### Check for existing issues

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

### What happened?

token_counter() raises a ValueError when a message content block contains {"type": "image_url", "image_url": None}.

Expected behavior: should return a default token count instead of crashing, since None is a valid edge case that can occur when image_url is optional or not yet populated.

I have a fix ready and will submit a PR immediately after filing this issue.

### Steps to Reproduce

1. Install litellm: pip install litellm

2. Run the following Python script:

import litellm

result = litellm.token_counter( model="gpt-4-vision-preview", messages=[{ "role": "user", "content": [ {"type": "text", "text": "hello"}, {"type": "image_url", "image_url": None}, ], }] )

3. Observe the ValueError is raised instead of returning a token count

### Relevant log output

```shell ValueError: Error getting number of tokens from content list: Invalid image_url type: NoneType. Expected str or dict with 'url' field., default_token_count=None ```

### What part of LiteLLM is this about?

SDK (lit…