Originally created by @dromeuf on GitHub (Feb 19, 2025).
Feature Request
When using custom Model Chat, I sometimes have long conversations. How do I know if I've reached the context limit of the LLM I'm using? Is there an option or counter to find out where I am in the context window limit ? Does OpenWebUI offer a “native” counter that shows exactly how many tokens have been used and where you are in relation to the model's context limit ? Is there an official indicator or option for automatically displaying the number of tokens consumed on the interface?
at some point the quality of the conversation is affected when it's long.
Thanks for your great work. David.
Originally created by @dromeuf on GitHub (Feb 19, 2025).
# Feature Request
When using custom Model Chat, I sometimes have long conversations. How do I know if I've reached the context limit of the LLM I'm using? Is there an option or counter to find out where I am in the context window limit ? Does OpenWebUI offer a “native” counter that shows exactly how many tokens have been used and where you are in relation to the model's context limit ? Is there an official indicator or option for automatically displaying the number of tokens consumed on the interface?
at some point the quality of the conversation is affected when it's long.
Thanks for your great work. David.
Hello silentoplayz, I'm sorry but I can't find a clear answer in the tickets quoted.
@dromeuf commented on GitHub (Feb 20, 2025):
> En relation - [#573](https://github.com/open-webui/open-webui/issues/573)
Hello silentoplayz, I'm sorry but I can't find a clear answer in the tickets quoted.
Hello silentoplayz, I'm sorry but I can't find a clear answer in the tickets quoted.
In short, there's not a way within Open WebUI to accurately count how many tokens have been used within a chat. There might be community made functions, but even those can be inaccurate if the model you're using doesn't use the tokenizer import of the function.
@silentoplayz commented on GitHub (Feb 21, 2025):
> > En relation - [#573](https://github.com/open-webui/open-webui/issues/573)
>
> Hello silentoplayz, I'm sorry but I can't find a clear answer in the tickets quoted.
In short, there's not a way within Open WebUI to accurately count how many tokens have been used within a chat. There might be community made functions, but even those can be inaccurate if the model you're using doesn't use the tokenizer import of the function.
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 @dromeuf on GitHub (Feb 19, 2025).
Feature Request
When using custom Model Chat, I sometimes have long conversations. How do I know if I've reached the context limit of the LLM I'm using? Is there an option or counter to find out where I am in the context window limit ? Does OpenWebUI offer a “native” counter that shows exactly how many tokens have been used and where you are in relation to the model's context limit ? Is there an official indicator or option for automatically displaying the number of tokens consumed on the interface?
at some point the quality of the conversation is affected when it's long.
Thanks for your great work. David.
@silentoplayz commented on GitHub (Feb 19, 2025):
Related - https://github.com/open-webui/open-webui/issues/573
@dromeuf commented on GitHub (Feb 20, 2025):
Hello silentoplayz, I'm sorry but I can't find a clear answer in the tickets quoted.
@silentoplayz commented on GitHub (Feb 21, 2025):
In short, there's not a way within Open WebUI to accurately count how many tokens have been used within a chat. There might be community made functions, but even those can be inaccurate if the model you're using doesn't use the tokenizer import of the function.