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

601–610 of 724 posts

Re: Claude Code weekly rate limits

#601

Post by closewith »

Wowfunhappy wrote: post #509
aspenmayer wrote: post #454

Earlier quoted context omitted.

> prevent people from gaming the system If I sit down for dinner at an all-you-can-eat buffet, I get to decide how much I’m having for dinner. I don’t mind if they don’t let me take leftovers, as it is already understood that they mean as much as I can eat in one sitting. If they don’t want folks to take advantage of an advertised offer, then they should change their sales pitch. It’s explicitly not gaming any system…

I feel like using Claude Code overnight while you sleep or sharing your account with someone else is equivalent to taking home leftovers from an all-you-can-eat buffet. I also find it hard to believe 5% of customers are doing that, though.

I use Claude Code with Opus four days a week for about 5 hours a day. I've only once hit the limit. Yet the tool others mentioned here (ccusage) indicates I used about $120 in API equivalents per day or about $1,800 to date this month on a $200 subscription. That has to be a loss leader for Anthropic that they now want to wind back.

I also wouldn't consider my usage extreme. I never use more than one instance, don't run overnight, etc.

Re: Claude Code weekly rate limits

#602

Post by dust42 »

gedy wrote: post #43
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.

I get it, and feel the same way but the current LLMs are very resource intensive. To the point that I'm reluctant to go all in on these tools if in future we get rug-pulled once companies admit "okay, this was not sustainable at that price.."

I am really afraid of this as well. When using one of the plugins for vscode, I would easily use a few million tokens a day. Thus with Claude Code I assume it isn't much different under the hood. The prices on openrouter are roughly $5/M for the better models. Therefore paying $20/month can't be sustainable.

Once enough developers are addicted to AI assisted coding the VCs will inevitably pull the rug.

I wonder if Alibaba will put out a 100B A10B coder model which could probably run for $0.5/M while giving decent output. That would be easily affordable for most developers/companies.

Re: Claude Code weekly rate limits

#603

Post by forty »

epolanski wrote: post #586
forty wrote: post #583

Earlier quoted context omitted.

I assume they have an opinion on the topic, but it doesn't mean they are right (or wrong). Think of driving a car. If the shortest path (in term to time of travel) is through traffic jam, and there is a longer path where you can drive must faster, it's very likely that most people will have the feeling to be more efficient with the longer path. Also the slow down of using LLM might be more subtle and harder to measur…

Apologies, but from antirez[1] to many other brilliant 1000x developers advocate for LLMs speeding up the process. I can see the impact on my own input both in quantity and quality (LLMs can come up with ideas I would not come up to, and are very useful for tinkering and quickly testing different solutions). As any tool it is up to the user to make the best out of it and understand the limits. At this point it is cle…

From your source

```

The fundamental requirement for the LLM to be used is: don’t use agents or things like editor with integrated coding agents. You want to:

* Always show things to the most able model, the frontier LLM itself.

* Avoid any RAG that will show only part of the code / context to the LLM. This destroys LLMs performance. You must be in control of what the LLM can see when providing a reply.

* Always be part of the loop by moving code by hand from your terminal to the LLM web interface: this guarantees that you follow every process. You are still the coder, but augmented.

```

Not sure about you, but I think this process, which your source seems to present as a prerequisites to use LLM efficiently (and seems good advice to me too, and actually very similar of how I use LLM myself) must be followed by less than 1% of LLM users.

Re: Claude Code weekly rate limits

#604

Post by virtualritz »

bugglebeetle wrote: post #129
KronisLV wrote: post #81

Earlier quoted context omitted.

I personally take an issue with them expecting that your usage would be more or less consistent throughout the month. Instead, I might have low usage throughout most of the month and then an 11 hour binge a few days, which in most cases would involve running into rate limits (either that, or just token limitations for inputs). That's why using the API directly and paying for tokens anything past that basic usage feel…

Gemini 2.5 Pro is a better coding model, but Gemini CLI is way behind Claude Code, perhaps because the model itself isn’t well-tuned for agentic work. If you’re just doing targeted refactoring and exploration, you can copy and paste back and forth from the web app for $20 a month.

Not if you write Rust. From regularly producing code that has unbalanced braces or quote characters somewhere to destroying well working code. It also easily gets into loops where it can't solve a problem, comes up with a half-working solution A, throws it away, comes up with B, then C, then goes back to A etc.

I run Gemini Pro from within CC but I only use it for analysis and planning for which it is better than Claude (Opus).

I guess if your target language is Python or JS/TS etc., your milage may be considerably better.

For Rust it's simply not true.

Re: Claude Code weekly rate limits

#605

Post by bluelightning2k »

Zacharias030 wrote: post #590
brookst wrote: post #462

Earlier quoted context omitted.

I think the simple product prioritization explanation makes way more sense than a a second-order conspiracy to trick people into hoarding. Reality is probably that there’s a backlog item to implement a view, but it’s hard to prioritize over core features.

I hear OpenAI and Anthropic are making tools that are supposedly pretty good at helping with creating a view from a backlog. Back to the conspiracy ^^

"We were going to implement a counter but hit out weekly Claude code limit before we could do it. Maybe next week? Anthropic."

Re: Claude Code weekly rate limits

#606

Post by mtkd »

pembrook wrote: post #599

These resource constraints create an extremely strong incentive for customers to try all competitors…this is what makes for the best products/services. When there’s no network effects it’s a fight over algorithms and compute and fundraising ability and we actually get real competition instead of natural monopolies. This is the most exciting business fight of our time and I’m chomping popcorn with glee. I think Anthro…

They need to max valuation before hardware catches up and qwen3-coder can be run locally for free

It's easy to forget the product Anthropic are selling here, and throttling, is based on data they mostly pay little or no content fee for

Re: Claude Code weekly rate limits

#607

Post by PeterStuer »

Does this mean they will force heavy users to have multiple accounts rather than being able to extend an account with extra subscriptions?

Who does that benefit? Does number of accounts beat revenue in their investor reports?

Re: Claude Code weekly rate limits

#608

Post by mtkd »

paxys wrote: post #196
flashgordon wrote: post #142

Earlier quoted context omitted.

wow - do you mind sharing any links to a specific setup? Also whats the biggest model anybody has run on this?

You can run a decent model on it, say highly quantized Qwen or Deepseek R1 getting 5-10 tokens/sec output, but it will be nothing in comparison to a commercial offering like Claude, o3 or Gemini. For that you need a datacenter-class GPU going for $50K-100K a pop.

But a small collective running that box, especially spanning timezones, could potentially be a viable alternative or will be soon -- with obv privacy gains too

Re: Claude Code weekly rate limits

#609

Post by vineyardmike »

benoittravers wrote: post #560
vineyardmike wrote: post #267

Earlier quoted context omitted.

Because the goal is to extract more money from the people who have significant usage. These users are the actual targets of the product. The idea that it’s a few bad actors is misdirection of blame to distract “power users”. They undercharged for this product to collect usage data to build better coding agents in the future. It was a ploy for data. Anecdotally, I use Claude Code with the $20/mo subscription. I just u…

What was the name of that CLI tool?

It’s called “ccusage”. Search for other comments on this story for more details.

Re: Claude Code weekly rate limits

#610

Post by andxor »

forty wrote: post #559
aprdm wrote: post #499

Earlier quoted context omitted.

backend web services devops frontend javascript just three possible examples

Yes. Web is more and more debatable as as time goes though, there is more and more only one company providing the software to access the web :)

And it's open source.
Post reply on HN