gpt4free-ts - Providing a free OpenAI GPT-4 API ! This is a replication project for the typescript version of xtekky/gpt4free

Created at: 2023-05-04 21:32:13
Language: TypeScript
License: GPL-3.0

GPT4Free TypeScript Version 🆓

Providing a free OpenAI GPT-4 API!

English | 中文 | 日本語

Discord Server

You can join our discord: for further updates. gpt4free Discord

👍 GPT4 Website Base on this project GPTGOD

Website Feature (Click to expand)

GPTGOD Support

  • [x] Midjourney The Most Powerful AI Drawing System in History
  • [x] Stable Diffusion
  • [x] Claude
  • [x] Chatgpt
  • [x] Chatgpt with internet
  • [x] Create wechat ai robot for yourself, just need one step

In the next two weeks, I will open source all the code for GPTGOD. If you need, Please watch this project or follow me to receive notifications.

Why now? because there are stil some secret config should be removed from that project.

🚩 Reverse target

Still striving to keep updating.

Have implemented models here: If you do not want your website to appear here, please raise an issue and I will remove it immediately.

model support status active time
chatdemo 👍gpt3.5 Active after 2023-06-13 GPT-4/gpt3.5 Active after 2023-06-13 👍GPT-3.5 Active after 2023-06-13 Gpt3.5/ Internet / good search Active after 2023-06-14 GPT-4/3.5 GPT-4/3.5 GPT-3.5 / Internet GPT-3.5

🏃‍♂️ Run

First of all, you should create file .env.

All operation methods require this step.

  • http_proxy: config your proxy if you can not access target website directly
  • forefront use env:
    • rapid_api_key: you should config this if you use forefront api, this apikey is used for receive register email, get api key here
    • EMAIL_TYPE: temp email type includes temp-email temp-email44 tempmail-lol
      • temp-email: soft limit 100req/days, if over use money, need bind credit card! Very Stable!
      • temp-email44: hard limit 100req/days! Stable!
      • tempmail-lol: nothing need, limit 25request/5min. Not Stable.
    • DEBUG: Valid when use forefront You can set =1 when you run local. show reverse process
    • POOL_SIZE: forefront concurrency size. Keep set=1 until you run it successfully!!! You can engage in {POOL_SIZE} conversations concurrently. More pool size, More conversation can be done simultaneously, But use more RAM
  • phind use env:
    • PHIND_POOL_SIZE: phind concurrency size.You can engage in {POOL_SIZE} conversations concurrently. More pool size, More conversation can be done simultaneously, But use more RAM

Run local 🖥️

# install module
# start server
yarn start

Run with docker(Suggest!) 🐳

docker run -p 3000:3000 --env-file .env xiangsx/gpt4free-ts:latest

Deploy with docker-compose 🎭

first, you should create file .env; Follow step "Run with docker


docker-compose up --build -d

🚀 Let's Use GPT4

Return when chat complete***&model=***&site=***

Return with eventstream***&model=***&site=***

Request Params 📝

  • prompt: your question. It can be a string or jsonstr.
    • example jsonstr:[{"role":"user","content":"hello\n"},{"role":"assistant","content":"Hi there! How can I assist you today?"},{"role":"user","content":"who are you"}]
    • example string: who are you
  • model: default gpt3.5-turbo. model include:gpt4 gpt3.5-turbo net-gpt3.5-turbo
  • site: default you. target site, include forefront you chatdemo phind

Site Support Model 🧩

  • forefront :gpt4
  • you: gpt3.5-turbo
  • chatdemo: gpt3.5-turbo
  • phind: net-gpt3.5-turbo

Response Params 🔙

Response when chat end(/ask):

interface ChatResponse {
    content: string;
    error?: string;

Response with stream like, Suggest!!(/ask/stream):

event: message
data: {"content":"I"}

event: done
data: {"content":"'m"}

event: error
data: {"error":"some thind wrong"}


  1. request to site you with history

req:[{"role":"user","content":"hello"},{"role":"assistant","content":"Hi there! How can I assist you today?"},{"role":"user","content":"who are you"}]


  "content": "Hi there! How can I assist you today?"

  1. request to site you with stream return

req: are you


event: message
data: {"content":"I"}

event: message
data: {"content":"'m"}

event: message
data: {"content":" a"}

event: message
data: {"content":" search"}

event: message
data: {"content":" assistant"}
event: done
data: {"content":"done"}

👥 Wechat Group

🌟 Star History

Star History Chart

You may join our discord: for further updates. gpt4free Discord

This is a replication project for the typescript version of gpt4free

gpt4free logo

Legal Notice

This repository is not associated with or endorsed by providers of the APIs contained in this GitHub repository. This project is intended for educational purposes only. This is just a little personal project. Sites may contact me to improve their security or request the removal of their site from this repository.

Please note the following:

  1. Disclaimer: The APIs, services, and trademarks mentioned in this repository belong to their respective owners. This project is not claiming any right over them nor is it affiliated with or endorsed by any of the providers mentioned.

  2. Responsibility: The author of this repository is not responsible for any consequences, damages, or losses arising from the use or misuse of this repository or the content provided by the third-party APIs. Users are solely responsible for their actions and any repercussions that may follow. We strongly recommend the users to follow the TOS of the each Website.

  3. Educational Purposes Only: This repository and its content are provided strictly for educational purposes. By using the information and code provided, users acknowledge that they are using the APIs and models at their own risk and agree to comply with any applicable laws and regulations.

  4. Copyright: All content in this repository, including but not limited to code, images, and documentation, is the intellectual property of the repository author, unless otherwise stated. Unauthorized copying, distribution, or use of any content in this repository is strictly prohibited without the express written consent of the repository author.

  5. Indemnification: Users agree to indemnify, defend, and hold harmless the author of this repository from and against any and all claims, liabilities, damages, losses, or expenses, including legal fees and costs, arising out of or in any way connected with their use or misuse of this repository, its content, or related third-party APIs.

  6. Updates and Changes: The author reserves the right to modify, update, or remove any content, information, or features in this repository at any time without prior notice. Users are responsible for regularly reviewing the content and any changes made to this repository.

By using this repository or any code related to it, you agree to these terms. The author is not responsible for any copies, forks, or reuploads made by other users. This is the author's only account and repository. To prevent impersonation or irresponsible actions, you may comply with the GNU GPL license this Repository uses.