Set up Cline CLI
This guide uses GPT-6.1 Sol (model ID gpt-6.1-sol). Copy your I Code Easy API key from API keys and choose the Standard endpoint for GPT models in Endpoint selection.
Cline CLI
Install Cline CLI and select openai-compatible to use Chat Completions. The example uses Bash.
npm install --global cline
export ICODEEASY_API_KEY="YOUR_ICODEEASY_API_KEY"
cline auth --provider openai-compatible \
--apikey "$ICODEEASY_API_KEY" \
--modelid gpt-6.1-sol \
--baseurl https://api.icodeeasy.cc/v1
cline -i
In PowerShell, set your key with $env:ICODEEASY_API_KEY = "YOUR_ICODEEASY_API_KEY", replace "$ICODEEASY_API_KEY" in the configuration command with "$env:ICODEEASY_API_KEY", and run the command on one line. Cline CLI saves these settings in its own configuration directory. Run cline config to review them.
Verify your first request
Send a short text prompt in the interactive session and confirm the model and status in Usage logs. Check your key for HTTP 401 and your model ID and endpoint for permission errors. If the connection is unstable, rerun cline auth with https://jp.icodeeasy.cc/v1 or https://sg.icodeeasy.cc/v1 as --baseurl.
Official client documentation
Related guides
Chat Completions
Send a conversation using the OpenAI Chat format. Check that your model and selected endpoint support the Chat protocol before sending the request.
VS Code Setup
Install and configure Codex or Claude extensions in VS Code, use secure credentials and custom API addresses, and resolve login prompts.
How do I troubleshoot slow connections or failed requests?
Match 401, 403, 429, timeouts, and Gemini path errors before changing hosts. Switch to the jp or sg backup domain only after the network is the problem.