### Check for existing issues

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

### What happened?

[Bug]: litellm.InternalServerError: InternalServerError: Custom_openaiException - AsyncCompletions.create() got an unexpected keyword argument 'client_metadata'. Received Model Group=qwen3.5-0.8b Available Model Group Fallbacks=None LiteLLM Retried: 2 times

my config.yaml is:

general_settings: master_key: sk-1234 # ? your proxy admin key (must start with sk-) database_url: "postgresql://llmproxy:dbpassword9090@db:5432/litellm" store_model_in_db: True

litellm_settings: # set_verbose: True # Uncomment this if you want to see verbose logs; not recommended in production drop_params: True

### Steps to Reproduce

first. i use lmstudio create model, the model name is "qwen3.5-0.8b", then, i use litellm add model,provider , i chose custom openai

<img width="1277" height="258" alt="Image" src="https://github.com/user-attachments/assets/328a27f1-702f-441d-9869-1a66db0eef40" />

then, i add a virtual key to share this model, then ,i use cc-switch to add this model because i use codex ,and test is ok

<img width="692" height="543" alt="Ima…