logoalt Hacker News

agentdev001 • yesterday at 3:10 AM • 1 reply • view on HN

Note that, being that this is gpt-6-luna under the hood, this offers you 1m token input window, and multi-modal (image) input. In my testing so far, I'm seeing 160-175ms end to end. Worst 5% 285ms, worst so far was 743ms.


Replies

copperx • yesterday at 4:36 AM

Image input? Wait a second; so this can be used for image classification without any kind of training at those speeds?

➕ show 1 reply