github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-07-21 17:29:50 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

[GH-ISSUE #17403] issue: Gemini API - OpenAI Auth Failure #18273

New Issue
Closed
opened 2026-04-20 00:28:28 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-20 00:28:28 -05:00
Owner
Copy Link
Copy Source

Originally created by @Robertde34 on GitHub (Sep 12, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/17403

Check Existing Issues

  • I have searched for any existing and/or related issues.
  • I have searched for any existing and/or related discussions.
  • I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

v.06.28

Ollama Version (if applicable)

0.11.10

Operating System

Windows Docker

Browser (if applicable)

every Browser

Confirmation

  • I have read and followed all instructions in README.md.
  • I am using the latest version of both Open WebUI and Ollama.
  • I have included the browser console logs.
  • I have included the Docker container logs.
  • I have provided every relevant configuration, setting, and environment variable used in my setup.
  • I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
  • I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
  • Start with the initial platform/version/OS and dependencies used,
  • Specify exact install/launch/configure commands,
  • List URLs visited, user input (incl. example values/emails/passwords if needed),
  • Describe all options and toggles enabled or changed,
  • Include any files or environmental changes,
  • Identify the expected and actual result at each stage,
  • Ensure any reasonably skilled user can follow and hit the same issue.

Expected Behavior

(Admin Settings → Connections → OpenAI API)

URL: https://generativelanguage.googleapis.com/v1beta/openai/

Authentication: API_Key

Documentation:
https://ai.google.dev/gemini-api/docs/openai?hl=en

Actual Behavior

WebUI don't get access direct to Gemini API (Admin Settings → Connections → OpenAI API)

The Open WebUI user interface has changed again, and the “Generative AI” option is no longer directly selectable as a provider.

This has caused confusion among many users. The Gemini API must be configured via the OpenAI-compatible interface provided by Open WebUI.

The problem is that Open Webui treats the Gemini API as a kind of OpenAI-compatible endpoint, but does not translate all authentication details correctly. In most cases, when using the OpenAI connection for Gemini, the API expects the key to be passed as a “bearer token” in the URL, rather than as a simple API key.

API-Key in URL also doesn't work.
https://generativelanguage.googleapis.com/v1beta/models?key=API_Key

MY API Key is tested and is working in other APP, simple by paste API Key and this URL.
base_url="https://generativelanguage.googleapis.com/v1beta/openai/

Steps to Reproduce

WebUI (Admin Settings → Connections → OpenAI API)

URL: https://generativelanguage.googleapis.com/v1beta/openai/

Authentication bearer: Gemini_API_Key

Logs & Screenshots

Screenshot-838

Additional Information

Please update WebUI OpenAI API Documentation after fixing this issue.

Originally created by @Robertde34 on GitHub (Sep 12, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/17403 ### Check Existing Issues - [x] I have searched for any existing and/or related issues. - [x] I have searched for any existing and/or related discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version v.06.28 ### Ollama Version (if applicable) 0.11.10 ### Operating System Windows Docker ### Browser (if applicable) every Browser ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have included the browser console logs. - [x] I have included the Docker container logs. - [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.** - [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc). - [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps: - Start with the initial platform/version/OS and dependencies used, - Specify exact install/launch/configure commands, - List URLs visited, user input (incl. example values/emails/passwords if needed), - Describe all options and toggles enabled or changed, - Include any files or environmental changes, - Identify the expected and actual result at each stage, - Ensure any reasonably skilled user can follow and hit the same issue. ### Expected Behavior (Admin Settings → Connections → OpenAI API) URL: https://generativelanguage.googleapis.com/v1beta/openai/ Authentication: API_Key Documentation: https://ai.google.dev/gemini-api/docs/openai?hl=en ### Actual Behavior WebUI don't get access direct to Gemini API (Admin Settings → Connections → OpenAI API) The Open WebUI user interface has changed again, and the “Generative AI” option is no longer directly selectable as a provider. This has caused confusion among many users. The Gemini API must be configured via the OpenAI-compatible interface provided by Open WebUI. The problem is that Open Webui treats the Gemini API as a kind of OpenAI-compatible endpoint, but does not translate all authentication details correctly. In most cases, when using the OpenAI connection for Gemini, the API expects the key to be passed as a “bearer token” in the URL, rather than as a simple API key. API-Key in URL also doesn't work. https://generativelanguage.googleapis.com/v1beta/models?key=API_Key MY API Key is tested and is working in other APP, simple by paste API Key and this URL. base_url="https://generativelanguage.googleapis.com/v1beta/openai/ ### Steps to Reproduce WebUI (Admin Settings → Connections → OpenAI API) URL: https://generativelanguage.googleapis.com/v1beta/openai/ Authentication bearer: Gemini_API_Key ### Logs & Screenshots <img width="387" height="135" alt="Screenshot-838" src="https://github.com/user-attachments/assets/2cf4bdaa-0bbc-445d-b651-90dc24434922" /> ### Additional Information Please update WebUI OpenAI API Documentation after fixing this issue.
GiteaMirror added the bug label 2026-04-20 00:28:28 -05:00
GiteaMirror commented 2026-04-20 00:28:32 -05:00
Author
Owner
Copy Link
Copy Source

@tjbck commented on GitHub (Sep 12, 2025):

Image

Unable to reproduce, works as intended.

<!-- gh-comment-id:3286605904 --> @tjbck commented on GitHub (Sep 12, 2025): <img width="1510" height="372" alt="Image" src="https://github.com/user-attachments/assets/650cd532-09d3-4460-8302-1e6ae612af20" /> Unable to reproduce, works as intended.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No labels bug
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
GiteaMirror ninjasurge (Kaehlen Rog)
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#18273