mirror of
https://github.com/open-webui/open-webui.git
synced 2026-11-17 03:03:27 -06:00
[GH-ISSUE #16445] feat: increase OpenAI API compatibility by redirecting API calls going to '/v1' #33434
Reference in New Issue
Block a user
Originally created by @c0008 on GitHub (Aug 10, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/16445
Check Existing Issues
Problem Description
When using Open-WebUI's own API endpoint in other tools there can be compatibility issues with the url format after the base url. In these tools you have to provide a base url, like the string 'http://localhost:8080/api' for open-webui. Then for api requests the tool extends this string, e.g. for the model list it would add '/v1/models', so the resulting url would be 'http://localhost:8080/api/v1/models'. This is working with the OpenAI API, llama.cpp server, Ollama and GPU-Stack but not with Open-WebUI when you want to use it as a unified LLM provider. Open-WebUI would only accept 'http://localhost:8080/api/models'.
Desired Solution you'd like
Handle api calls like '/v1/models' or '/v1/chat/completions' the same as '/models' or '/chat/completions'.
Alternatives Considered
No response
Additional Context
This is not an issue with tools that expect the '/v1' to be part of the base url.
@tjbck commented on GitHub (Aug 10, 2025):
Addressed with
32a022a823