You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
These issues are related to displaying performance metrics and detailed session information. Tokens/second metrics could be part of an expanded performance monitoring feature alongside these existing requests.
Feel free to ignore if your specific case differs from these.
This is a feature I'd love. I'm testing different models, and speed is one of the factors I'm comparing. A token speed indicator would be very helpful.
Reacted by Josh Sansom, Sebastian Vilstrup, Haydon Ryan, Carlo Taleon, Hicsy, Sean Ward, Joseph, Jared Ping, noam stein, Petr Spac and 17 more
Huge plus one from me. Just approx t/s in the bottom right corner or something.
It would really help people who are looking to buy hardware to run models locally to know what experience they're seeing in the cloud. This can then be cross referenced to other's builds.
Hey all — I just opened a PR that tackles this: #12721
It adds a tok/s metric right after the duration in the response footer (e.g. 18.3s · 131 tok/s). I've been switching between providers a lot and wanted a quick way to see the actual speed difference without external tools.
The TPS logic lives in core/tokens/ so it can be reused outside the TUI later. Would love feedback from anyone still interested in this!
Reacted by Haydon Ryan, Kamil Cukrowski, Martin Emrich, Yashank, gyq, Forbidden Era, Josh, Lindit Ajvazaj, Sam.Wang, Dmitry Olyenyov and 6 more
Activity
github-actions commentedon Dec 11, 2025
This issue might be a duplicate of existing issues. Please check:
These issues are related to displaying performance metrics and detailed session information. Tokens/second metrics could be part of an expanded performance monitoring feature alongside these existing requests.
Feel free to ignore if your specific case differs from these.
Madmanden commentedon Dec 25, 2025
This is a feature I'd love. I'm testing different models, and speed is one of the factors I'm comparing. A token speed indicator would be very helpful.
ForbiddenEra commentedon Jan 23, 2026
plz+1
haydonryan commentedon Feb 5, 2026
Huge plus one from me. Just approx t/s in the bottom right corner or something.
It would really help people who are looking to buy hardware to run models locally to know what experience they're seeing in the cloud. This can then be cross referenced to other's builds.
JohnCode-Dev commentedon Feb 10, 2026
Hey all — I just opened a PR that tackles this: #12721
It adds a
tok/smetric right after the duration in the response footer (e.g.18.3s · 131 tok/s). I've been switching between providers a lot and wanted a quick way to see the actual speed difference without external tools.The TPS logic lives in
core/tokens/so it can be reused outside the TUI later. Would love feedback from anyone still interested in this!SamWang32191 commentedon Mar 7, 2026
This feature would be very helpful for my use case. I was wondering if there have been any updates on it.🙏
ForbiddenEra commentedon Mar 10, 2026
This would be great for people doing local stuff
Navaneeth-Sharma commentedon Mar 13, 2026
Yes, adding to the above conv. This feature would be great.
evilbuck commentedon Mar 19, 2026
+1 on this. If nothing else, just to keep the providers honest.
slimypi commentedon Mar 26, 2026
+1 This would be great to see if providers are not lying...
ForbiddenEra commentedon Mar 27, 2026
I suppose that's a good use too!
PEMessage commentedon Mar 30, 2026
+1 on this. very helpful
codenoid commentedon Mar 31, 2026
+1 on this
Tarquinen commentedon Apr 4, 2026
This can be done via plugin now, for example:
https://github.com/Tarquinen/oc-tps
3 remaining items
SergioSV96 commentedon May 7, 2026
This should be part of native OpenCode! vouch
chris-hatton commentedon Jun 16, 2026
This should be built-in - surely everyone wants to know how their compute endpoint is performing during normal work.
chinhnt38 commentedon Jul 3, 2026
+1 vote for this
bzavolovich commentedon Jul 6, 2026
+1 on this
grahammiranda13 commentedon Aug 10, 2026
+1 on this
feat(tui): add reusable token-rate meter (anomalyco#5374)
feat(tui): show live tokens/s in home footer while streaming (anomaly…
fix(tui): guard assistant tokens + drop unused isActive (anomalyco#5374)
JasonJason-oy commentedon Sep 8, 2026
https://github.com/JasonJason-oy/oc-metricboard
try this, for real-time LLM metrics (TPS / TTFT / token usage) with sub-agent aggregation and per-model breakdown.
yisier commentedon Sep 11, 2026
+1 on this
JoyousJohn commentedon Sep 22, 2026
+1
OverHash commentedon Sep 22, 2026
It hasn't been mentioned in the thread, but this is a native feature of OpenCode V2 thanks to #45265!
In
cli.json(c):{ "session": { "tps": true } }which displays tokens per second for each step.
feat(tui): add live tokens/sec display
rekram1-node commentedon Oct 1, 2026
https://opencode.ai/v2/docs
as said by @OverHash this is supported in opencode v2 out of the box!