Claude Code adjusting down 5hr limits

Yeah this is a bit crazy and not surprising at all.

The limits have always been opaque and you never know when they change.

I started building an open-source local proxy that logs every rate-limit header Claude Code sends.

I am using it to track and get a better sense of the 5h and 7d weekly limits.

Some initial data from 11 observed 5h sessions on Max 20x: - 5h budget: roughly $120–$280 per window - 7d budget: roughly $1,300–$1,900 - Separate Sonnet-only 7d budget at ~$150 - 95% of tokens are cache reads. They barely move the meter.

It’s open source so more people can run it and we can figure out the real numbers.

https://github.com/abhishekray07/claude-meter

This morning I hit 100% 5hr usage on a task that took ~10% in the past. Looks like they are still testing the limits, but it seems over-tuned to me.

Also not great that they communicate this now, since people have been complaining about sudden and strange usage spikes for a few days with no response from Anthropic.

And they don't announce it through any official communications but hope it gets buried on Twitter.

One of the shadiest things I've seen is how openai treats their weekly limit. They reset it whenever they want! So if you use 25% but then it's day 3 or day 4 of the week, you've used less than the pro-rata, they'll just reset the limit.

Makes me incandescent that OpenAI would have these different rate limits that apply to you, but they can do whatever they want with your limit. It's just incredibly hostile treatment & incredibly incredibly rude.

Similar to what google recently pulled with Antigravity limits.

I guess we may be on the cusp of seeing how much AI usage is really going to cost us when demand goes up and the subsidies disappear.

Is this legal for Anthropic to do? The whole thing screams fraud / rug pull.

Next up:

Spend 1.99 and get a chest full of Anthropic emeralds, that you can redemem for Claude Chests, and a chance at winning a million more tokens.

Or watch this 3 minute ad, for 1000 tokens.

I did not think this day would come this soon, but I assure you that anthropic has no moat.

Like electric cars. It's nice to charge it in summer 2013 when you're the only one on supercharger, and pain waiting in a pissing queue of 10 cars right now

Running out of compute and the subscriptions are not covering the costs.

I keep saying it because it’s true: I do an insane amount of work with my little $20/mo. ChatGPT Plus subscription and never hit limits. For me Claude (especially Opus) is not built for real work, no matter how good the model may be, because the limits are comically prohibitive. Which is a shame because I love their models, but their shadiness around usage is bad business.

Also, these “peak hours” are different from the “2x outside peak hours” hours.

Super shady and opaque. And this is just the start of the enshittification slope…