the settings, restart the extension, and send a short request in a new chat.
Key settings
Prerequisites
- The current version of the tool is installed
- A BetterToken API key: register and get one
- A Model ID from the model plaza
Additional requirements
- VS Code installed
Install
Install or open Kilo Code, then continue with the manual setup below.Manual setup
Complete this setup in the Kilo Code settings UI. You do not need to edit a configuration file.Setup
1
Clear conflicting environment variables
2
Open Kilo Code settings
Open the Kilo Code settings UI.
3
Configure the API provider
Fill in:
- API Provider →
OpenAI Compatible - Base URL →
https://bettertoken.ai/v1 - API Key → your BetterToken API Key
- Model → a model ID from a supported provider copied from the model plaza
4
Only configure extra headers when the official docs explicitly require them
The official Kilo Code material we checked mentions optional custom headers for OpenAI-compatible providers, but it does not treat
User-Agent as a required BetterToken setup step.If you are also using a custom gateway, tenant routing, observability, or caching layer, add headers only according to that upstream service’s official docs.5
Restart Kilo Code
After changing the config, restart VS Code or reload the Kilo Code extension so the new settings take effect.
If you need extra headers, follow the current Kilo Code docs or your upstream gateway requirements instead of assuming
User-Agent is mandatory for BetterToken.Verify the connection
Open a new Kilo Code chat and send a short prompt such asReply with one word: OK. If the tool responds without an authentication or Model ID error, the first request succeeded. Restart VS Code or the extension after changing the configuration. If it fails, go directly to Common errors.
Switch models
Open the model selector or change theModel field in the configuration. Use the exact Model ID from the model plaza, then restart the current session.
Common errors
- OpenAI-compatible API vs Anthropic-compatible API
- MCP vs API Key and Base URL
- What are model_provider, base_url, and wire_api?
- How to configure an OpenAI-compatible API in Cline
Advanced setup
Supported providers
Statuses apply to the BetterToken setup documented on this page.
What the setup methods mean
What the setup methods mean
- Manual setup: enter the API Key, Base URL, and Model.
- Not supported: no verified direct setup is currently available.
Technical details
Protocol, endpoint, and internal provider fields
Protocol, endpoint, and internal provider fields
This setup uses
https://bettertoken.ai/v1. The tool appends the OpenAI-compatible endpoint path. Do not add /chat/completions or /responses unless a specific field explicitly requires it.