News for hackers. Stuff that matters.

A comment on Command A: Max performance, minimal compute – 256k context window.

Re:Command A: Max performance, minimal compute – 256k contex... by casey2 on Monday March 17, 2025 @02:16PM (#43391242)
LLM pricing makes no sense. Why pay the same rate for tokens that are in/out of the context window when that's 99% of performance.

Now the burden is on the user to somehow guess or reverse-engineer the internals of your model

[ Parent | on HN ]

There are no comments on this comment yet.