You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I’d like to see how many tokens each thread has consumed and its estimated cost, so I can understand the expense of individual tasks and compare model choices.
Ideally, each thread would have a compact usage summary showing:
Total token usage, with input, output, and cached tokens where available.
Estimated API cost, clearly distinguished from actual billed spend for subscription accounts.
A breakdown by model when multiple models are used in the same thread.
A thread breakdown on the Usage page would also be useful. Maybe link from the thread too.
It has been implemented in #9017 but I want to open a discussion in case PR gets closes or too stale.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
I’d like to see how many tokens each thread has consumed and its estimated cost, so I can understand the expense of individual tasks and compare model choices.
Ideally, each thread would have a compact usage summary showing:
A thread breakdown on the Usage page would also be useful. Maybe link from the thread too.
It has been implemented in #9017 but I want to open a discussion in case PR gets closes or too stale.
It think the UI implemented looks fine.

Related work:
Could this issue track the feature request through V2, independently of those implementation PRs?
Also somewhat related to #6683
All reactions