I have searched the existing issues and discussions.
Problem Description
I use openwebui quite a bit now for most all my AI chats as API is cheaper in most cases than their monthly costs on their apps but would like the choice to see the cost of each response and overall chat
Desired Solution you'd like
I would like to see how many tokens it used to reply (With / without reasoning), time to first token, total time and even a cost as some APIs do provide a tokeniser to use and configure a cost for each million tokens (With account of input, cached and output) for that specific response and the entire conversation so far
Alternatives Considered
I have considered and tried to use LiteLLM however I have found it quite unreliable and would prefer a built in tool instead
Additional Context
No response
Originally created by @TimyIsCool on GitHub (Jul 20, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/15895
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
### Problem Description
I use openwebui quite a bit now for most all my AI chats as API is cheaper in most cases than their monthly costs on their apps but would like the choice to see the cost of each response and overall chat
### Desired Solution you'd like
I would like to see how many tokens it used to reply (With / without reasoning), time to first token, total time and even a cost as some APIs do provide a tokeniser to use and configure a cost for each million tokens (With account of input, cached and output) for that specific response and the entire conversation so far
### Alternatives Considered
I have considered and tried to use LiteLLM however I have found it quite unreliable and would prefer a built in tool instead
### Additional Context
_No response_
Can be done with filter functions. Should not be done baked in by open webui.
Duplicate issue
<!-- gh-comment-id:3095221580 -->
@Classic298 commented on GitHub (Jul 21, 2025):
Can be done with filter functions. Should not be done baked in by open webui.
Duplicate issue
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @TimyIsCool on GitHub (Jul 20, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/15895
Check Existing Issues
Problem Description
I use openwebui quite a bit now for most all my AI chats as API is cheaper in most cases than their monthly costs on their apps but would like the choice to see the cost of each response and overall chat
Desired Solution you'd like
I would like to see how many tokens it used to reply (With / without reasoning), time to first token, total time and even a cost as some APIs do provide a tokeniser to use and configure a cost for each million tokens (With account of input, cached and output) for that specific response and the entire conversation so far
Alternatives Considered
I have considered and tried to use LiteLLM however I have found it quite unreliable and would prefer a built in tool instead
Additional Context
No response
@Classic298 commented on GitHub (Jul 21, 2025):
Can be done with filter functions. Should not be done baked in by open webui.
Duplicate issue