d3Xt3r | Hacker News

Comment by d3Xt3r | original | ZCode – Harness for GLM-5.2

[−]d3Xt3r · 2026-07-01 Wed 20:09 UTC · link

   For GLM Coding Plan subscribers, quota consumed via Coding Plan for GLM-5.2 in ZCode is discounted by the coefficients below — the same usage draws down less quota, roughly 1.5x the effective allowance.
   
   Peak hours (14:00–18:00 daily)  3x -> 2x
   Off-peak (remaining 20 hours)   1x -> 0.67x

I wonder whether that is referring to local time, or CST (UTC+8)?

[−]qaz_plm · 2026-07-01 Wed 20:46 UTC · link

Peak hours are 14:00–18:00 (UTC+8)

https://docs.z.ai/devpack/overview

[−]d3Xt3r · 2026-07-01 Wed 20:56 UTC · link

Thanks. Those are some odd hours though, why would evening time be peak hours? Usually (in the western world anyway), 9AM - 12PM would be peak hours. Things normally slow down post-lunch, and be its slowest at close-of-business.

[−]TurdF3rguson · 2026-07-01 Wed 21:01 UTC · link

Because westerners are using it is my guess and for them that's right in your window

[−]VulgarExigency · 2026-07-01 Wed 22:19 UTC · link

They're peak hours in Beijing

[−]kgeist · 2026-07-02 Thu 00:25 UTC · link

I run a corporate AI server and coding peak hours here are 1PM-5PM judging by AI usage stats. My guess is that people spend 9AM-12PM in meetings and at lunch, and the actual coding starts around 1 PM.

[−]dadoum · 2026-07-01 Wed 20:49 UTC · link

From https://z.ai/subscribe#code-plans-container:

> Explanation and Recommendations Regarding Usage for Plan-Supported Models

> Note: Peak hours are from 14:00 to 18:00 daily (UTC+8).