Gpt4 models missing when starting webui with OPENAI_API_KEY

[Seviks]

I'm starting the webui with:
docker run -d -p 3000:8080 -e OPENAI_API_KEY="secretapikey" -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main

I can then select my Ollama models or gtp-3.5-turbo, gtp-3.5-turb-0125 or gtp-3.5-turbo-0301.

How can I use the gpt4 models?

Some info:

• Open web ui version v0.1.124
• Docker is running on Windows 11
• Ollama (v0.1.32) is running in the background in wsl2.
• GPT-3.5 models work
• OpenAI: There are credits and usage limit is not reached

[justinh-rahb]

If the other gpt-* models are showing, just not the gpt-4* ones then I'd say it seems your API key is restricted.

[Seviks]

Thanks for your hint. This may be, as I'm not experienced with the openAI API. But in the API settigns it seems ok:

Fruther hints are appreciated.

If I enter a wrong key, no model is shown.

[cheahjs]

https://help.openai.com/en/articles/7102672-how-can-i-access-gpt-4-gpt-4-turbo-and-gpt-4o

After you have made a successful payment of $5 or more (usage tier 1), you'll be able to access the GPT-4, GPT-4 Turbo, and GPT-4o models via the OpenAI API.

[Seviks]

I'm already on Tier 1, so this is not the solution. However, I replicated every step on my home computer (running Pop-Os) with the same version of open-webui and there everything works fine. So it seems I have to check the configuration on the windows computer on my end.
Thank you for your answers and sorry for the noise (I will add a solution if I find one).

[Seviks]

After I removed container and the volume and recreated the container with the command above, all is working as expected.
Maybe it was because for the first time I run
docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main

but I couldn't replicate the problem