I pay for the lowest plan. I used to struggle to hit my quota.
Now a single question consistently uses around 15% of my quota
Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
11–20 of 695 posts
Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
#12Bubble's bursting, get in.
Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
#13For whoever else is having the same problems, worth voting these kind of issues. There needs to be more transparency over what goes on with our subscriptions.
We vote here on HN and it's much more effective. Anyone from Anthropic reading conversations on HN like this one can be scared. We'll jump ship if they don't address such glaring issues.
Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
#14I had used Claude Code max as my daily driver last year and this sort of drama was par for the course. It's why I migrated entirely to Codex, despite liking Claude, the harness, more.
There's this honeymoon period with Claude you experience for a month or two followed by a trough of disillusionment, and then a rebound after a model update (rinse and repeat). It doesn't help that Anthropic is experiencing a vicious compute famine atm.
Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
#15so basically the anthropic employee who responded says those 1h caches were writes were almost never accessed, so a silent 5m cache change is for our best interest and saves cost. (justifying why they did this silently)
however his response gaslights us because in the OPs opening post his math demonstrates this is not true, it shows reads 26x more so at least in his case the cache is not doing what the anthropic employee describes.
clearly we are being charged for less optimization here and being given the message (from my perspective by anthropic) that if you are in a special situation your needs don't matter and we will close your thread without really listening.
Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
#16That’s why I switched to Codex. It’s so much more generous and in my experience, just as good. Also, optimizing your setup for working with agents can easily make a 5x difference.
Plus, whenever Codex does something you dislike, you can just tell Codex to fix itself. Open source software is wonderful.
Especially when it's on purpose.
Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
#17That’s why I switched to Codex. It’s so much more generous and in my experience, just as good. Also, optimizing your setup for working with agents can easily make a 5x difference.
> Also, optimizing your setup for working with agents can easily make a 5x difference.
Any highlights you can share here? I'm always looking to improve me setup.
Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
#18GPT-5.4 works amazingly well. I’ve moved away from Claude and toward open-source models plus a ChatGPT subscription. That setup has worked really well for me: the subscription is generous, the API is flexible, and it fits nicely into my workflow. GPT-5.4 + Swival ( https://swival.dev ) are now my daily drivers.
Yeah it's much better, another plus is you can use it with OpenCode (or other 3rd party tools) so you can easily switch between Codex and most other models by alright companies (not Anthropic or Google).
Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
#19Been experiencing similar issues even with the lower tier models. Fair transactions involve fair and transparent measurements of goods exchanged. I'm going to cancel my subscription this month.
Yes: Claude Code “consumes tokens” and starts a session when the computer is asleep without anything started. Or consumes 10% of my session for “What time is it?”
Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
#20I had used Claude Code max as my daily driver last year and this sort of drama was par for the course. It's why I migrated entirely to Codex, despite liking Claude, the harness, more. There's this honeymoon period with Claude you experience for a month or two followed by a trough of disillusionment, and then a rebound after a model update (rinse and repeat). It doesn't help that Anthropic is experiencing a vicious co…
I like the term "compute famine" - it appears that all AI infrastructure is maxed out globally.