### Check for existing issues

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

### What happened?

I am trying to configure the Nemotron 3 Super 120B model to work with LiteLLM through Cloudflare.

https://developers.cloudflare.com/workers-ai/models/nemotron-3-120b-a12b/

I have my credentials set and when adding the model the Test Connection fails.

This is a Docker deployment through docker compose.

### Steps to Reproduce

1. Configure Workers AI credentials. 2. Add Model. 3. Select Cloudflare as the Provider. 4. Enter a custom model: @cf/nvidia/nemotron-3-120b-a12b 5. Select existing credentials. 6. Click Test Connection. 7. Watch it crash and burn.

### Relevant log output

```shell This appears as an Error: in the dialog:

'response' Traceback (most recent call last): File "/usr/lib/python3.13/site-packages/litellm/main.py", line 620, in acompletion response = await init_response ^^^^^^^^^^^^^^^^^^^ File "/usr/lib/python3.13/site-packages/litellm/llms/custom_httpx/llm_http_handler.py", line 319, in async_completion initial_response = provider_config.transform_response( model=model, ...<9 lines>... json_mode=json_mode, ) File "/usr/li…