Pro Max 5x quota exhausted in 1.5 hours despite moderate usage

Post by weavie » Sun, Apr 12, 2026, 7:25 PM UTC

ac29 wrote: post #339

weavie wrote: post #90

How good are local LLMs at coding these days? Does anyone have any recommendations for how to get this setup? What would the minimum spend be for usable hardware? I am getting bored of having to plan my weekends around quota limit reset times...

The very best open models are maybe 3-12 months behind the frontier and are large enough that you need $10k+ of hardware to run them, and a lot more to run them performantly. ROI here is going to be deeply negative vs just using the same models via API or subscription. You can run smaller models on much more modest hardware but they aren't yet useful for anything more than trivial coding tasks. Performance also reall…

Post by brookst » Sun, Apr 12, 2026, 7:26 PM UTC

HauntingPin wrote: post #315

brookst wrote: post #193

Earlier quoted context omitted.

My hypothesis is that people who have continuous sessions that keep the cache valid see the behavior you’re describing: at 95% cache hits (or thereabouts), the max plan goes a long way. But people who go > 5 minutes between prompts and see no cache, usage is eaten up quickly. Especially passing in hundreds of thousands of tokens of conversation history. I know my quote goes a lot further when I sit down and keep sess…

Why is it our job to micromanage all this when it used to work fine without? Something's clearly changed for the worse. Why are people insisting on pushing the responsibility on paying users?

Post by holoduke » Sun, Apr 12, 2026, 7:31 PM UTC

pxc wrote: post #298

holoduke wrote: post #244

Earlier quoted context omitted.

Maybe words. But quality texts in even with opus not perfect. But good enough.

For short texts, the translation I usually want the most is fast translation, and local models are actually great for this. But for high-ish quality translations of substantive texts, you typically want a harness that's pretty different from Claude Code. You want a glossary of technical terms or special names, a structured summary of the wider context, a concise style guide, and you have to chop the text into chunks…

Post by caminante » Sun, Apr 12, 2026, 7:37 PM UTC

KaoruAoiShiho wrote: post #417

wesammikhail wrote: post #233

Earlier quoted context omitted.

I've seen sources like this before. It's all hearsay and promo. I was asking for any publicly available verifiable information regarding the cost of inference at scale. I haven't seen any such info personally which is why I asked. I'm dying to see S-1 filing for Anthropic or OpenAI. I don't actually think inference is as cheap as people say if you consider the total cost (hardware, energy, capex, etc)

Well they're not public yet so you'll have to put up with rumors. But the numbers are available for companies like DeepSeek say they have an 80% profit margin, so it stands to reason OAI etc would do similar numbers considering they charge much more.

Post by egamirorrim » Sun, Apr 12, 2026, 7:45 PM UTC

avree wrote: post #269

bcherny wrote: post #210

Hey all, Boris from the Claude Code team here. We've been investigating these reports, and a few of the top issues we've found are: 1. Prompt cache misses when using 1M token context window are expensive. Since Claude Code uses a 1 hour prompt cache window for the main agent, if you leave your computer for over an hour then continue a stale session, it's often a full cache miss. To improve this, we have shipped a few…

Hey Boris - why is the best way to get support making a Hacker News or X post, and hoping you reply? Why does Anthropic Enterprise Support never respond to inquiries?