Hi, it would be nice to be able to limit inference API spending.
I like the simple OpenAI system: soft and hard limit.
Would be useful, especially when someone makes the mistake of an infinite loop calling the API 
6 Likes
Second this - a hard limit to billing would be fantastic
1 Like
Actually hard and soft limit, i.e. to get warnings after exceeding soft limit (so one can e.g. reconsider budget, change app usage or whatever e.g. to stay operational, or increase hard limit before it kicks in) , and ofc hard limit for safety reasons!
1 Like
Yes to both - I’d feel safer knowing I’d get en email notification if an improperly configured experiment starts blowing through our budget.
This feature is definitely overdue
2 Likes
Think how easy it is to implement ‘if expense > limit then stop & send email’… it’s not an oversight.