Utilize the unlimited free GPT-3.5-Turbo API service provided by the login-free ChatGPT Web.
Due to the frequent updates of OpenAI, I have once again created a new version, which is based on DuckDuckGo, and is GPT-3.5-Turbo-0125.
Repo: https://github.com/missuo/FreeDuckDuckGo
npm install
node app.jsdocker run -p 3040:3040 ghcr.io/missuo/freegpt35docker run -p 3040:3040 missuo/freegpt35mkdir freegpt35 && cd freegpt35
wget -O compose.yaml https://raw.githubusercontent.com/missuo/FreeGPT35/main/compose/compose.yaml
docker compose up -dFreeGPT35 Service with ChatGPT-Next-Web:
mkdir freegpt35 && cd freegpt35
wget -O compose.yaml https://raw.githubusercontent.com/missuo/FreeGPT35/main/compose/compose_with_next_chat.yaml
docker compose up -dAfter deployment, you can directly access http://[IP]:3040/v1/chat/completions to use the API. Or use http://[IP]:3000 to directly use ChatGPT-Next-Web.
FreeGPT35 Service with lobe-chat:
mkdir freegpt35 && cd freegpt35
wget -O compose.yaml https://raw.githubusercontent.com/missuo/FreeGPT35/main/compose/compose_with_lobe_chat.yaml
docker compose up -dAfter deployment, you can directly access http://[IP]:3040/v1/chat/completions to use the API. Or use http://[IP]:3210 to directly use lobe-chat.
location ^~ / {
proxy_pass http://127.0.0.1:3040;
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header REMOTE-HOST $remote_addr;
proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection "upgrade";
proxy_http_version 1.1;
add_header Cache-Control no-cache;
proxy_cache off;
proxy_buffering off;
chunked_transfer_encoding on;
tcp_nopush on;
tcp_nodelay on;
keepalive_timeout 300;
}upstream freegpt35 {
server 1.1.1.1:3040;
server 2.2.2.2:3040;
}
location ^~ / {
proxy_pass http://freegpt35;
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header REMOTE-HOST $remote_addr;
proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection "upgrade";
proxy_http_version 1.1;
add_header Cache-Control no-cache;
proxy_cache off;
proxy_buffering off;
chunked_transfer_encoding on;
tcp_nopush on;
tcp_nodelay on;
keepalive_timeout 300;
}You don't have to pass Authorization, of course, you can also pass any string randomly.
curl http://127.0.0.1:3040/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer any_string_you_like" \
-d '{
"model": "gpt-3.5-turbo",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"stream": true
}'You can use it in any app, such as OpenCat, Next-Chat, Lobe-Chat, Bob, etc. Feel free to fill in an API Key with any string, for example, gptyyds.
- Forked From: https://github.com/skzhengkai/free-chatgpt-api
- Original Author: https://github.com/PawanOsman/ChatGPT
AGPL 3.0 License