You hit a vague, never-quite-explained 5h window limit that has nothing to do with what you're doing, but with what every user is doing together. It's totally not downtime, you're just "using it too much" and they're telling you to fuck off until the overall usage slows down.

The order of priority is: everyone using the API (you don't want to calculate the price) → everyone on a $200/month plan → everyone on a $20/month plan → every free user.

Yeah it's way too vague.

This morning: (new chat) 42 seconds of thinking, 20 lines of code changed in 4 files = 5% usage

Last night: 25 minutes of thinking, 150 lines of code generated in 10 new files = 7% usage

I think the first message consumes disproportionately much percentage because it's not cached and includes the system prompt, tools, etc.

Here comes the "you're using it wrong" defence!

Let's be perfectly clear: if user actions had anything to do with hitting these limits, the limits would be prominently displayed within the tool itself, you'd be able to watch it change in real time, and you'd be able to pinpoint your usage per each conversation and per each message within that conversation.

The fact that you cannot do that is not because they can't be bothered to add such a feature, but because they want to be able to tweak those numbers on the backend while still having plausible deniability and being able to blame it on the user.

Instead, the little "usage stats" they give you is grouped by the hour and only split between input and output tokens, telling you nothing.

Interesting. What do you think the reason for not being transparent on this matter?

For the same reason they use "tokens" instead of kilobytes: so that you don't do the conversion yourself and realise that for example spending a million "tokens" on claude-opus-4.6 costs you anywhere from $10 (input tokens) to $37.5 (output tokens). Now, 1 million tokens sounds pretty big and "unreachable" until you realise that's about 4 megabytes of text. It's less than three floppy disks of data going back and forth.

Now let's assume you want to send a CD worth of data to Opus 4.6. 700 megabytes * $10 (price per million input tokens) / 4 (rounding down one megabyte to roughly 250k "tokens") = $1750. For Opus 4.6 to return a CD amount of data back to you: $37.50 * 700 / 4 = ~$6.5k.

A terabyte worth of data with a 50:50 input/output ratio would cost you $5.7 million. A terabyte worth of data with a 50:50 input/output ratio on gpt-5.2-pro would cost you $25.2 million. (Note: OpenAI's API pricing still hasn't been updated to reflect 5.3 prices.)

So we get layers upon layers upon layers upon layers upon layers of obfuscation to hide those numbers from you when you simply subscribe for a fixed monthly fee!

Do people care about how many bytes they are sending or receiving?

Most people care about getting the right bytes.

Oh man. Thanks for explaining. That sounds like a dark pattern.

Blurring the cost-benefit analysis in the interest of downplaying the costs.

I definitely noticed that Claude is faster on Central European mornings, e.g. deep night in the US.

you can just watch the limit on the claude usage settings view.

itd be nice to know how much the session context window applies wrt token caching, but disabling all those skills and stopping sending a screenshot every couple messages gets that 5hour limit and weekly limit a bunch better

It hasn't always done this, it's a relatively recent problem in the last 1-4 weeks (roughly). (note: I'm on the $160AUD/mo plan, so I think that's $100USD).

> what are all these people who “barely wrote code anymore” doing?

Writing self-serving LinkedIn productivity porn