Coding Tools
Cline
Configure Cline to use TokenLab models
Overview
Cline can use TokenLab through its OpenAI-compatible settings.
Install
Install Cline from your editor's extension marketplace, then open the Cline panel. Cline supports VS Code, Cursor, VSCodium, Windsurf, Antigravity, and JetBrains IDEs.
Configure TokenLab
Save the current provider, model and connection settings locally before editing. These controls change the active model selection; restore your previous values when finished. Keep signed-in accounts and tool permissions unchanged. Do not overwrite another OpenAI-compatible connection without a restorable backup.
- Click the gear icon in the Cline panel.
- Set API Provider to OpenAI Compatible.
- Enter the following values:
| Field | Value |
|---|---|
| Base URL | https://api.tokenlab.sh/v1 |
| API Key | Your TokenLab API key |
| Model ID | kimi-k3 |
- Click Verify.
For the kimi-k3 example, Cline's optional model configuration can use:
| Capability | Value |
|---|---|
| Context / input limit | 1048576 |
| Max output tokens | 131072 |
| Image support | Enabled |
The model catalog changes over time. Use the live TokenLab model catalog when selecting another model instead of copying a stale list.
Verify
After Verify succeeds, send a small read-only task before allowing edits:
List the files in this workspace and explain which one is the application entry point. Do not edit anything.Saving settings or listing models does not verify a key or a completed request. A prompt uses TokenLab balance. Check the reply and its matching request record before trying tools; auxiliary requests may also be billed.