Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
GLM-5.3-FlashX: Delivering inference speeds of 200 tokens/s
(
z.ai
)
5 points
by
theanonymousone
44 days ago
|
hide
|
past
|
favorite
|
1 comment
esafak
41 days ago
[–]
5x the price of 5.3 flash and the measured speed is only 75tk/s, whereas 5.3 flash measures 40tk/s. So it's either too slow or too expensive.
https://openrouter.ai/z-ai/glm-5.3-flash
https://openrouter.ai/z-ai/glm-5.3-flashx
Consider applying for YC's Winter 2027 batch!
Applications
are open till November 2.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
https://openrouter.ai/z-ai/glm-5.3-flash
https://openrouter.ai/z-ai/glm-5.3-flashx