Hacker News
Favorites
Setup
☰
Home
Favorites
Setup
Comment by MarceloHenry |
original
|
ZCode – Harness for GLM-5.2
[−]
MarceloHenry
· 2026-07-01 Wed 23:05 UTC ·
link
fave
17M tokens... I think it is a lot. What were you working on?
[−]
bearjaws
· 2026-07-01 Wed 23:26 UTC ·
link
fave
Is that 17M output tokens?
At 200k context that is only 85 requests for a whole week.
[−]
davikr
· 2026-07-02 Thu 00:04 UTC ·
link
fave
That's like 30 minutes of MCP usage.
[−]
computerex
· 2026-07-02 Thu 02:47 UTC ·
link
fave
Not really. I have spent 163M deepseek v4 flash tokens in July and it literally just started.
https://i.postimg.cc/MHhgwsv0/image.png
At 200k context that is only 85 requests for a whole week.
https://i.postimg.cc/MHhgwsv0/image.png