### Check for existing issues

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

### What happened?

When using Xiaomi MiMo models (`MiMo-V2-Pro` and `MiMo-V2-Omni`) with the `output_config` parameter, requests fail with:

```javascript Xiaomi_mimoException - AsyncCompletions.create() got an unexpected keyword argument 'output_config' ```

__Test Results Summary:__

__MiMo-V2-Pro:__

- `/v1/messages` + output_config: ❌ FAILS (all combinations) - `/v1/chat/completions` + output_config alone: ✅ WORKS (only scenario that works) - `/v1/chat/completions` + output_config + streaming: ❌ FAILS

__MiMo-V2-Omni:__

- `/v1/messages` + output_config: ❌ FAILS (all combinations) - `/v1/chat/completions` + output_config: ❌ FAILS (all combinations)

__Expected:__ LiteLLM should filter provider-specific parameters (like `output_config`) before calling the provider's SDK, similar to how other Anthropic-specific parameters are handled.

__Actual:__ The parameter is passed through unfiltered, breaking Xiaomi model requests.

### Steps to Reproduce

``` import requests

BASE_URL = "https://your-litellm-proxy" API_KEY = "your-api-key" headers = {"Authorization": …