I have searched for any existing and/or related issues.
I have searched for any existing and/or related discussions.
I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
I am using the latest version of Open WebUI.
Installation Method
Git Clone
Open WebUI Version
v0.6.43
Ollama Version (if applicable)
No response
Operating System
Debian 12
Browser (if applicable)
Firefox 146.0.1
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
When using gpt-image-1.5 via Azure, image generation should work...it doesn't.
Actual Behavior
When attempting to create an image using gpt-image-1.5 via Azure, the following is returned:
It looks like the image generation attempt failed due to the following error:
[ERROR: azure-openai error: Unknown parameter: 'response_format'.]
If I grab the actual POST from Open WebUI and remove the response_format from the body: "response_format": "b64_json"
The image generation works properly.
Steps to Reproduce
Go to Microsoft Foundry (Azure AI) and provision your gpt-image.1.5 model.
Within Open WebUI, go to Admin Panel > Settings > Images, and setup gpt-image-1.5.
Generate an image...it fails.
Using dalle-3 works...but Azure will be decommissioning DALLE-3 on February 18, 2026.
Logs & Screenshots
It looks like the image generation attempt failed due to the following error:
[ERROR: azure-openai error: Unknown parameter: 'response_format'.]
Additional Information
No response
Originally created by @rutgers-master on GitHub (Jan 6, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/20423
### 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 have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
- [x] I am using the latest version of Open WebUI.
### Installation Method
Git Clone
### Open WebUI Version
v0.6.43
### Ollama Version (if applicable)
_No response_
### Operating System
Debian 12
### Browser (if applicable)
Firefox 146.0.1
### 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
When using gpt-image-1.5 via Azure, image generation should work...it doesn't.
### Actual Behavior
When attempting to create an image using gpt-image-1.5 via Azure, the following is returned:
```
It looks like the image generation attempt failed due to the following error:
[ERROR: azure-openai error: Unknown parameter: 'response_format'.]
```
If I grab the actual POST from Open WebUI and remove the response_format from the body:
` "response_format": "b64_json"`
The image generation works properly.
### Steps to Reproduce
1. Go to Microsoft Foundry (Azure AI) and provision your gpt-image.1.5 model.
2. Within Open WebUI, go to Admin Panel > Settings > Images, and setup gpt-image-1.5.
3. Generate an image...it fails.
Using dalle-3 works...but Azure will be decommissioning DALLE-3 on February 18, 2026.
### Logs & Screenshots
```
It looks like the image generation attempt failed due to the following error:
[ERROR: azure-openai error: Unknown parameter: 'response_format'.]
```
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-04-20 01:31:22 -05:00
@owui-terminator[bot] commented on GitHub (Jan 6, 2026):
🔍Similar Issues Found
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
#19451issue: Images with gpt-image-1 ERROR: No connection adapters were found by 3keyallen3 • Nov 25, 2025 • bug
#19433issue: error while creating an image using openai gpt-image-1 by Abdelrahman1993 • Nov 24, 2025 • bug
#20237issue: Image editing stopped working by tomasloksa • Dec 29, 2025 • bug, confirmed issue
💡Tips:
If this is a duplicate, please consider closing this issue and adding any additional details to the existing one
If you found a solution in any of these issues, please share it here to help others
This comment was generated automatically by a bot. Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
<!-- gh-comment-id:3714722348 -->
@owui-terminator[bot] commented on GitHub (Jan 6, 2026):
🔍 **Similar Issues Found**
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
1. [#19451](https://github.com/open-webui/open-webui/issues/19451) **issue: Images with gpt-image-1 ERROR: No connection adapters were found**
*by 3keyallen3 • Nov 25, 2025 • `bug`*
2. [#19433](https://github.com/open-webui/open-webui/issues/19433) **issue: error while creating an image using openai gpt-image-1**
*by Abdelrahman1993 • Nov 24, 2025 • `bug`*
3. [#20237](https://github.com/open-webui/open-webui/issues/20237) **issue: Image editing stopped working**
*by tomasloksa • Dec 29, 2025 • `bug`, `confirmed issue`*
---
💡 **Tips:**
- If this is a duplicate, please consider closing this issue and adding any additional details to the existing one
- If you found a solution in any of these issues, please share it here to help others
*This comment was generated automatically by a bot.* Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
Ive got an instance running Open WebUI with gpt-image-1.5 via Azure OpenAI, and image generation works fine.
My Configs:
Model: gpt-image-1.5
Image Size: 1024x1024
Image prompt generation: true
Image generation engine: OpenAI
OpenAI API Base URL: https://${AZURE_OPENAI_RESOURCE}/openai/deployments/${AZURE_OPENAI_IMAGE_DEPLOYMENT_NAME}/
OpenAI API Key: Key from Azure OpenAI
OpenAI API Version: 2025-04-01-preview
No additional parameters.
Same for edit, that works too.
Hope this helps!
<!-- gh-comment-id:3715025863 -->
@rozatoo commented on GitHub (Jan 6, 2026):
Hi! :)
Ive got an instance running Open WebUI with gpt-image-1.5 via Azure OpenAI, and image generation works fine.
My Configs:
Model: `gpt-image-1.5`
Image Size: `1024x1024`
Image prompt generation: `true`
Image generation engine: `OpenAI`
OpenAI API Base URL: `https://${AZURE_OPENAI_RESOURCE}/openai/deployments/${AZURE_OPENAI_IMAGE_DEPLOYMENT_NAME}/`
OpenAI API Key: `Key from Azure OpenAI`
OpenAI API Version: `2025-04-01-preview`
No additional parameters.
Same for edit, that works too.
Hope this helps!
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @rutgers-master on GitHub (Jan 6, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/20423
Check Existing Issues
Installation Method
Git Clone
Open WebUI Version
v0.6.43
Ollama Version (if applicable)
No response
Operating System
Debian 12
Browser (if applicable)
Firefox 146.0.1
Confirmation
README.md.Expected Behavior
When using gpt-image-1.5 via Azure, image generation should work...it doesn't.
Actual Behavior
When attempting to create an image using gpt-image-1.5 via Azure, the following is returned:
If I grab the actual POST from Open WebUI and remove the response_format from the body:
"response_format": "b64_json"The image generation works properly.
Steps to Reproduce
Using dalle-3 works...but Azure will be decommissioning DALLE-3 on February 18, 2026.
Logs & Screenshots
Additional Information
No response
@owui-terminator[bot] commented on GitHub (Jan 6, 2026):
🔍 Similar Issues Found
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
#19451 issue: Images with gpt-image-1 ERROR: No connection adapters were found
by 3keyallen3 • Nov 25, 2025 •
bug#19433 issue: error while creating an image using openai gpt-image-1
by Abdelrahman1993 • Nov 24, 2025 •
bug#20237 issue: Image editing stopped working
by tomasloksa • Dec 29, 2025 •
bug,confirmed issue💡 Tips:
This comment was generated automatically by a bot. Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
@rozatoo commented on GitHub (Jan 6, 2026):
Hi! :)
Ive got an instance running Open WebUI with gpt-image-1.5 via Azure OpenAI, and image generation works fine.
My Configs:
Model:
gpt-image-1.5Image Size:
1024x1024Image prompt generation:
trueImage generation engine:
OpenAIOpenAI API Base URL:
https://${AZURE_OPENAI_RESOURCE}/openai/deployments/${AZURE_OPENAI_IMAGE_DEPLOYMENT_NAME}/OpenAI API Key:
Key from Azure OpenAIOpenAI API Version:
2025-04-01-previewNo additional parameters.
Same for edit, that works too.
Hope this helps!