News for hackers. Stuff that matters.
Re:Claude Opus 4.6 by Someone1234 on Thursday February 05, 2026 @03:29PM (#46904759)
Specifically including routing (i.e. which model you route to based on load/ToD)?

PS - I appreciate you coming here and commenting!

Re:Claude Opus 4.6 by hhh on Thursday February 05, 2026 @03:32PM (#46904798)
There is no routing with API, or when you choose a specific model in chatGPT.
Re:Claude Opus 4.6 by zwaps on Friday February 06, 2026 @01:09AM (#46909670)
In the past it seemed there was routing based on context-length. So the model was always the same, but optimized for different lengths. Is this still the case?