Repository navigation
provider (Console Go): constant rate_limit_exceeded despite usage far below quota #47634
Description
Description
Constant [rate_limit_exceeded] errors from provider (Console Go) on every request, even though the usage dashboard shows all quotas far from exhausted (5h: 6%, weekly: 57%, monthly: 23.2%). The UI keeps scheduling automatic retries ("Retry attempt N scheduled") which also fail, making the session unusable.
Exact error:
Retry attempt 4 scheduled: Error from provider (Console Go): Upstream request failed: [rate_limit_exceeded] Rate limit exceeded. Please retry after a brief wait.
The usage dashboard at the same time shows:
- 5-hour window: 6%, resets in ~3h
- Weekly: 57%, resets in ~9h
- Monthly: 23.2%, resets in ~24 days
So either the client is hitting a different (much lower) upstream limit than the one displayed, or the displayed quota is stale/wrong, or requests are misattributed to the wrong account/bucket.
Plugins
None (default config; only a local MCP server configured, unrelated to model requests).
OpenCode version
1.18.18 (CLI). Note: the runtime diagnostics snapshot in-session reported 0.0.0-beta-19157 / channel beta — flagging in case the mismatch matters.
Steps to reproduce
- Open an opencode session using the Muse Spark model (default auth, no custom provider in
opencode.jsonc). - Send any message.
- Observe
Error from provider (Console Go): Upstream request failed: [rate_limit_exceeded]with automatic retries that also fail. - Check the usage dashboard: all windows well below 100%.
Screenshot and/or share link
No screenshot; error text pasted above verbatim.
OS
macOS 25.3.0 (darwin arm64)
Terminal
Apple_Terminal (TERM=xterm-256color, COLORTERM=truecolor)
Additional context
- Shell: /bin/zsh. Install appears to be a beta/release CLI build (1.18.18).
- Frequency: constant, not intermittent — reproduces on every request.
- Only model tested: Muse Spark (no other model tried, so unknown whether provider-wide or model-specific).
- No workaround tried yet.
- No recent config change on the user side (minimal
opencode.jsonc: single local MCP server only).
Activity
github-actions commentedon Sep 6, 2026
This issue might be a duplicate of existing issues. Please check:
parthkhxndelwal commentedon Sep 8, 2026
Any updates onto this???
dinered commentedon Sep 8, 2026
I'm seeing the same problem.
OpenCode Go paid subscription
Model: Muse Spark 1.3 Contributor
macOS on Apple Silicon
iTerm2
Normal interactive coding/agent usage
Go quota is still far from exhausted
The failures are intermittent but frequent:
Upstream request failed: [rate_limit_exceeded]
Other OpenCode Go models continue working when Muse starts returning these errors.
This makes it look like a Muse/upstream capacity limit rather than the documented OpenCode Go quota.
I'm seeing this repeatedly today, September 8, 2026.
xpufx commentedon Sep 8, 2026
@McRosbeef It's not your usage limit. This error or similar would normally happen when you're using too many concurrent connections or sending very rapid requests. I can confirm that IS NOT the case here. I am getting the same error constantly with Muse Spark 1.3. They are probably overloaded due to demand and the api is lying with an incorrect error message. It should probably say "api overloaded" like some other providers.
Unless it's a bug of course.
dinered commentedon Sep 8, 2026
It has gotten significantly worse for me today.
At this point, almost every Muse Spark 1.3 Contributor request starts with 1–3
rate_limit_exceededretries before it eventually succeeds.This is happening during normal interactive usage while my OpenCode Go quota is still available. Other Go models do not show the same behavior.
@MrMushrooooom could you please take a look and let us know what's going on with Muse? There hasn't been any maintainer response here yet, and the issue appears to be getting worse.
neriousy commentedon Oct 21, 2026
Thanks for the report. This error isn't your Go quota. It means the upstream provider for that model was temporarily out of capacity. Retrying or switching models usually gets around it.
OpenCode Go and the free models have usage limits. They're set by plan, and for free models they also change with available capacity, so they're not something we can raise case by case. Your current usage and reset times are in the console, and how the limits work is described at https://opencode.ai/docs/go. If you think your usage was counted wrongly on your account, email [email protected] with your workspace ID.