### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### What happened?

When using native image generation feature of OpenWeb UI, I provided LiteLLM base url as OpenAI Base URL. For e.g. https://litellm.example.com/v1 and provided API key.

OpenWeb UI chat window is using model with native function calling and it successfully calls the image generation tool. But the image generation fails with `400: [ERROR: Bad Request]`.

### Steps to Reproduce

1. Go Admin Panel --> Settings --> Images 2. Enable Image generation and Choose image generation engine "Default (Open AI)" 3. Provide OpenAI API Base URL as LiteLLM base URL --> https://litellm.example.com/v1 and Provide API key 4. Enable native function calling in model and select image generation in chat window 5. Send image generation prompt 6. Model calls generate image tool but it fails with 400 Bad Request error

### Relevant log output

```shell <img width="2684" height="1048" alt="Image" src="https://github.com/user-attachments/assets/f185bda5-83a2-49aa-bf44-d57d7eace831" /> ```

### What part of LiteLLM is this about?

Proxy

### What LiteLLM version are you on …