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

Claude Code weekly rate limits

news.ycombinator.com

Post reply on HN
Print view View original

381–390 of 724 posts

Re: Claude Code weekly rate limits

#381

Post by tqwhite »

CodeBrad wrote: post #179
Jcampuzano2 wrote: post #171

Earlier quoted context omitted.

My opinion is all of these tools should completely get rid of the "pay 20/month, 200/month", etc just to get access to some beholden rate limited amount that becomes hard to track. Mask off completely and just make it completely usage based for everyone. You could do something for trial users like first 20 (pick your number here) requests are free if you really need to in order to get people on board. Or you could do…

I think Claude Code also already has the option to provide an API key directly for usage based pricing. I'm a fan of having both a subscription and a usage based plan available. The subscription is effectively a built in spending limit. If I regularly hit it and need more value, I can switch to an API key for unlimited usage. The downside is you are potentially paying for something you don't use, but that is the same…

I use API but think about getting the $100/mo plan and using API for overflow if it occurs.

But I have slow months and think that might not actually be the winner. Basically I'm going to wait and see before I sign up for auto-pay.

Re: Claude Code weekly rate limits

#383

Post by gardnr »

knowsuchagency wrote: post #187

One feature I would love to have is the ability to switch the model used for a message using a shorthand like #sonnet. Often, I don't want or need opus but I don't want to engage in a 3 step process where I need to: 1. switch models using /model 2. message 3. switch back to opus using /model Help me help you (manage usage) by allowing me to submit something like "let's commit and push our changes to github #sonnet".…

That would be great! I want to plan and analyze with opus but happy to use sonnet for code gen. Sonnet is faster and just as good at codegen. Opus is better at planning a change.

Re: Claude Code weekly rate limits

#384

Post by volleygman180 »

jimbo808 wrote: post #22

I'm not sure how this will play out long term, but I really am not a fan of having to feel like I'm using a limited resource whenever I use an LLM. People like unlimited plans, we are used to them for internet, text messaging, etc. The current pricing models just feel bad.

Agreed. The internet would be livid if Apple Music or Hulu limited how many hours you were allowed to stream per week. Especially the users who pay for the top-tier packages that include 4K (or lossless for music), extra channel add-ons, etc.

Re: Claude Code weekly rate limits

#385

Post by geor9e »

>affecting less than 5% of users

Notice they didn't say 5% of Max users. Or 5% of paid users. To take it to the extreme - if the free:paid:max ratio were 400:20:1 then 5% of users would mean 100% of a tier. I can't tell what they're saying.

Re: Claude Code weekly rate limits

#386

Post by bravesoul2 »

jjcm wrote: post #14

They need metered billing for their plans. All AI companies are hitting the same thing and dealing with the same play - they don't want users to think about cost when they're prompting, so they offer high cost flat fee plans. The reality is though there will always be a cohort of absolute power users who will push the limits of those flat fee plans to the logical extremes. Startups like Terragon are specifically engi…

It's 1990s shared hosting again!

Re: Claude Code weekly rate limits

#387

Post by oc1 »

el_benhameen wrote: post #128
Wowfunhappy wrote: post #88

I'm probably not going to hit the weekly limit, but it makes me nervous that the limit is weekly as opposed to every 36 hours or something. If I do hit the limit, that's it for the entire week —a long time to be without a tool I've grown accustomed to! I feel like someone is going to reply that I'm too reliant on Claude or something. Maybe that's true, but I'd feel the same about the prospect of loosing ripgrep for a…

This is how I feel about the 100 msg/wk limit on o3 for the ChatGPT plus plan. There’s no way to see how much I’ve used, and it’s an important enough resource that my lizard brain wants to hoard it. The result is that I way underutilize my plan and go for one of the o4-mini models instead. I would much prefer a lower daily limit, but maybe the underutilization is the point of the weekly limit. *edited to change “pro”…

They know this psychology. This dark pattern is intentional so you will use their costly service less.

Re: Claude Code weekly rate limits

#388

Post by pxc »

Could this be in part because many of the recent Chinese models (which seem great, tbh) show signs of having been distilled from one or another Claude models?

Or is that a silly idea, because distillation is unlikely to be stopped by rate limits (i.e., if distillation is a worthwhile tactic, companies that want to distill from Anthropic models will gladly spend a lot more money to do it, use many, many accounts to generate syntheitc data, etc.)?

Re: Claude Code weekly rate limits

#389

Post by bravesoul2 »

QuadmasterXLII wrote: post #340

Their business model with the pro plan is to sell a dollar for 80 cents for a while to gain market share. Once they have spent the money allocated to this plan and bring it to a close, don’t expect them to resume it in response to righteous indignation: the money will be gone. See also Uber, MoviePass etc

That elusive free lunch.

Re: Claude Code weekly rate limits

#390

Post by belter »

TeMPOraL wrote: post #165
belter wrote: post #87

Earlier quoted context omitted.

The real bottleneck isn’t Jevons paradox, it’s the Theory of Constraints. A human brain runs on under 20 W, yet every major LLM vendor is burning cash and running up against power supply limits. If anything pops this bubble, it won’t be ethics panels or model tweaks but subscription prices finally reflecting those electricity bills. At that point, companies might rediscover the ROI of good old meat based AI.

Where is this oft-repeated idea coming from? Inference isn't that expensive.

My back of envelope estimate, is that even a partly restricted plan, would need to cost roughly $4,000–$4,500 per month just to break even.
Post reply on HN