Big Pickle model loops with "too many requests" error in high mode (free trial) #7450

Open
opened 2026-02-16 18:07:12 -05:00 by yindo · 5 comments
Owner

Originally created by @ftbhabuk on GitHub (Jan 24, 2026).

Originally assigned to: @fwang on GitHub.

Description

When using the Big Pickle model through OpenCode Zen on a free trial account with the "high" quality mode, requests consistently loop with "too many request, please try again" errors before eventually succeeding after multiple retries. This creates a frustrating user experience even though the request does eventually work.

The issue appears to be a rate limiting problem where the retry logic doesn't properly handle backoff, causing repeated failures before success.

Plugins

None

OpenCode version

1.1.28

Steps to reproduce

Select the "Big Pickle" model
4. Set quality/thinking mode to "high"
5. Send any coding request (e.g., "request a simple analysis inside a project folder")
6. Observe the repeated "too many requests" error messages
7. Wait for eventual success after multiple retry loops

Expected: Request succeeds on first attempt or fails with clear rate limit message
Actual: Multiple "too many requests" errors before eventual success

Screenshot and/or share link

No response

Operating System

6.18.6-arch1-1

Terminal

Kitty

Originally created by @ftbhabuk on GitHub (Jan 24, 2026). Originally assigned to: @fwang on GitHub. ### Description When using the Big Pickle model through OpenCode Zen on a free trial account with the "high" quality mode, requests consistently loop with "too many request, please try again" errors before eventually succeeding after multiple retries. This creates a frustrating user experience even though the request does eventually work. The issue appears to be a rate limiting problem where the retry logic doesn't properly handle backoff, causing repeated failures before success. ### Plugins None ### OpenCode version 1.1.28 ### Steps to reproduce Select the "Big Pickle" model 4. Set quality/thinking mode to "high" 5. Send any coding request (e.g., "request a simple analysis inside a project folder") 6. Observe the repeated "too many requests" error messages 7. Wait for eventual success after multiple retry loops Expected: Request succeeds on first attempt or fails with clear rate limit message Actual: Multiple "too many requests" errors before eventual success ### Screenshot and/or share link _No response_ ### Operating System 6.18.6-arch1-1 ### Terminal Kitty
yindo added the bugzen labels 2026-02-16 18:07:12 -05:00
Author
Owner

@github-actions[bot] commented on GitHub (Jan 24, 2026):

This issue might be a duplicate of existing issues. Please check:

  • #2398: AI_RetryError: Failed after 4 attempts. Last error: Too Many Requests (exact same error message)
  • #1712: Implement exponential back-off when hitting rate limits (related retry logic issue)
  • #8769: Retry: allow user to change exponential backoff to fixed interval (retry strategy configuration)
  • #8618: GLM Coding Plan Pro unusable due to rate limits (similar rate limiting symptoms)

Feel free to ignore if none of these address your specific case.

@github-actions[bot] commented on GitHub (Jan 24, 2026): This issue might be a duplicate of existing issues. Please check: - #2398: AI_RetryError: Failed after 4 attempts. Last error: Too Many Requests (exact same error message) - #1712: Implement exponential back-off when hitting rate limits (related retry logic issue) - #8769: Retry: allow user to change exponential backoff to fixed interval (retry strategy configuration) - #8618: GLM Coding Plan Pro unusable due to rate limits (similar rate limiting symptoms) Feel free to ignore if none of these address your specific case.
Author
Owner

@jeremyakers commented on GitHub (Jan 26, 2026):

I have the same issue, and I am not even using "high". Just "default"

Image Image
@jeremyakers commented on GitHub (Jan 26, 2026): I have the same issue, and I am not even using "high". Just "default" <img width="569" height="65" alt="Image" src="https://github.com/user-attachments/assets/cef9eb02-b327-46e2-b782-58e34f3a90c3" /> <img width="573" height="52" alt="Image" src="https://github.com/user-attachments/assets/7500e8ea-6f1d-4e0c-a61e-3f8f9fb130d0" />
Author
Owner

@i-am-noamg commented on GitHub (Jan 26, 2026):

same here

Image
@i-am-noamg commented on GitHub (Jan 26, 2026): same here <img width="604" height="91" alt="Image" src="https://github.com/user-attachments/assets/ffbaac82-b52c-4cd7-a090-215c73acd840" />
Author
Owner

@quickreactor commented on GitHub (Jan 27, 2026):

Same, windows. Also getting rate limit or failed connection to any Gemini models

@quickreactor commented on GitHub (Jan 27, 2026): Same, windows. Also getting rate limit or failed connection to any Gemini models
Author
Owner

@ellannjohnson commented on GitHub (Jan 28, 2026):

Same issue and just started recently. Using MacOS Tahoe and is occurring on 2 separate machines. Simple queries and definitely not too many requests. The requests will complete after several auto retries.

@ellannjohnson commented on GitHub (Jan 28, 2026): Same issue and just started recently. Using MacOS Tahoe and is occurring on 2 separate machines. Simple queries and definitely not too many requests. The requests will complete after several auto retries.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#7450