Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
mritchie712
50 days ago
|
parent
|
context
|
favorite
| on:
Grok 4.3
for reference, it's the 2nd fastest model tracked in the "Highlights" section of
https://artificialanalysis.ai/
Cakez0r
50 days ago
|
next
[–]
Yes, it's incredibly fast. Openrouter is clocking 60 tokens per second, which is on par with the likes of sonnet, opus, GPT 5.5.
goldenarm
50 days ago
|
prev
[–]
That section misses Cerebras and Groq which are up to 5x faster.
Havoc
50 days ago
|
parent
[–]
Very different tech and limitations though so wouldn’t make sense to compare 1:1 I think
goldenarm
50 days ago
|
root
|
parent
[–]
What are the limitations ?
gslepak
50 days ago
|
root
|
parent
[–]
Much smaller context
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
