### Check for existing issues

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

### What happened?

Databricks supports response_format, but the model_info remains out-of-date.

The model_info's 'supports_response_schema' gives info on whether or not we can pass arg `{"type": "json_schema", "json_schema": {...}}` as a response_format to the completion request. For databricks models, when we run ```python model = get_model_info("databricks/databricks-meta-llama-3-1-8b-instruct") model['supports_response_schema'] # None ```

we expect this to fail: ```python iimport litellm import os

os.environ['DATABRICKS_API_KEY']= "..." os.environ['DATABRICKS_API_BASE'] = "..."

model_id = "databricks/databricks-meta-llama-3-1-8b-instruct" response_format = { "type": "json_schema", "json_schema": { "name": "ingredient_extraction", "schema": { "type": "object", "properties": { "recipe_name": {"type": "string"}, "difficulty": {"type": "string", "enum": ["easy", "medium", "hard"]}, "ingredients": { "type": "array", "item…