Hacker News Reader

Dude! This is so freaking cool. Curious to know how much are you spending in LLMs to generate each model.

Thanks! Well, it had previously been about $5usd a day. Until today and this post... So far in the last 24 hours I've auto topped up while I was asleep 4 times and spent $170 bucks on inference alone.

The complexity of the model does heavily influence the cost. Some models can cost me at little as 7 cents to generate. Others can be a couple bucks.

At the moment I'm focusing on user experience. I just trying to make a product people love as number 1 priority. I'm constantly trying to improve the speed and quality of the model outputs for user. Thankfully, optimising speed helps bring costs down as a side effect too!

I'm also self-funding my own solo-dev "in it for the love of the game" agentic app[0], mine for woodworking. It also supports STL output for printing the woodworking designs.

I found building an MCP was the easiest way to avoid paying for inference or having to charge to try it out. Anyone can add the MCP to chatgpt or claude and use their subscription to do the inference.

[0] sawdust.diy

Reply on news.ycombinator.com