### Check for existing issues

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

### The Feature

I saw this merged PR(https://github.com/BerriAI/litellm/pull/30264). But gemma won't work on bedrock now via litellm, because it now is located on mantle endpoint and there should be another base url - https://aws.amazon.com/blogs/machine-learning/introducing-gemma-4-models-on-amazon-bedrock/

### Motivation, pitch

I am trying to use Gemma in our application from bedrock mantle - and now I created workaround for setting correct base url, but it would be nice to have production code clean

so this code:

`import litellm import os

response = litellm.responses( model="bedrock_mantle/google.gemma-4-31b", input="Hello! How can you help me today?", ) print(response)`

failed with the exception: MaskedHTTPStatusError: Client error '401 Unauthorized' for url 'https://bedrock-mantle.us-east-1.api.aws/v1/chat/completions' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/401 litellm.APIConnectionError: Bedrock_mantleException - {"error":{"code":"access_denied","message":"Berm is not enabled for this account","par…