GitHub Copilot CLI

OverviewCopy Anchor Link

GitHub Copilot CLI can connect to any OpenAI Chat Completions-compatible endpoint. TokenLab works through Copilot CLI's BYOK environment variables.

InstallCopy Anchor Link

With Node.js 22 or later, install through npm:

npm install -g @github/copilot@1.0.85

On macOS or Linux, you can alternatively use Homebrew:

brew install --cask copilot-cli

Verify the installation:

copilot --version

Configure TokenLabCopy Anchor Link

Set the provider variables before starting Copilot CLI:

Use the Quickstart terminal instructions for macOS, Linux, WSL, or Windows PowerShell to set TOKENLAB_API_KEY without putting the key in command history. Launch Copilot CLI from that terminal. For persistent use, use your local secret manager; do not append a plaintext key to your shell profile.

These variables apply only to this launch; your saved account, default model and permission settings stay in place. Launch normally without the variables to use your previous setup. Do not persist them in your shell profile.

COPILOT_PROVIDER_TYPE=openai COPILOT_PROVIDER_BASE_URL=https://api.tokenlab.sh/v1 COPILOT_PROVIDER_API_KEY="${TOKENLAB_API_KEY:?Set TOKENLAB_API_KEY first}" copilot --model kimi-k3

GitHub requires the selected model to support both streaming and tool calling. kimi-k3 exposes tool use and a context window larger than GitHub's recommended 128K minimum.

VerifyCopy Anchor Link

Inside Copilot CLI, ask for a read-only action first, such as:

Inspect this repository and summarize its top-level structure. Do not modify files.

You can also inspect provider help or switch the model for the current session:

copilot help providers

TroubleshootingCopy Anchor Link

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.