### Check for existing issues

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

### What happened?

Litellm initiates an HTTP request on module import by default. This is very slow and consideed hostile.

this should be lazily done when needed or opt-in.

Curently `get_model_cost_map` is called on module load. By default this calls `fetch_remote_model_cost_map`.

Importing a module should be quick and should not require a user to have a network connection on import.

### Steps to Reproduce

1. 2. 3.

### Relevant log output

```shell

```

### What part of LiteLLM is this about?

_No response_

### What LiteLLM version are you on ?

v1.81.x

### Twitter / LinkedIn details

_No response_