On Vext, "Query" is a basic usage unit that calculates how many times an LLM has been triggered. We decided not to use "token" because it could be confusing for some and difficult to manage/forecast usage and cost.
For example, if you have a project with one LLM configured and is integrated with your app via API, when there's a POST request to the API, it's considered 1 query.
Where there are multiple LLMs configured in a project, say three LLMs within the same project, and when invoked, it's considered 3 queries.
Was this article helpful?
That’s Great!
Thank you for your feedback
Sorry! We couldn't be helpful
Thank you for your feedback
Feedback sent
We appreciate your effort and will try to fix the article