github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-24 22:52:13 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #15707] glm-5.1:cloud model returns 403 authentication error with GitHub Copilot (CLI & VSCode) while other models work #72075

New Issue
Closed
opened 2026-05-05 03:25:11 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-05 03:25:11 -05:00
Owner
Copy Link

Originally created by @jonathanGGa on GitHub (Apr 19, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15707

What is the issue?

Bug Description

When using GitHub Copilot (CLI & Chat (VSCode) ) with Ollama Cloud as the provider, the glm-5.1:cloud model consistently fails with a 403 authentication error on every request. All other Ollama Cloud models authenticate and respond correctly.

Steps to Reproduce

  1. Configure GitHub Copilot to use Ollama Cloud as the language model provider
  2. Select the glm-5.1:cloud model
  3. Send any message in Copilot
  4. Request fails immediately with authentication error

Expected Behavior

The glm-5.1:cloud model should authenticate successfully and return responses, just like other Ollama Cloud models.

Actual Behavior in Copilot CLI

Every request to glm-5.1:cloud fails with:

Authentication failed with provider at http://127.0.0.1:11434/v1 (HTTP 403).
Check your COPILOT_PROVIDER_API_KEY or COPILOT_PROVIDER_BEARER_TOKEN.

Actual Behavior in Copilot Chat (VSCode)

Every request to glm-5.1:cloud fails with:

Sorry, your request failed. Please try again.

Copilot Request id: 9c3f19f1-b94c-45f9-83b7-b49b08bd11c5

Reason: token expired or invalid: 403: Error: token expired or invalid: 403 at Dj._provideLanguageModelResponse (c:\Users\33665.vscode\extensions\github.copilot-chat-0.44.1\dist\extension.js:1688:13141) at process.processTicksAndRejections (node:internal/process/task_queues:103:5)

Environment

  • Ollama version: (latest)
  • Affected model: glm-5.1:cloud
  • Working models: All other Ollama Cloud models tested (kimi, qwen, minimax)

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @jonathanGGa on GitHub (Apr 19, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15707 ### What is the issue? #### Bug Description When using GitHub Copilot (CLI & Chat (VSCode) ) with Ollama Cloud as the provider, the `glm-5.1:cloud` model consistently fails with a 403 authentication error on every request. All other Ollama Cloud models authenticate and respond correctly. #### Steps to Reproduce 1. Configure GitHub Copilot to use Ollama Cloud as the language model provider 2. Select the `glm-5.1:cloud` model 3. Send any message in Copilot 4. Request fails immediately with authentication error #### Expected Behavior The `glm-5.1:cloud` model should authenticate successfully and return responses, just like other Ollama Cloud models. #### Actual Behavior in Copilot CLI Every request to `glm-5.1:cloud` fails with: ``` Authentication failed with provider at http://127.0.0.1:11434/v1 (HTTP 403). Check your COPILOT_PROVIDER_API_KEY or COPILOT_PROVIDER_BEARER_TOKEN. ``` #### Actual Behavior in Copilot Chat (VSCode) Every request to `glm-5.1:cloud` fails with: ``` Sorry, your request failed. Please try again. Copilot Request id: 9c3f19f1-b94c-45f9-83b7-b49b08bd11c5 Reason: token expired or invalid: 403: Error: token expired or invalid: 403 at Dj._provideLanguageModelResponse (c:\Users\33665.vscode\extensions\github.copilot-chat-0.44.1\dist\extension.js:1688:13141) at process.processTicksAndRejections (node:internal/process/task_queues:103:5) ``` #### Environment - **Ollama version:** (latest) - **Affected model:** `glm-5.1:cloud` - **Working models:** All other Ollama Cloud models tested (kimi, qwen, minimax) ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-05-05 03:25:11 -05:00
GiteaMirror commented 2026-05-05 03:25:19 -05:00
Author
Owner
Copy Link

@MihaelIsaev commented on GitHub (Apr 21, 2026):

Still getting 403 in Copilot with glm-5.1:cloud while glm-5:cloud works

<!-- gh-comment-id:4290726995 --> @MihaelIsaev commented on GitHub (Apr 21, 2026): Still getting 403 in Copilot with `glm-5.1:cloud` while `glm-5:cloud` works
GiteaMirror commented 2026-05-05 03:25:22 -05:00
Author
Owner
Copy Link

@jonathanGGa commented on GitHub (Apr 21, 2026):

Still getting 403 in Copilot with glm-5.1:cloud while glm-5:cloud works

It looks like it doesn't work in free plan, but it works when you subs to pro plan

<!-- gh-comment-id:4290749071 --> @jonathanGGa commented on GitHub (Apr 21, 2026): > Still getting 403 in Copilot with `glm-5.1:cloud` while `glm-5:cloud` works It looks like it doesn't work in free plan, but it works when you subs to pro plan
GiteaMirror commented 2026-05-05 03:25:23 -05:00
Author
Owner
Copy Link

@MihaelIsaev commented on GitHub (Apr 21, 2026):

Still getting 403 in Copilot with glm-5.1:cloud while glm-5:cloud works

It looks like it doesn't work in free plan, but it works when you subs to pro plan

Oh ok, good to know, thanks

<!-- gh-comment-id:4290760922 --> @MihaelIsaev commented on GitHub (Apr 21, 2026): > > Still getting 403 in Copilot with `glm-5.1:cloud` while `glm-5:cloud` works > > It looks like it doesn't work in free plan, but it works when you subs to pro plan Oh ok, good to know, thanks
GiteaMirror commented 2026-05-05 03:25:25 -05:00
Author
Owner
Copy Link

@netetireallyhuman commented on GitHub (Apr 22, 2026):

Still getting 403 in Copilot with glm-5.1:cloud

<!-- gh-comment-id:4300083373 --> @netetireallyhuman commented on GitHub (Apr 22, 2026): Still getting 403 in Copilot with glm-5.1:cloud
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#72075
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?