Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

github.com

Post reply on HN
Print view View original

51–60 of 695 posts

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

#51

Post by vidarh »

jedisct1 wrote: post #7

GPT-5.4 works amazingly well. I’ve moved away from Claude and toward open-source models plus a ChatGPT subscription. That setup has worked really well for me: the subscription is generous, the API is flexible, and it fits nicely into my workflow. GPT-5.4 + Swival ( https://swival.dev ) are now my daily drivers.

I hit the limits on the lower tiers of Codex just as fast as with Claude. At the moment I'm cycling between Claude, Codex, GLM5.1, and Kimi. The latter two are getting good enough, though, that I can make things go really far by doing planning with Opus and then switching to one of the cheap models for execution.

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

#52

Post by hirako2000 »

cmaster11 wrote: post #25
postalcoder wrote: post #14

I had used Claude Code max as my daily driver last year and this sort of drama was par for the course. It's why I migrated entirely to Codex, despite liking Claude, the harness, more. There's this honeymoon period with Claude you experience for a month or two followed by a trough of disillusionment, and then a rebound after a model update (rinse and repeat). It doesn't help that Anthropic is experiencing a vicious co…

I've been using Code for half a year, these past couple weeks have been a totally different experience I'm on max 20, and seeing my weekly quota going bust in ~3 days is a bit absurd when nothing has significantly changed in the way I work

I refuse to use anthropic's models (and openai, gemini) because the math simply doesn't add up.

To add the fact we are being taken for fools with dramatic announcements, FOMOs messages. I even suspect some reaction farms are going on to boost post from people boasting Claude models.

These don't happen for codex. Nor for mistral. Nor for deepseek. It can't just be that Claude code is so much better.

There are open weight models that work perfectly fine for most cases, at a fraction of the cost. Why are more people not talking about those. Manipulation.

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

#53

Post by gessha »

zkmon wrote: post #24

Unless the agent code is open-sourced, there is hardly any transparency in how the agent is spending your tokens and how does it calculate the tokens. It's like asking your lawyer why they charged some amount.

Lawyers can give you a breakdown by the minute in some cases. A better example can be military contracting.

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

#54

Post by zozbot234 »

chandureddyvari wrote: post #40

Claude has gotten noticeably worse for me too. It goes into long exploration loops for 5+ minutes even when I point it to the exact files to inspect. Then 30 minutes later I hit session limits. Three sessions like that in a day, and suddenly 25% of the weekly limit is gone. I ended up buying the $100 Codex plan. So far it has been much more generous with usage and more accurate than Claude for the kind of work I do.…

> It goes into long exploration loops for 5+ minutes even when I point it to the exact files to inspect.

Give it a custom sandbox and context for the work, so it has no opportunity to roam around when not required. AI agentic coding is hugely wasteful of context and tokens in general (compared to generic chat, which is how most people use AI), there's a whole lot of scope for improvement there.

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

#55

Post by 10keane »

this same pattern seems to occur every time a new model is about to release. i didnt notice the usage problem - i am on 20x. but opus 4.6 feels siginificantly dumber for some reason. i cant qualitify it, but it failed on everyday tasks where it used to complete perfectly

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

#56

Post by meetingthrower »

I don't get it. Last week on the 100 bucks plan I generated probably 50k LOC (not a quality measure for sure!) and just barely kissed the weekly limit. I did get rate limited on some sessions for sure, but that's to be expected.

I'm curious what are people doing that is consuming your limits? I can't imagine filling the $200 a month plan unless I was essentially using Claude code itself as the api to mass process stuff? For basic coding what are people doing?

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

#57

Post by stingraycharles »

hrimfaxi wrote: post #10
comandillos wrote: post #5

Quite scared by the fact that the original issue pointing out the actual root cause of the issue has been 'Closed as not planned' by Anthropic. https://github.com/anthropics/claude-code/issues/46829

The response doesn't even make sense and appears to be written by AI. > The March 6 change makes Claude Code cheaper, not more expensive. 1h TTL for every request could cost more, not less Feels very AI. > Restore 1h as the default / expose as configurable? 1h everywhere would increase total cost given the request mix, so we're not planning a global toggle. They won't show a toggle because it will increase costs for…

Sounds like a decision I would make when memory is expensive and you want to get rid of the very long (in time) tail of waiting 1h to evict cache when a session has stopped.

There must be a better way to do this. The consumer option is the pricing difference. If they’d make cache writes the same price as regular writes, that would solve the whole problem. If you really want to push it, use that pricing only for requests where number of cache hits > 0 (to avoid people setting this flag without intent to use it), and you solved the whole issue.

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

#58

Post by mr_mitm »

rvz wrote: post #44

Why so many 'developers' complaining about Claude rate limiting them? You know you can actually....use local LLMs? instead of donating your money to Anthropic's casino? I guess this is fitting when the person who submitted the issue is in "AI | Crypto". Well there's no crying at the casino when, you exhaust your usage or token limit. The house (Anthropic) always wins.

Local LLMs are nowhere near as powerful as commercial models. Plus, they have hefty hardware requirements.

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

#59

Post by onlyrealcuzzo »

chandureddyvari wrote: post #40

Claude has gotten noticeably worse for me too. It goes into long exploration loops for 5+ minutes even when I point it to the exact files to inspect. Then 30 minutes later I hit session limits. Three sessions like that in a day, and suddenly 25% of the weekly limit is gone. I ended up buying the $100 Codex plan. So far it has been much more generous with usage and more accurate than Claude for the kind of work I do.…

> Claude has gotten noticeably worse for me too.

My experience is limited only to CC, Gemini-cli, and Codex - not Aider yet, trying different combinations of different models.

But, from my experience, CC puts everything else to shame.

How does Cursor compare? Has anyone found an Aider combination that works as well?

Post reply on HN