Skip to main content

Log in to comment and vote

Comments2

  • Jack

    Team•

    Jun 17, 2025

    Do you mean for reasoning models? or the time it takes for the full output to be completed in long messages?

    • Copper Honey

      •

      Jun 17, 2025

      Both would be interesting. It would be a combination of:

      • Time the bot started responding from the moment the prompt was sent

      • Time the thought lasted in thinking models

      • Time the message was fully generated (from the moment the prompt was sent until the bot finishes responding)