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

151–160 of 724 posts

Re: Claude Code weekly rate limits

#151

Post by pakitan »

thorum wrote: post #68
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.

The long term is unlimited access to local LLMs that are better than 2025’s best cloud models and good enough for 99% of your needs, and limited access to cloud models for when you need to bring more intelligence to bear on a problem. LLMs will become more efficient, GPUs, memory and storage will continue to become cheaper and more commonplace. We’re just in the awkward early days where things are still being figured…

I'm often using LLMs for stuff that requires recent data. No way I'm running a web crawler in addition to my local LLM. For coding it could theoretically work as you don't always need latest and greatest but would still make me anxious.

Re: Claude Code weekly rate limits

#152

Post by hkt »

belter wrote: post #87
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.

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.

I suspect for this reason we are going to see a lot of attempts at applied AI: I saw an article semi-recently about an AI weather forecasting model using considerably less power than it's algorithmic predecessor, for instance. The answer is, as ever, to climb the value chain and make every penny (and joule) count.

Re: Claude Code weekly rate limits

#154

Post by cpursley »

flashgordon wrote: post #99
colonCapitalDee wrote: post #96

Earlier quoted context omitted.

You should consider self-hosting in the cloud. When you start coding run a script that spins up a new VM and loads the LLM of your choice, then run another script to spin it back down when you're done. For intermittent use this works great and is much cheaper than buying your own hardware, plus it's future proof. It does admittedly lack the cool factor of truly running locally though.

Yeah this is the setup I am thinking for now as it is all the "Freedom" with only hardware dependence. Wierdly enough I noticed Qwen3 (coder) was also almost same price as opus 4 which was wierd.

Qwen pricing on fireworks.ai is pretty good

Re: Claude Code weekly rate limits

#155

Post by steveklabnik »

bravura wrote: post #144
steveklabnik wrote: post #100

Earlier quoted context omitted.

npx ccusage@latest I'm assuming it'll get updated to include these windows as well. Pass in "blocks --live" to get a live dashboard!

Does ccusage (or claude code with subscription) actually tell you what the limits are or how close you are too them?

https://ccusage.com/guide/live-monitoring

See that screenshot. It certainly shows you when your 5 hour session is set to refresh, in my understanding it also attempts to show you how you're doing with other limits via projection.

Re: Claude Code weekly rate limits

#156

Post by tialaramex »

cmsjustin wrote: post #115
rmujica wrote: post #108

Earlier quoted context omitted.

Internet and SMS used to be expensive and metered until they weren't thanks to technological advances and expanded use. I think LLMs will follow the same path, maybe on a shorter timespan.

They were not expensive to operate, they were only expensive for consumers

Right, that's crucial to understand. In 1985 you could make a direct dial from England to the US but it was eye wateringly expensive. £2 per minute. An hour's call to your mum? That's over £100.

But the cost to Bell and British Telecom was not £2 per minute, or £1 per minute, or even 1p per minute, it was nothing at all. Their costs were not for the call, but for the infrastructure over which the call was delivered, a transatlantic cable. If there was one call for ten minutes, once a week essentially at random, that cable must still exist, but if there are 10 thousand call minutes per week, a thousand times more, it's the same cable.

So the big telcos all just picked a number and understood it as basically free income. If everybody agrees this call costs £2 then it costs £2 right, and those 10 thousand call minutes generate a Million pound annual income.

It's maybe easier for Americans to understand if you tell them that outside the US the local telephone calls cost money back then. Why were your calls free? Because why not, the decision to charge for the calls is arbitrary, the calls don't actually cost anything, but you will need to charge somehow to recoup the maintenance costs. In the US the long distance calls were more expensive to make up for this for a time, today it's all absorbed in a monthly access fee on most plans.

Re: Claude Code weekly rate limits

#157

Post by Dylan16807 »

ohdeargodno wrote: post #117
serial_dev wrote: post #33

Earlier quoted context omitted.

All of these AI services tell everyone how amazing AI is, it can run things, solve things on its own, while the developers are drinking coffee or sleeping. Some developers could actually do that with the service they paid for, fully in agreement with the terms and now it is their fault?

"they paid for" $100 doesn't even cover the electricity of running the servers every night, they were abusing a service and now everyone suffers because of them.

Any good numbers on what it costs? I can look up how many watts a GPU needs but I don't know how the batching is typically done to understand how many users are sharing those watts.

But a compute-focused datacenter is probably not paying more than 10 cents per kWh, so $100 would pay for more than a 24/7 kilowatt of GPU plus cooling plus other overhead.

Re: Claude Code weekly rate limits

#158

Post by wrs »

furyofantares wrote: post #74
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.

The Sonnet usage does not really look limited at 240-480 hours per week (a week has 168 hours in it). Opus at 24-40 looks pretty good too. A little hard to believe they aren't losing a bunch of money still if you're using those limits tbh.

You can run multiple instances of Claude Code at the same time.

Re: Claude Code weekly rate limits

#160

Post by jstummbillig »

serial_dev wrote: post #61
jstummbillig wrote: post #15

Earlier quoted context omitted.

This seems to be the exact opposite?

The writing is on the wall, we just need to read it. Fixed price offerings will be either gone or neutered.

Why? There are a lot of products where fixed price offerings can exist, like internet access in many parts of the world. The way that Anthropic implemented this change and how they explain it, hints that this could work very much the same: There is be a level of borderline abusers that need to be reigned in. The rest are a few power users that are subsidized by a lot of normal users.

I am not saying this is what must happen here, but I see no effort to substantiate why it could not.

Post reply on HN