Skip to content

DeepSeek V4 Flash keeps throwing "Provider rate limit exceeded" error with Go subscription #34885

Closed

Description

@HongkaiSong

Description

When using the DeepSeek V4 Flash model under the OpenCode Go subscription, the model suddenly became unavailable. Every request returns the error:
Error from provider (Console Go): Provider rate limit exceeded [retrying in 15s attempt #5]
The retry mechanism keeps running but never succeeds, and the issue persists even after restarting the editor and re-authenticating the account. Normal usage was fine before, and there was no excessive request volume on my side.

Plugins

No response

OpenCode version

v1.17.13

Steps to reproduce

  1. Activate OpenCode Go subscription and select DeepSeek V4 Flash as the active model.
  2. Initiate a chat request or trigger code completion.
  3. The request fails immediately and shows the "Provider rate limit exceeded" error with automatic retries.
  4. Restarting the editor / reloading the plugin / switching models back and forth does not resolve the issue.

Screenshot and/or share link

Error from provider (Console Go): Provider rate limit exceeded [retrying in 15s attempt #5]

Operating System

Windows 11

Terminal

No response

Activity

  1. github-actions commented on Jul 2, 2026

    @github-actions
    Contributor

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

  2. HongkaiSong commented on Jul 2, 2026

    @HongkaiSong
    Author
    Image
  3. OZKY23 commented on Jul 2, 2026

    @OZKY23

    same at version 1.17.13. No limits reached and "Use your available balance after reaching the usage limits" active. Tried also with MiMo v2.5

  4. Amouren7 commented on Jul 2, 2026

    @Amouren7

    The same issue has occurred, suspecting whether it's due to insufficient accounts on the official Go package, causing the allocated rate to reach its limit, but mimo2.5 is also equally slow, and I haven't tried other models

  5. FurryWolfX commented on Jul 2, 2026

    @FurryWolfX

    same issue

  6. irfanekon04 commented on Jul 2, 2026

    @irfanekon04

    same issue happening on previous versions as well

  7. fwang commented on Jul 4, 2026

    @fwang
    Contributor

    we are migrating our inference servers .. things are already much more stable

    thanks for your patience

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions