<div align="center">
# GPT4Free TypeScript Version ð
###### Providing a free OpenAI GPT-4 API!
English | [ä¸æ](README_zh.md) | [æ¥æ¬èª](README_ja.md)
[![Discord Server](https://discordapp.com/api/guilds/1115852499535020084/widget.png?style=banner2&count=true)](https://discord.gg/cYUU8mCDMd)
<p>You can join our discord: <a href="https://discord.gg/cYUU8mCDMd">discord.gg/gptgod<a> for further updates. <a href="https://discord.gg/cYUU8mCDMd"><img align="center" alt="gpt4free Discord" width="22px" src="https://raw.githubusercontent.com/peterthehan/peterthehan/master/assets/discord.svg" /></a></p>
</div>
## ð Free OpenAI Key
Base URL: `https://api.gptgod.online`
Api Key: `sk-OsMMq65tXdfOIlTUYtocSL7NCsmA7CerN77OkEv29dODg1EA`
Support Models: `gpt-4-all`,`gpt-3.5-turbo`,`gpt-3.5-turbo-16k`,`net-gpt-3.5-turbo`,`net-gpt-3.5-turbo-16k`,`claude-1-100k`,`google-palm`,`llama-2-70b`,`llama-2-13b`,`llama-2-7b`,`code-llama-34b`,`code-llama-13b`,`code-llama-7b`,`qwen-72b`,`stable-diffusion`,`mixtral-8x7b`,`mistral-medium`
## ð© Reverse target
I suggest you fork this project first. Some websites may go offline at any time.
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. Unfortunately, most of the sites here are no longer available.
***Update At 2023-09-10***
| Site | Models |
|----------|---------------------------------------------------|
| you | gpt-3.5-turbo |
| phind | net-gpt-3.5-turbo |
| forefront| gpt-3.5-turbo, claude |
| mcbbs | gpt-3.5-turbo, gpt-3.5-turbo-16k |
| chatdemo | gpt-3.5-turbo, gpt-3.5-turbo-16k |
| vita | gpt-3.5-turbo |
| skailar | gpt-4 |
| fakeopen | gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-4 |
| easychat | gpt-4 |
| better | gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-4 |
| pweb | gpt-3.5-turbo, gpt-3.5-turbo-16k |
| bai | gpt-3.5-turbo |
| gra | gpt-3.5-turbo, gpt-3.5-turbo-16k |
| magic | gpt-3.5-turbo, gpt-4, claude-instance, claude, claude-100k |
| chim | gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-4 |
| ram | gpt-3.5-turbo-16k |
| chur | gpt-3.5-turbo, gpt-3.5-turbo-16k |
| xun | gpt-3.5-turbo, gpt-3.5-turbo-16k |
| vvm | gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-4 |
| poef | |
| claude | claude-2-100k |
| cursor | gpt-3.5-turbo, gpt-4 |
| chatbase | gpt-3.5-turbo |
| ails | gpt-3.5-turbo |
| sincode | gpt-3.5-turbo, gpt-4 |
| openai | too much |
| jasper | gpt-3.5-turbo, gpt-4 |
| pap | |
| acytoo | gpt-3.5-turbo |
| google | search |
| www | url |
| ddg | search |
## ðââï¸ Run
First of all, you should create file `.env`.
> ***All operation methods require this step.***
```env
http_proxy=http://host:port
rapid_api_key=xxxxxxxxxx
EMAIL_TYPE=temp-email44
DEBUG=0
POOL_SIZE=0
PHIND_POOL_SIZE=0
```
- `http_proxy`: config your proxy if you can not access target website directly; If you dont need proxy, delete this line;
- `forefront` use env(this site has been removed):
- `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](https://rapidapi.com/Privatix/api/temp-mail): soft limit 100req/days, if over use money, need bind credit card! Very Stable!
- [temp-email44](https://rapidapi.com/calvinloveland335703-0p6BxLYIH8f/api/temp-mail44): 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 ð¥ï¸
```shell
# install module
yarn
# start server
yarn start
```
### Run with docker(Suggest!) ð³
```
docker run -p 3000:3000 --env-file .env xiangsx/gpt4free-ts:latest
```
### Deploy with docker-compose ð
first, you should create file .env; Follow step "Run with docker
deploy
```
docker-compose up --build -d
```
### Clash+one-api+gpt4free-ts Start with one command ð®
[gpt4free-ts-deploy](https://github.com/xiangsx/gpt4free-ts-deploy)
## ð Let's Use GPT4
> Find supports model and site http://127.0.0.1:3000/supports [GET]
> The same as openai http://127.0.0.1:3000/:site/v1/chat/completions [POST]
> The same as openai http://127.0.0.1:3000/v1/chat/completions?site=xxx [POST]
> Return when chat complete http://127.0.0.1:3000/ask?prompt=***&model=***&site=*** [POST/GET]
> Return with eventstream http://127.0.0.1:3000/ask/stream?prompt=***&model=***&site=*** [POST/GET]
### Request Params ð
- `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` `gpt-3.5-turbo-16k`
- `site`: default `you`. target site, include `fakeopen` `better` `forefront` `you` `chatdemo` `phind` `vita`
### Site Support Model ð§©
query supports site and models with api `127.0.0.1:3000/supports`
```json
[
{
"site": "you",
"models": [
"gpt-3.5-turbo"
]
},
...
]
```
### Response Params ð
Response when chat end(/ask):
```typescript
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"}
```
### Exampleð¡
1. request to site you with history
req:
[127.0.0.1:3000/ask?site=you&prompt=[{"role":"user","content":"hello"},{"role":"assistant","content":"Hi there! How can I assist you today?"},{"role":"user","content":"who are you"}]]()
res:
```json
{
"content": "Hi there! How can I assist you today?"
}
```
[127.0.0.1:3000/ask?site=you&prompt=[{"role":"user","content":"ä½ å¥½\n"},{"role":"assistant","content":"ä½ å¥½ï¼æä»ä¹æå¯ä»¥å¸®å©ä½ çåï¼"},{"role":"user","content":"ä½ æ¯è°"}]]()
2. request to site you with stream return
req:
[127.0.0.1:3000/ask/stream?site=you&prompt=who are you]()
res:
```
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"}
```
## ð¥ Chat Gr
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
chatgpt4 我建议你首先复制这个项目。一些网站可能随时会下线。 仍在努力保持更新。 在这里已经实现了模型:如果你不希望你的网站出现在这里,请提出一个问题,我将立即将其移除。不幸的是,这里的大多数网站现在已经不再可用。 ChatGPT 4是OpenAI开发的最新一代语言模型,它代表了人工智能在自然语言处理领域的一个重要进步。尽管目前没有具体的公开信息表明存在一个命名为"ChatGPT 4"的模型,但是可以基于OpenAI之前发布的模型,如GPT-3(生成式预训练转换器的第三版),来推测ChatGPT 4可能具备的一些特性和改进: 更强大的语言理解能力:ChatGPT 4可能会在理解自然语言方面有显著提升,能够更准确地解析复杂的语句和上下文。 更准确的响应生成:新一代模型可能会生成更准确、更连贯、更自然的文本响应。 增强的上下文记忆:ChatGPT 4可能会有改进的记忆机制,使其能够更好地记住对话中早先提及的信息。
资源推荐
资源详情
资源评论
收起资源包目录
chatgpt4的免费api,还支持以下模型:gpt-4-all,gpt-3.5-turbo,gpt-3.5-turbo-16k (101个子文件)
Dockerfile 513B
.dockerignore 30B
.gitignore 75B
tsconfig.json 12KB
package.json 2KB
yarn.lock 189KB
README_zh.md 13KB
README.md 11KB
README_ja.md 10KB
HowToUse.md 4KB
.prettierrc 256B
emailFactory.ts 33KB
index.ts 26KB
proxyAgent.ts 21KB
index.ts 15KB
index.ts 15KB
index.ts 15KB
index.ts 14KB
index.ts 14KB
base.ts 14KB
index.ts 13KB
index.ts 13KB
define.ts 13KB
index.ts 13KB
index.ts 11KB
index.ts 11KB
router.ts 11KB
index.ts 11KB
index.ts 10KB
index.ts 10KB
index.ts 10KB
index.ts 10KB
index.ts 10KB
config.ts 10KB
index.ts 10KB
index.ts 9KB
child.ts 9KB
index.ts 9KB
index.ts 9KB
index.ts 9KB
index.ts 9KB
pool.ts 9KB
index.ts 9KB
index.ts 9KB
puppeteer.ts 8KB
define.ts 8KB
index.ts 8KB
child.ts 8KB
index.ts 8KB
index.ts 8KB
auto.ts 8KB
child.ts 8KB
define.ts 7KB
index.ts 7KB
index.ts 7KB
index.ts 7KB
index.ts 7KB
index.ts 7KB
index.ts 6KB
index.ts 6KB
index.ts 6KB
prompt.ts 6KB
captcha.ts 6KB
index.ts 5KB
index.ts 5KB
log.ts 5KB
child.ts 5KB
index.ts 4KB
index.ts 4KB
index.ts 4KB
index.ts 4KB
prompt.ts 4KB
index.ts 4KB
cache.ts 3KB
index.ts 3KB
index.ts 3KB
index.ts 3KB
index.ts 3KB
index.ts 3KB
index.ts 3KB
index.ts 3KB
index.ts 3KB
index.ts 2KB
index.ts 2KB
index.ts 2KB
index.ts 2KB
index.ts 2KB
index.ts 2KB
index.ts 2KB
index.ts 2KB
index.ts 2KB
index.ts 2KB
file.ts 2KB
index.ts 1KB
define.ts 1KB
define.ts 257B
define.ts 153B
koa.d.ts 152B
LICENSE.txt 34KB
docker-compose.yaml 444B
共 101 条
- 1
- 2
资源评论
就是一顿骚操作
- 粉丝: 550
- 资源: 51
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- 本地镜像源配置脚本本地镜像源配置脚本
- 与spoon配套使用的jdk
- 基于单片机的便携式粮食水分测试仪的研究
- 测绘基坑支护工程变形监测报告1.pdf
- 基于PHP+swoole实现的微信机器人,依赖vbot和微信网页版的功能,帮助管理微信群/聊天/踢人等+源码+开发文档+运行教程
- com.xunmeng.pinduoduo_Release_cd290ca9_ARM64.apk
- 2788727d-25a0-41b2-b6b4-265d193edb95.doc
- 基于AVR单片机的伺服电机系统研究
- Lab-Electronic Craft Practicum-2-Simulation of a Single Tube Com
- 贪吃蛇基于TypeScript
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功