Claude Code users hitting usage limits 'way faster than expected'
1–10 of 245 posts
Re: Claude Code users hitting usage limits 'way faster than expected'
#2Yesterday (pro plan) I ran one small conversation in which Claude did one set of three web searches, a very small conversation with no web search, and I added a single prompt to an existing long conversation. I was shocked to see after the last prompt that I had somehow hit my limit until 5:00pm. This account is not connected to an IDE or Code, super confusing.
Re: Claude Code users hitting usage limits 'way faster than expected'
#3Yesterday (pro plan) I ran one small conversation in which Claude did one set of three web searches, a very small conversation with no web search, and I added a single prompt to an existing long conversation. I was shocked to see after the last prompt that I had somehow hit my limit until 5:00pm. This account is not connected to an IDE or Code, super confusing.
Tool calls (particularly fetching for context) eats the context window heavily. I explicitly send MCP calls to sub agents because they are so “wordy”.
Re: Claude Code users hitting usage limits 'way faster than expected'
#4I cancelled my pro plan last month. I was using Claude as my daily driver. In fact had the API plan also and topped it with $20 more. So it was around $40 each month. Starting from December last year it has been like this. When sessions could last a couple of hours with some deep boilerplate and db queries etc. to architecture discussion and tool selection. Slowly the last two months it just gets over. One prompt and few discussions as to why this and not that and it is done.
Re: Claude Code users hitting usage limits 'way faster than expected'
#5Yesterday (pro plan) I ran one small conversation in which Claude did one set of three web searches, a very small conversation with no web search, and I added a single prompt to an existing long conversation. I was shocked to see after the last prompt that I had somehow hit my limit until 5:00pm. This account is not connected to an IDE or Code, super confusing.
Tool calls (particularly fetching for context) eats the context window heavily. I explicitly send MCP calls to sub agents because they are so “wordy”.
Everyone who has not hit this bug thinks it’s user error… It’s not. It happened to me a few days ago, and the speed at which I tore through my 5 hour usage cap was easily 10x faster than normal.
Also: sub agents do not get you free usage. They just protect your main context window.
Re: Claude Code users hitting usage limits 'way faster than expected'
#6Earlier quoted context omitted.
Tool calls (particularly fetching for context) eats the context window heavily. I explicitly send MCP calls to sub agents because they are so “wordy”.
Everyone who has not hit this bug thinks it’s user error… It’s not. It happened to me a few days ago, and the speed at which I tore through my 5 hour usage cap was easily 10x faster than normal. Also: sub agents do not get you free usage. They just protect your main context window.
Don't they consume less of the token quota in case the subagents are running cheaper models like Sonnet and Haiku compared to Opus?
Re: Claude Code users hitting usage limits 'way faster than expected'
#7[dead]
Re: Claude Code users hitting usage limits 'way faster than expected'
#8I'm guessing their newer models are taking way more compute than they can afford to give away. The biggest challenge of AI will eventually be, how to bring down how much compute a powerful model takes. I hope Claude puts more emphasis into making Haiku and Sonnet better, when I use them via JetBrains AI it feels like only Opus is good enough, for whatever odd reason.
Re: Claude Code users hitting usage limits 'way faster than expected'
#9When asking it to write a http library which can decode/parse/encode all three versions of it the usage limit of the day gets hit with one sentence. In the pro plan. Even when you hand it a library which does hpack/huffmann.
Re: Claude Code users hitting usage limits 'way faster than expected'
#10please tell me if i'm crazy.
i just refuse to use openai/google/anthropic subscriptions, i only use open source models with ZDR tokens.
- i like privacy in my work, and i share when i wish. somehow we accepted that our prompts and work may be read and moderated by employees. would you accept people moderating what you write in excel, google docs, apple pages?
- i want a consistent tool, not something that is quantised one day, slow one day, a different harness one day, stops randomly.
- unless i am missing something, the closed source models are too slow for me to watch what they are doing. i feel comfortable with monitoring something, usually at about 200-300tps on GLM 5. above that it might even be too fast!