Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Except the latency is significant and not suitable for clients with advanced agent features. The experience between using a frontier model via first party API and the best open weight models via OpenRouter is night and day. Can't get any real work done with it.


Good point. When I use it, the inference doesn't seem very fast compared to the big providers, esp Time to First (non-reasoning)Token.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: