This project aims to compare the cost of buying a GPU versus the cost of using an API for Large Language Model (LLM) inference.

At the end of the day, this is very crude but it's a start and was immensely helpful for me to understand the cost of using an API for LLM inference for me.

If you like it, AWESOME... if not, sorry... I will try harder next time. :D

You can try it here

Screenshot 1

Screenshot 2

Screenshot 3

Screenshot 4

1. Install http-server locally by running:

   npm install http-server
   npm install -g http-server

1. Run the following command to start the HTTP server:

   ./run.sh

2. Open the web page in your default browser by visiting:

   http://localhost:8080

• Make sure to have Node.js installed on your machine before running the script.
• Report / PDF download not working yet... my bad.