ChatGPT-on-WeChat Integration Guide

Target audience: Developers, Deployment Administrators Last updated: 2026-08-06

ChatGPT-on-WeChat currently provides OpenAI Compatible Key and Base URL fields in its configuration template. We recommend getting the project running on a web or terminal channel first, then configuring WeChat-related capabilities. This approach separates model connection issues from messaging channel issues.

Install the Project

git clone https://github.com/zhayujie/chatgpt-on-wechat
cd chatgpt-on-wechat
python -m pip install -r requirements.txt
cp config-template.json config.json

Configure the Model Connection

Modify the relevant fields in your existing config.json. Do not overwrite the entire configuration with the snippet below:

{
  "open_ai_api_key": "YOUR_API_KEY",
  "open_ai_api_base": "https://<your-api-endpoint>",
  "model": "deepseek-v4-flash"
}

open_ai_api_base is the field name used in the current project template. Copy the model call name from the console. Keep the original project configuration for channel, group chat, trigger word, and plugin settings.

Use the endpoint address shown on the "API Key" page in the console.

Step-by-Step Verification

After starting the project, send a message through the simple channel provided by the project and check the usage records in the console. Once model calls are working correctly, configure the WeChat channel following the project's official documentation.

If the model works but WeChat does not receive messages, check the channel login, callback, and session limits. Do not repeatedly modify the API address and Key that have already been verified.