Inference speed is slower than expected with GPT-4.1 in Opencode #629

Closed
opened 2026-02-16 17:27:39 -05:00 by yindo · 6 comments
Owner

Originally created by @netanelbi on GitHub (Jul 11, 2025).

Originally assigned to: @thdxr on GitHub.

I have observed that model inference speed in Opencode (using Copilot and GPT-4.1) is noticeably slower than expected. When using Copilot with Claude via my proxy, the inference speed is much higher. Since GPT-4.1 is known for fast performance, something may be holding down the models in Opencode. Please investigate possible bottlenecks, such as API throttling, network delays, or code inefficiencies.

Originally created by @netanelbi on GitHub (Jul 11, 2025). Originally assigned to: @thdxr on GitHub. I have observed that model inference speed in Opencode (using Copilot and GPT-4.1) is noticeably slower than expected. When using Copilot with Claude via my proxy, the inference speed is much higher. Since GPT-4.1 is known for fast performance, something may be holding down the models in Opencode. Please investigate possible bottlenecks, such as API throttling, network delays, or code inefficiencies.
yindo closed this issue 2026-02-16 17:27:39 -05:00
Author
Owner

@drewbitt commented on GitHub (Jul 11, 2025):

What is the tps you are seeing?

@drewbitt commented on GitHub (Jul 11, 2025): What is the tps you are seeing?
Author
Owner

@netanelbi commented on GitHub (Jul 11, 2025):

running:
opencode --model github-copilot/gpt-4.1 run "write 1k drama story about apple"
took ~17-22 seconds.
on claude it took 14s. thats fine i guess

but openning opencode and doing the same request using the interface took 43 seconds

@netanelbi commented on GitHub (Jul 11, 2025): running: opencode --model github-copilot/gpt-4.1 run "write 1k drama story about apple" took ~17-22 seconds. on claude it took 14s. thats fine i guess but openning opencode and doing the same request using the interface took 43 seconds
Author
Owner

@Uranium2 commented on GitHub (Jul 12, 2025):

Hello,
Just tried opencode for few days, and it does feel like Copilot GPT-4.1 is slow. I don't have other model to compare on Opencode. But when using Copilot GPT-4.1 directly on Vscode, it does seem faster.
Also, it feels like my CPU fan is bursting when asking a task to Opencode. And i think that the files are modified fast, but in the terminal, the display/writing of "code" that the model will create is slow. Most of the time, the file is already edited and ready, but the console is still writing code (and most of the time the code written doesn't seem to be 100% what he updated on the file)

@Uranium2 commented on GitHub (Jul 12, 2025): Hello, Just tried opencode for few days, and it does feel like Copilot GPT-4.1 is slow. I don't have other model to compare on Opencode. But when using Copilot GPT-4.1 directly on Vscode, it does seem faster. Also, it feels like my CPU fan is bursting when asking a task to Opencode. And i think that the files are modified fast, but in the terminal, the display/writing of "code" that the model will create is slow. Most of the time, the file is already edited and ready, but the console is still writing code (and most of the time the code written doesn't seem to be 100% what he updated on the file)
Author
Owner

@Yorizel commented on GitHub (Jul 16, 2025):

i also facing this

@Yorizel commented on GitHub (Jul 16, 2025): i also facing this
Author
Owner

@Uranium2 commented on GitHub (Jul 17, 2025):

Pretty sure it's the same issue here
https://github.com/sst/opencode/issues/811

@Uranium2 commented on GitHub (Jul 17, 2025): Pretty sure it's the same issue here https://github.com/sst/opencode/issues/811
Author
Owner

@adamdotdevin commented on GitHub (Jul 17, 2025):

yeah, this is an issue with rendering performance on some systems; can you all share what OS/etc you're using in #811, going to close this as duplicate

@adamdotdevin commented on GitHub (Jul 17, 2025): yeah, this is an issue with rendering performance on some systems; can you all share what OS/etc you're using in #811, going to close this as duplicate
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#629