### Check for existing issues

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

### What happened?

I configured a rate limit for a locally served model. When the rate limit is hit, I get back the following error: ```Python RateLimitError: Error code: 429 - {'error': {'message': 'No deployments available for selected model.', 'type': 'None', 'param': 'None', 'code': '429'}} ```

For me, that error message is confusing. The exception class is the correct one, but "No deployments available" is misleading. The text comes from the `RouterErrors` enum in _types/router.py_, from the `no_deployments_available` member. There is a `user_defined_ratelimit_error` member as well, which (or something similar) might be more appropriate.

I also experienced another unexpected behavior. I use the `litellm` command proxy that comes with the Python package. When the rate limit is exceeded, aside from the usual log, the stack trace for the exception is printed three times on the console. I see two problems with this:

1. Why print it in the first place? 2. Why three times? I explicitly set `num_retries: 0` in the router configuration.

The configuration: ```yam…