But they literally advertise it on the Usage/Billing page.
We can select gpt-4o-mini or cursor-small before making a request. Doesn’t this make it a slow request?
no it is not the same. what is requested in this thread to use unlimited slow requests for premium models(gpt-4, sonnet) instead of the 500 fast requests
1 Like
As a consultant I’d love to be able to toggle this.
I’d like to save the fast requests for my own work.
The people I’m billing by the hour can get slow requests unless they want to pay for it. They’re already getting way more for their dollar than a year ago. 
Hi,
Could someone from the team respond to this? It’s a bit frustrating to see credits get burned when I’m not in a hurry and just doing something else in the meantime. On the flip side, at the end of the month when I am in a rush, it’s even more frustrating to be stuck in long queues when I need to iterate quickly.
Is this a conscious design choice from the team, or something you might consider improving?
Thanks!
1 Like