[GH-ISSUE #22448] feat: Show response generation time per message #35243

Closed
opened 2026-04-25 09:28:38 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @fuleinist on GitHub (Mar 8, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/22448

Problem Description

When comparing different models or troubleshooting slow responses, I have no visibility into how long each response took to generate. I need to estimate performance differences between models but there's no timing information displayed.

Desired Solution

Display a small timestamp or duration (e.g., "2.3s") next to each AI response, showing how long the generation took. This could be a subtle indicator similar to how some chat apps show message timestamps.

Use Case

  • Comparing model speeds when testing different providers
  • Identifying performance issues with specific models
  • Understanding latency differences between local and cloud models

Alternatives Considered

Browser DevTools network tab - but this requires technical knowledge and doesn't show per-message timing in the UI context.

Originally created by @fuleinist on GitHub (Mar 8, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/22448 ### Problem Description When comparing different models or troubleshooting slow responses, I have no visibility into how long each response took to generate. I need to estimate performance differences between models but there's no timing information displayed. ### Desired Solution Display a small timestamp or duration (e.g., "2.3s") next to each AI response, showing how long the generation took. This could be a subtle indicator similar to how some chat apps show message timestamps. ### Use Case - Comparing model speeds when testing different providers - Identifying performance issues with specific models - Understanding latency differences between local and cloud models ### Alternatives Considered Browser DevTools network tab - but this requires technical knowledge and doesn't show per-message timing in the UI context.
Author
Owner

@Classic298 commented on GitHub (Mar 8, 2026):

Can be done using filters - should be done using filters

<!-- gh-comment-id:4019024067 --> @Classic298 commented on GitHub (Mar 8, 2026): Can be done using filters - should be done using filters
Author
Owner
<!-- gh-comment-id:4019024612 --> @Classic298 commented on GitHub (Mar 8, 2026): https://docs.openwebui.com/features/extensibility/plugin/functions/filter example: https://openwebui.com/posts/token_usage_display_a94ea72f
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#35243