Re:What I learned building an opinionated and minimal coding...
by cyanydeez on Sunday February 01, 2026 @11:31AM
(#46847295)
And its doubtful they are anywhere near break even costs
Re:What I learned building an opinionated and minimal coding...
by 0xbadcafebee on Sunday February 01, 2026 @01:06PM
(#46847999)
According to the article, Pi massively shrinks your context use (due to smaller system prompt and lack of MCPs) so your token use may drop. Also Pi seems to support Anthropic OAuth for your plan (but afaik they might ban you)
Re:What I learned building an opinionated and minimal coding...
by ebenes on Thursday February 12, 2026 @09:08AM
(#46989013)
I second that from using Pi for two weeks now. It's not a little but a massive difference. My estimation is about 5-10x longer lasting token windows. Getting done more is just one of the benefits. I've briefly summarised my experience in this article:
https://ewaldbenes.com/en/blog/the-only-coding-agent-you-ll-...
I’m on a $100/mo plan, but the codex bar makes it look like I’m burning closer to $500 every 30 days. I tried going local with Qwen 3 (coding) on a Blackwell Pro 6000, and it still feels a beat behind, either laggy, or just not quite good enough for me to fully relinquish Claude Code.
Curious what other folks are seeing: any success stories with other agents on local models, or are you mostly sticking with proprietary models?
I’m feeling a bit vendor-locked into Claude Code: it’s pricey, but it’s also annoyingly good