Thread token usage endpoint

Any way for me to check out how many tokens a given thread is using
(in the context of the Assistants API)

Or is it all abstracted by the assistant - model interaction and there is no way around it?

This is a common question that the community still hasn’t found an answer to. At the moment, it is abstracted and you can only estimate it, if you’re interested on that I have a couple recommendations here:

1 Like

I see, the tough part is when some functions are called and the assistant uses only a few parts of the information for the completion. It’s becoming a guessing game

1 Like

Small update
I’ve been adding messages and runing fnuction calls, and for functions with larger results, there seems to be a limit of 10000 tokens added to the context per function call, or close enough

I’m using tiktoken btw

1 Like