Set up Maka
This guide uses Apache Maka (Incubating) and 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.
Maka
Follow the Apache Maka download and installation instructions. Open Settings → Models → Add connection and select Custom connection.
Fill in the following fields and click Save provider.
- Connection identifier
icodeeasy - Display name I Code Easy
- Service URL
https://api.icodeeasy.cc/v1 - API Key Your I Code Easy API key
- Default request protocol OpenAI Chat Completions
- Default model
gpt-6.1-sol
If gpt-6.1-sol is missing from the model list, use Fetch models or add it manually. Enable it and set it as the default model.
Command line
Install the nightly version from the official CLI guide. Follow the connection wizard on first launch, or open it with /setup. Choose a custom Chat Completions connection, use the address, key, and model above, then select gpt-6.1-sol with /model.
npm install --global maka-agent@nightly
maka
Verify your first request
Select the model, send a short text prompt, then confirm the model and status in Usage logs. If the connection is unstable, use https://jp.icodeeasy.cc/v1 or https://sg.icodeeasy.cc/v1 as the service URL.
Official client documentation
Related guides
OpenAI Responses
Send input using the OpenAI Responses format. This page shows HTTP streaming. See the related guide for Codex client setup.
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.
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.