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

661–670 of 695 posts

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

#661

Post by railsgirls112 »

mchinen wrote: post #107

I've been feeling the squeeze too. I've tried switching between different models as a test, I can at least say it feels like the limits are about half of what they used to be a few months ago. I'd be totally willing to concede that this is just my perception if Anthropic would only release some tools for measuring your usage. In theory the /stats command tells you how many tokens you've used, which you could use to c…

The only other pricing data available suggests its the context cache that's eating usage. If you have a big context on a 5 min cache (default) you're essentially sending the whole context every time you take a break from the api. You can configure 1 hr TTL which should help if you run long heavy sessions like me. That's been my theory lately. Still need to get my company admin to let me test lol.

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

#662

Post by downrightmike »

1970-01-01 wrote: post #74
geeky4qwerty wrote: post #39

I'm afraid the music may be slowly fading at this party, and the lights will soon be turned on. We may very well look back on the last couple years as the golden era of subsidized GenAI compute. For those not in the Google Gemini/Antigravity sphere, over the last month or so that community has been experiencing nothing short of contempt from Google when attempting to address an apparent bait and switch on quota expec…

Lights on = Ads in your output. EOY latest; they can't keep kicking the massive costs down the road.

Pouring 99% of your funds into massive datacenters you can't actually build and ignore product seems short sighted.

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

#663

Post by maerF0x0 »

Jensson wrote: post #303
maerF0x0 wrote: post #255

Earlier quoted context omitted.

And you think companies aren't doing the same back to us? Are you sure you're speaking to a human?

Its your claude speaking to their claude, which is fair, but it makes this whole discussion a bit dumb since we are basically talking about two bots arguing with each other.

This was part of Sam Altman's (supposed) concerns about AI not being open and equally available. It a dystopian future it might be their cluster of 1000 agents using a GWhr of power to argue against your open weights agent who has to run on a M5.

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

#664

Post by je42 »

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…

Does this 60min ttl of also apply to claude code web?

I have regularly sessions open for multiple days.

Is that a pattern that is not advised?

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

#665

Post by caminante »

bachmeier wrote: post #410
caminante wrote: post #196

Earlier quoted context omitted.

Great point. The parent's argument is that the marginal cost of inference is minimal. However, the fundamental flaw is that he's separating inference from the high cost frontier models. It's a cross-subsidy that can't be ignored.

Without any insider knowledge on the economics of these companies, I suspect it's that the amount of infrastructure you have to build is determined by peak usage rather than average usage. If peak usage is much higher for a small part of one day a week (say on Monday morning as software developers across the US get back to work) the cost of fulfilling demand at all times can be insane. That's why companies are implem…

Check out this article from today [0].

It sounds like it's more of a profit maximization function (and not just demand) with GPU rental prices increasing 48% since Feb.

> Renting one of Nvidia’s most-advanced Blackwell generation of chips for one hour costs $4.08, up 48% from the $2.75 it cost two months ago, according to the Ornn Compute Price Index.

[0] https://www.wsj.com/tech/ai/ai-is-using-so-much-energy-that-...

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

#666

Post by embedding-shape »

ajma wrote: post #474
stevenae wrote: post #440

Earlier quoted context omitted.

The quantitative ux research team at Google was created for exactly this problem: a service which became popular before the right metrics existed, meaning metrics need to be derived first, then optimized. We would observe users (irl), read their logs, then generate experiments to improve the behavior as measured by logs, and return to see if the experiment improves irl experiences. There were not many of us and we ar…

I worked with Boris in the past and in my experience, Boris cares deeply about the customer. I'd vouch that Boris really cares about the issue people are running into.

But no other user has yet come and said "I worked with ajma in the past ..." so how can we trust your judgement about Boris?

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

#667

Post by saltcured »

TheLegace wrote: post #650
stevenae wrote: post #440

Earlier quoted context omitted.

The quantitative ux research team at Google was created for exactly this problem: a service which became popular before the right metrics existed, meaning metrics need to be derived first, then optimized. We would observe users (irl), read their logs, then generate experiments to improve the behavior as measured by logs, and return to see if the experiment improves irl experiences. There were not many of us and we ar…

Metrics and quantitative ux results in really bad software, making it rigid while optimizing for the wrong things. The most obvious example is Google creating multiple steps for Login where you have to enter your password after you put in your user. I wonder what metric lead to that decision or was it a political decision to make it seem like their "old" software has some new feature.

If you mean Google website login, that step is needed because the email address is used to determine which identity provider to use. E.g. I have three different accounts that branch off from that same initial login flow.

One is my person "gmail.com" account, and the other two go through enteprise identity providers related to my employment and their G-Suite licenses. So after I put in one of these three email addresses, I get prompted for the appropriate next step. Only one of them involves giving a password to a Google server. The other two are redirects to completely separate login systems operated by my employer.

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

#669

Post by einsteinx2 »

SparkyMcUnicorn wrote: post #395
ac29 wrote: post #294

Earlier quoted context omitted.

1M context window is still a separate, non-default model in Claude Code and not included with subscriptions (billed at API rates only)

Opus[1m] has heen the default model for max subscriptions since 2.1.75. https://github.com/anthropics/claude-code/commit/48b1c6c0ba0...

It depends on your account and seems to be random.

On my personal Max 5x account it’s not default and if I force it, it says I’ll pay API rates past 200k. On my other account that I use for work (not an enterprise account just another regular Max 5x account) the 1M model has been the default since that rollout. I’ve tried updating and reinstalling etc, and I can’t ever get the 1M default model on my personal account.

Based on other comments and discussion online as well as Claude code repo issues, it seems I’m not the only one not getting the 1M model for whatever reason and the issue continues to be unresolved.

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

#670

Post by einsteinx2 »

byzantinegene wrote: post #548
willio58 wrote: post #538

Earlier quoted context omitted.

Agreed, and the answer is pretty obvious as to how they start making profit. The answer is in this thread, CRANKING the cost up immensely once they establish agreements between the duopoly leaders in the field to do so in tandem and buy up any competition that seeks to challenge them. I’m thinking 20x what the cost is now is where they’ll land. It’ll be a massive line item for software dev shops.

the problem now is how much can they hike the costs without people just going back to coding by hand.

Or switch to using the way cheaper open weight models from various providers who don’t have to subsidize training costs so can just race to the bottom on inference pricing…

The quality isn’t really SOTA yet but at some point I assume they’ll be good enough (maybe already are?).

Post reply on HN