GPT4Free: Decompile the AI Dialog website interface and use multiple GPT models for free!

General Introduction

GPT4Free is an open source project released on GitHub by developer xtekky, aiming to provide a wide range of powerful language models for free, including GPT-3.5, GPT-4, Llama, Gemini-Pro, Bard and Claude etc. The project provides features such as timeout, load balancing, and flow control by aggregating multiple API requests. Users can easily use these high-level language models through simple installation and configuration.

This project needs to rely on a number of services, decompile the website interface is obsolete, you can branch the project to deploy the latest version. Recommended https://github.com/xiangsx/gpt4free-ts , or use Sealos one-click deployment.

Online experience: https://gptgod.online/

Function List

• Multi-model support: Supports multiple language models such as GPT-3.5, GPT-4, Llama, Gemini-Pro, Bard and Claude.
• Open source and free: Completely open source, users can use and modify the code for free.
• API Integration: Provides a variety of API request features, supporting timeouts, load balancing, and flow control.
• Documentation and Tutorials: Detailed documentation and tutorials to help users get started quickly.
• Community Support: Active community support where users can communicate and get help on GitHub, Telegram, and Discord.

Using Help

Installation process

1. Download Code::
   • Open a terminal and run the following command to clone the project:

     git clone https://github.com/xtekky/gpt4free.git
     

2. Installation of dependencies::
   • Go to the project directory and run the following command to install the required dependencies:

     cd gpt4free
     pip install -r requirements.txt
     

3. Configuration environment::
   • Configure environment variables and API keys as needed, please refer to the project documentation for specific steps.

Guidelines for use

1. Starting services::
   • Run the following command to start the service:

     python main.py
     

2. Calling the API::
   • Requests are made using the provided API, a simple example is shown below:

     import requests
     url = "http://localhost:8000/api/v1/gpt4"
     payload = {
     "model": "gpt-4",
     "prompt": "你好，GPT-4！",
     "max_tokens": 100
     }
     response = requests.post(url, json=payload)
     print(response.json())
     

3. Using Docker::
   • If you prefer to use Docker, you can run the following command to start a Docker container:

     docker-compose up -d
     

common problems

• How do I get an API key?
  • Refer to the project documentation for detailed instructions on obtaining and configuring API keys.
• What to do if you encounter an error?
  • Check that dependencies are installed correctly, make sure environment variables are configured correctly, or ask for help in the community.