I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.
Installation Method
Docker
Open WebUI Version
0.6.15
Ollama Version (if applicable)
0.9.3
Operating System
Windows 10
Browser (if applicable)
No response
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
The model should be ready to start a conversation immediately after appearing in the model list
Actual Behavior
Model not found Error
Steps to Reproduce
Create a new model using ollama by any method, such as simply copying a model to get a new one
Switch to open webui and observe a new model appearing in the model selector
Click on the model to try a conversation and receive the message "Model not found"
Please try immediately after creating or copying a new model; this issue will disappears after some time
Originally created by @EntropyYue on GitHub (Jun 26, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/15336
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
- [x] I am using the latest version of Open WebUI.
### Installation Method
Docker
### Open WebUI Version
0.6.15
### Ollama Version (if applicable)
0.9.3
### Operating System
Windows 10
### Browser (if applicable)
_No response_
### 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
The model should be ready to start a conversation immediately after appearing in the model list
### Actual Behavior
`Model not found` Error
### Steps to Reproduce
Create a new model using ollama by any method, such as simply copying a model to get a new one
Switch to open webui and observe a new model appearing in the model selector
Click on the model to try a conversation and receive the message "Model not found"
### Logs & Screenshots
```
open-webui-3 | 2025-06-27 06:13:57.967 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.18.0.1:0 - "POST /api/chat/completions HTTP/1.1" 400 - {}
open-webui-3 | 2025-06-27 06:14:06.526 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.18.0.1:0 - "POST /api/chat/completions HTTP/1.1" 400 - {}
open-webui-3 | 2025-06-27 06:14:07.176 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.18.0.1:0 - "POST /api/chat/completions HTTP/1.1" 400 - {}
open-webui-3 | 2025-06-27 06:14:07.746 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.18.0.1:0 - "POST /api/chat/completions HTTP/1.1" 400 - {}
open-webui-3 | 2025-06-27 06:14:08.276 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.18.0.1:0 - "POST /api/chat/completions HTTP/1.1" 400 - {}
```
### Additional Information
Please try immediately after creating or copying a new model; this issue will disappears after some time
GiteaMirror
added the bug label 2026-05-05 18:56:50 -05:00
MODEL_LIST_CACHE_TTL env var has been added with 0447790e6a, try setting it as an empty string, and this should resolve your issue.
<!-- gh-comment-id:3012773140 -->
@tjbck commented on GitHub (Jun 27, 2025):
`MODEL_LIST_CACHE_TTL` env var has been added with 0447790e6ad9b4c543c1f354457c64e56eaca1fa, try setting it as an empty string, and this should resolve your issue.
<!-- gh-comment-id:3015176696 -->
@tjbck commented on GitHub (Jun 28, 2025):
Renamed to `MODELS_CACHE_TTL` with 2b88f66762a6607969ae3a9eb00b03d69127a7a4
@tjbck is there a mechanism to invalidate the cache keys for cached models? I have a scenario where we use the LiteLLM gateway connected to OpenWebUI, and sometimes, when we try to access the new models on OWUI, some % of the requests keep failing with Model not found error.
<!-- gh-comment-id:3334634711 -->
@saivarunk commented on GitHub (Sep 25, 2025):
@tjbck is there a mechanism to invalidate the cache keys for cached models? I have a scenario where we use the LiteLLM gateway connected to OpenWebUI, and sometimes, when we try to access the new models on OWUI, some % of the requests keep failing with `Model not found` error.
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 @EntropyYue on GitHub (Jun 26, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/15336
Check Existing Issues
Installation Method
Docker
Open WebUI Version
0.6.15
Ollama Version (if applicable)
0.9.3
Operating System
Windows 10
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
The model should be ready to start a conversation immediately after appearing in the model list
Actual Behavior
Model not foundErrorSteps to Reproduce
Create a new model using ollama by any method, such as simply copying a model to get a new one
Switch to open webui and observe a new model appearing in the model selector
Click on the model to try a conversation and receive the message "Model not found"
Logs & Screenshots
Additional Information
Please try immediately after creating or copying a new model; this issue will disappears after some time
@tjbck commented on GitHub (Jun 27, 2025):
MODEL_LIST_CACHE_TTLenv var has been added with0447790e6a, try setting it as an empty string, and this should resolve your issue.@tjbck commented on GitHub (Jun 28, 2025):
Renamed to
MODELS_CACHE_TTLwith2b88f66762@saivarunk commented on GitHub (Sep 25, 2025):
@tjbck is there a mechanism to invalidate the cache keys for cached models? I have a scenario where we use the LiteLLM gateway connected to OpenWebUI, and sometimes, when we try to access the new models on OWUI, some % of the requests keep failing with
Model not founderror.