Skip to main content

AI tokens usage monitoring and estimation

Feature Requests

It’s important for the user to monitor and track their AI generation costs, and it should be greater if it can estimate cost of the next generation
It should have
1. Tokens usage for each generation (input/output and thinking tokens)
2. Current context window usage, such as tokens of current input, total tokens of all previous messages, system-prompt, MCP and Toolings

And it would be awesome if it had a dashboard for generation logs.

Posted by Planxnx ·
Status: Completed9 comments

Log in to comment and vote

Comments9

  • Daniel Nguyen

    Team•

    Jan 7

    I’ve added token usage & estimate costs in v2.5.0.

    • Planxnx

      •

      Jan 8

      Thanks! I’ve already tried it, but it’s not showing the tokens for Custom provider, Ollama, or LM Studio 🥲

      • Daniel Nguyen

        Team•

        Jan 8

        Ah shoot, my bad. I excluded them because I thought you wouldn’t need cost estimation for local models. I forgot that we still need to see token usage. I’m going to fix it now.

      • Daniel Nguyen

        Team•

        Jan 15

        Hey. I’ve fixed this in v2.6.0. Can you confirm? :D

        • Planxnx

          •

          Jan 21

          It’s work nicely!
          Thanks!

  • Daniel Nguyen

    Team•

    Jan 4

    Thanks. I’ve made some great progress and will release soon. You can see message-level & chat-level usage data.

  • Shirish Pothi

    •

    Dec 13, 2025

    +1. Another thing to consider: tok/sec & Time-to-First token: sec

  • Kathaleeyaice

    •

    Nov 29, 2025

    +1, It’s essential basic feature

  • Misterious77

    •

    Nov 27, 2025

    I agree. It’s important.