OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why?

Re:OpenAI and Anthropic cut their LLM prices by up to 80% wi... by ylrd91 on Sunday October 25, 2026 @07:27PM (#50237076)

Don’t write your own. Fork maki.sh and customize it like I did. It’s built in Rust and is absolutely amazing.

[ Parent | on HN ]

Re:OpenAI and Anthropic cut their LLM prices by up to 80% wi... by schaefer on Sunday October 25, 2026 @08:21PM (#50237414)

Thanks for the suggestion, but that’s not a fit for me.

I’m writing my own harness to learn. And I’m writing it in zig.

But, I’ll absolutely add maki.sh to my reading list. So, that’s a win.

[ Parent | on HN ]

Re:OpenAI and Anthropic cut their LLM prices by up to 80% wi... by crossroadsguy on Monday October 26, 2026 @05:07AM (#50241068)

You should do that. I am also summoning the motivation to start on my own. I guess the worse will be that I fail. Might as well fork sth more basic, or build on top of sth SDK/library like.

[ Parent | on HN ]

Re:OpenAI and Anthropic cut their LLM prices by up to 80% wi... by schaefer on Monday October 26, 2026 @08:42AM (#50242652)

I don't know if you'll be interested, but there is an excellent book on the topic: Build an AI Agent (From Scratch), by Jungjun Hur and Younghee Song (Manning Publication).

By chapter four you have a minimal working codebase in python. Later chapters add out features like tool calling, planning, and reflection.

[ Parent | on HN ]

Re:OpenAI and Anthropic cut their LLM prices by up to 80% wi... by crossroadsguy on Monday October 26, 2026 @05:05AM (#50241061)

I am thinking about it but I think forking will miss the point. I'd rather do in a way when there is a prevalence of various types of agentic/harness SDKs for people to make their own apps (aka harnesses) from.

[ Parent | on HN ]

Re:OpenAI and Anthropic cut their LLM prices by up to 80% wi... by ylrd91 on Monday October 26, 2026 @09:59AM (#50243846)

That’s what pi.dev exist for but I’m not touching it because like all of the other harnesses it’s built in JS and they’re all terrible when it comes to cpu and memory use. Maki is the only one I found the be the most efficient harness. It uses 1% cpu idle vs 20-30%.

[ Parent | on HN ]