[GH-ISSUE #4610] Support for Manually Customizing Models When API Providers Don't Support /v1/models Endpoint #13671

New Issue

GiteaMirror · 2026-04-19T20:19:47-05:00

GiteaMirror commented

2026-04-19 20:19:47 -05:00

Originally created by @zhiqing0205 on GitHub (Aug 15, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/4610

Is your feature request related to a problem? Please describe.
I'm frustrated because some API providers do not support the /v1/models endpoint to retrieve available models, but they do support the /v1/chat/completions endpoint for normal chat interactions. This limitation prevents the use of certain API providers with OpenWebUI, as it currently relies on the /v1/models endpoint to detect available models.

Describe the solution you'd like
I would like to request the ability to manually customize or input a model in the top left corner of the interface. This feature would allow users to specify the model they want to use when the API provider does not support the /v1/models endpoint, enabling broader compatibility with different API providers.

Describe alternatives you've considered
An alternative could be implementing a fallback mechanism where, if the /v1/models endpoint is not supported by the API provider, users could still input a model manually or select from a predefined list of commonly used models.

This enhancement would greatly improve flexibility and compatibility with a wider range of API providers.

Originally created by @zhiqing0205 on GitHub (Aug 15, 2024). Original GitHub issue: https://github.com/open-webui/open-webui/issues/4610 **Is your feature request related to a problem? Please describe.** I'm frustrated because some API providers do not support the `/v1/models` endpoint to retrieve available models, but they do support the `/v1/chat/completions` endpoint for normal chat interactions. This limitation prevents the use of certain API providers with OpenWebUI, as it currently relies on the `/v1/models` endpoint to detect available models. **Describe the solution you'd like** I would like to request the ability to manually customize or input a model in the top left corner of the interface. This feature would allow users to specify the model they want to use when the API provider does not support the `/v1/models` endpoint, enabling broader compatibility with different API providers. **Describe alternatives you've considered** An alternative could be implementing a fallback mechanism where, if the `/v1/models` endpoint is not supported by the API provider, users could still input a model manually or select from a predefined list of commonly used models. This enhancement would greatly improve flexibility and compatibility with a wider range of API providers.

GiteaMirror closed this issue

2026-04-19 20:19:47 -05:00

GiteaMirror commented

2026-04-19 20:19:48 -05:00

@moblangeois commented on GitHub (Aug 15, 2024):

In addition, I'd like to point out that it is the case with perplexity API.

@moblangeois commented on GitHub (Aug 15, 2024): In addition, I'd like to point out that it is the case with perplexity API.

GiteaMirror referenced this issue

2026-04-19 22:47:15 -05:00

[GH-ISSUE #13671] issue: I Can't show model list at 'user role account' #16992

GiteaMirror referenced this issue

2026-04-25 06:27:03 -05:00

[GH-ISSUE #13671] issue: I Can't show model list at 'user role account' #32521

GiteaMirror referenced this issue

2026-05-05 17:46:12 -05:00

[GH-ISSUE #13671] issue: I Can't show model list at 'user role account' #55658

Sign in to join this conversation.