What's your reasoning effort set to? Max now uses way more tokens and isn't suggested for most usecases. Even the new default (xhigh) uses more than the old default (medium).

That's what I'm wondering. Is it people are defaulting to xhigh now and that's why it feels like it's consuming a lot more tokens? If people manually set it to medium, would it be comparable?

Switching back to medium seems to have fixed the issue for me.

Which plan are you on? I could see that happening with Pro (which I think defaults to Sonnet?), would be surprised with Max…

Opus is not available for claude code in pro

Yes it is.

https://claude.com/pricing

It's not available on Free plan, but it's available on Pro.

It eats even the Max plan like crazy.

Pro. It even gave me $20 free credits, and exhausted free credits nearly instantly.

The pro plan is useless. You need at least the 5x max plan to get any real work done.

That said I find the GPT plans much better value.

GPT 5.4 in Codex is good enough now.

Try it.

HN is getting ridiculous. You cannot seriously be complaining about Opus token usage on the Pro plan.

Compared to the usage you get on OpenAI's $20 plan tho?

Are you using Claude subscription? Because that's not how it works there.

I haven't used Claude. Because I suspect this sort of things to come.

With enterprise subscription, the bill gets bigger but it's not like VP can easily send a memo to all its staff that a migration is coming.

Individuals may end their subscription, that would appease the DC usage, and turn profits up.

Sorry you are missing out. I use claude all day every day with max and what people are reporting here has not been my experience. My current usage is 16% and it resets Thursday.

Some research argue LLMs (up to 2025) were giving a false sense of higher productivity.

That and atrophy, I will pass on what Claude is trying to accomplish.

I'm not dismissing LLMs entirely, for certain cases the concerns don't apply, at least not as much.