### Check for existing issues

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

### What happened?

## Summary

`litellm.token_counter()` raises a `ValueError` when a message content list contains a `video_url` block.

The error says supported content item types are `text`, `image_url`, `tool_use`, `tool_result`, and `thinking`, but multimodal OpenAI-compatible messages may include `video_url` content blocks.

## Environment

- Python: 3.12 - LiteLLM: please fill in your installed version - OS: Windows - Model passed to token_counter: `gpt-4o`

## Minimal Reproduction

```python from litellm import token_counter

messages = [ { "role": "user", "content": [ {"type": "text", "text": "Please describe this video."}, { "type": "video_url", "video_url": { "url": "data:video/mp4;base64,AAAA" }, }, ], } ]

print(token_counter(model="gpt-4o", messages=messages))

### Steps to Reproduce

1. add role: tool tool_call_id: chatcmpl-tool-a982416a7aff27fa name: read_video content: - type: video_url …