> I'm already at 27% of my weekly limit in ONE DAY.

Ouch, that's very different than experience. What effort level? Are you careful to avoid pushing session context use beyond 350k or so (assuming 1m context)?

▲

atonse 5 hours ago | parent | next [-]

Yeah fair point. I have had a couple of conversations (ingesting a pretty complex domain and creating about 42 high fidelity tailwind mockups with ui.sh).

And this particular set of things has context routinely hit 350-450k before I compact.

That's likely what it is? I think this particular work stream is eating a lot of tokens.

Earlier this week (before Open 4.7 hit), I just turned off 1m context and had it grow a lot slower.

I also have it on high all the time. Medium was starting to feel like it was making the occasional bad decisions and also forgetting things more.

▲

JimmaDaRustla 5 hours ago | parent | prev [-]

I'm mind blown people are complaining about token consumption and not communicating what thinking level they're using - if cost is a concern and you're paying any attention, you'd be starting with medium and seeing if you can get better results with less tokens. Every person complaining about token usage seem to have no methodology - probably using max and completely oblivious.

▲

AndyNemmity 5 hours ago | parent [-]

It's unsurprising when this is the first day that tokens have been crazy like this.

All of us doing crazy agentic stuff were fine on max before this. Now with Opus 4.7, we're no longer fine, and troubleshooting, and working through options.

▲

JimmaDaRustla 5 hours ago | parent [-]

> were fine on max before this

Ya...you may be who I'm talking about though (if you're speaking from experience). If your methodology is "I used 4.6 max, so I'm going to try 4.7 max" this is fully on you - 4.7 max is not equivalent to 4.6 max, you want 4.7 xhigh.

From their docs:

max: Max effort can deliver performance gains in some use cases, but may show diminishing returns from increased token usage. This setting can also sometimes be prone to overthinking. We recommend testing max effort for intelligence-demanding tasks.

xhigh (new): Extra high effort is the best setting for most coding and agentic use cases.

▲

AndyNemmity 5 hours ago | parent [-]

Sorry, in that case I misunderstood max to mean the subscription, max 20.

I am on xhigh.

▲

JimmaDaRustla 4 hours ago | parent [-]

Ah - xhigh is probably what you want. Their docs suggest xhigh for agentic coding, though judging by their blog high should be better than 4.6 max (ymmv)

I've always used high, so maybe I should be using xhigh

	▲	AndyNemmity 4 hours ago \| parent [-]
		I'm actually in the process of switching all of my agents to sonnet, and going to try to drop down to medium. I used up 1/3rd of my context in less than a day. I am working diligently to do whatever I can to lower token usage.