Hacker News

Favorites Setup
Comment by fcarraldo | original | ZCode – Harness for GLM-5.2
[−]fcarraldo · 2026-07-01 Wed 21:00 UTC · link
Does a mid-session provider switch result in loading the entire context into the new model, inflating session cost?

I don't think I understand the token/cost implications of this feature

[−]gunalx · 2026-07-01 Wed 22:12 UTC · link
Its nice if you used local, but needed å beefier modell, or more context Window. It will eat input tokens, but you do that all the time unless you have input caching.
[−]resonious · 2026-07-02 Thu 04:29 UTC · link
Yes you pay a big burst right after switching. After that, everything is cached and it's smooth sailing.