nvidia glm4.7 Error 404 #7307

Open
opened 2026-02-16 18:06:47 -05:00 by yindo · 8 comments
Owner

Originally created by @Be90nia on GitHub (Jan 23, 2026).

Originally assigned to: @rekram1-node on GitHub.

Description

Please fix the error message for NVIDIA GLM 4.7. I saw that NVIDIA GLM 4.7 was working today, so I wanted to try it out. I used OpenCode 1.1.33, but it immediately returned a 404 error. However, other NVIDIA models worked fine. Please fix this issue.

Plugins

No response

OpenCode version

No response

Steps to reproduce

No response

Screenshot and/or share link

No response

Operating System

No response

Terminal

No response

Originally created by @Be90nia on GitHub (Jan 23, 2026). Originally assigned to: @rekram1-node on GitHub. ### Description Please fix the error message for NVIDIA GLM 4.7. I saw that NVIDIA GLM 4.7 was working today, so I wanted to try it out. I used OpenCode 1.1.33, but it immediately returned a 404 error. However, other NVIDIA models worked fine. Please fix this issue. ### Plugins _No response_ ### OpenCode version _No response_ ### Steps to reproduce _No response_ ### Screenshot and/or share link _No response_ ### Operating System _No response_ ### Terminal _No response_
yindo added the bug label 2026-02-16 18:06:47 -05:00
Author
Owner

@github-actions[bot] commented on GitHub (Jan 23, 2026):

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

  • #9909: Unable to access GLM 4.7 on Google Vertex AI - Same model with similar 'Not Found' 404 error
  • #8431: GLM 4.7 AI_JSONParseError - Same GLM 4.7 model with related response handling issues
  • #7779: GLM 4.7 thinking process not properly formatted - Other GLM 4.7 specific issues
  • #6454: Google Auth Gemini 3 models return 404 error - Similar 404 error pattern with specific models
  • #10040: Gemini 3 Flash returns 404 with wrong Vertex AI endpoint format - Shows endpoint configuration as root cause

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

@github-actions[bot] commented on GitHub (Jan 23, 2026): This issue might be a duplicate of existing issues. Please check: - #9909: Unable to access GLM 4.7 on Google Vertex AI - Same model with similar 'Not Found' 404 error - #8431: GLM 4.7 AI_JSONParseError - Same GLM 4.7 model with related response handling issues - #7779: GLM 4.7 thinking process not properly formatted - Other GLM 4.7 specific issues - #6454: Google Auth Gemini 3 models return 404 error - Similar 404 error pattern with specific models - #10040: Gemini 3 Flash returns 404 with wrong Vertex AI endpoint format - Shows endpoint configuration as root cause Feel free to ignore if none of these address your specific case.
Author
Owner

@duduool commented on GitHub (Jan 23, 2026):

I encountered the same problem, Is there any solution?

@duduool commented on GitHub (Jan 23, 2026): I encountered the same problem, Is there any solution?
Author
Owner

@Be90nia commented on GitHub (Jan 23, 2026):

I encountered the same problem, Is there any solution?

I temporarily resolved the issue by rewriting the NVIDIA configuration in opencode.json.

@Be90nia commented on GitHub (Jan 23, 2026): > I encountered the same problem, Is there any solution? I temporarily resolved the issue by rewriting the NVIDIA configuration in opencode.json.
Author
Owner

@duduool commented on GitHub (Jan 24, 2026):

I encountered the same problem, Is there any solution?

I temporarily resolved the issue by rewriting the NVIDIA configuration in opencode.json.

Did you reauthorize? I tried to reauthorize with the same key and still got an error 404.

@duduool commented on GitHub (Jan 24, 2026): > > I encountered the same problem, Is there any solution? > > I temporarily resolved the issue by rewriting the NVIDIA configuration in opencode.json. Did you reauthorize? I tried to reauthorize with the same key and still got an error 404.
Author
Owner

@bladestone01 commented on GitHub (Jan 24, 2026):

same issue,

@bladestone01 commented on GitHub (Jan 24, 2026): same issue,
Author
Owner

@akayuki39 commented on GitHub (Jan 24, 2026):

I encountered the same problem, Is there any solution?

I temporarily resolved the issue by rewriting the NVIDIA configuration in opencode.json.

Hi @Be90nia , cloud you help to explain more about your solution? I also have the same issue.

@akayuki39 commented on GitHub (Jan 24, 2026): > > I encountered the same problem, Is there any solution? > > I temporarily resolved the issue by rewriting the NVIDIA configuration in opencode.json. Hi @Be90nia , cloud you help to explain more about your solution? I also have the same issue.
Author
Owner

@akayuki39 commented on GitHub (Jan 25, 2026):

I encountered the same problem, Is there any solution?

I temporarily resolved the issue by rewriting the NVIDIA configuration in opencode.json.

Hi @Be90nia , cloud you help to explain more about your solution? I also have the same issue.

It's solved. I was using the desktop app on Mac which has this issue, but switching to terminal solved this.

@akayuki39 commented on GitHub (Jan 25, 2026): > > > I encountered the same problem, Is there any solution? > > > > > > I temporarily resolved the issue by rewriting the NVIDIA configuration in opencode.json. > > Hi [@Be90nia](https://github.com/Be90nia) , cloud you help to explain more about your solution? I also have the same issue. It's solved. I was using the desktop app on Mac which has this issue, but switching to terminal solved this.
Author
Owner

@tom-hanks commented on GitHub (Jan 25, 2026):

我也遇到了同样的问题,请问有什么解决办法吗?

我通过重写 opencode.json 中的 NVIDIA 配置暂时解决了这个问题。

大佬 怎么重写的

@tom-hanks commented on GitHub (Jan 25, 2026): > > 我也遇到了同样的问题,请问有什么解决办法吗? > > 我通过重写 opencode.json 中的 NVIDIA 配置暂时解决了这个问题。 大佬 怎么重写的
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#7307