### Check for existing issues

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

### What happened?

A bug happened! i have config.yaml with below details - model_name: gpt-5.4 litellm_params: api_base: https://xxxxxxxx/ api_key: "xxxxx" model: azure/gpt-5.4 model_info: disable_background_health_check: true

also set health_check_skip_disabled_background_models: true in general_setting level but still litellm is crawing the models every 30 secs to verify its health with test prompt.

Is it expected behaviour?

### Steps to Reproduce

1. have litellm_config.yaml with model details with background_heath_checks=false. 2.also have health_check_skip_disabled_background_models: true in general_setting as per the litellm documentation page - https://docs.litellm.ai/docs/proxy/health#disable-background-health-checks-for-specific-models 3. i am using litellm 1.82.3-stable version. 4. I still see litellm is crawling every 30 seconds on the given modes.

<img width="1720" height="611" alt="Image" src="https://github.com/user-attachments/assets/298045d2-57a3-41ab-af85-cddf4b7e5a89" />

### Relevant log output

```shell

`…