>> 100k tokens is an absurdly low cutoff and it is only applicable to Haiku and not Sonnet or Opus. It's a low enough cutoff that it will be quickly exceeded if you are doing anything with Agents

Your vibes don't appear to be supported by facts. From the announcement:

>> Claude Haiku 5.5 is priced 90% lower than Claude Haiku 4.5 for requests up to 100,000 tokens, and 50% lower for requests over 100,000 tokens. On Haiku 4.5, 90% of requests fell into the former category.

▲

Philpax 6 hours ago | parent | next [-]

People weren't using Haiku 4.5 for agents before. 5.5 is good enough that it might be.

	▲	amgutier 2 hours ago \| parent [-]
		[dead]

▲

StilesCrisis 5 hours ago | parent | prev [-]

Haiku 4.5 users were using it for Kleenex requests because that was the best it could do.

▲

enraged_camel 4 hours ago | parent [-]

Not really. We use Haiku 4.5 to turn users' natural language queries and requests into fairly complex structured specs for interior design and construction. It has near perfect accuracy.

	▲	dotancohen 3 hours ago \| parent [-]
		How many examples are in your prompt? How large is that prompt? Or do you have some other way of tuning the output? I'm asking to learn for a similar project, not to discount anything you're saying.