### Check for existing issues

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

### The Feature

Currently there's only usage -> total token breakdown for all models (input/output/cache...) Having this breakdown per model (currently only shows total tokens) would be really helpful.

### Motivation, pitch

The token breakdown per model would be really helpful to estimate costs for models/providers that are available under subscription limits. For example, with the recent changes to "per use" billing on subscriptions such as github copilot, if you are overpaying for the subscription (or how much benefit you are getting, if you are maxing out your sub).

Since there's already such breakdown tracking for total tokens, it seems a low hanging fruit to achieve it per-model.

### What part of LiteLLM is this about?

UI Dashboard

### LiteLLM is hiring a founding backend engineer, are you interested in joining us and shipping to all our users?

No

### Twitter / LinkedIn details

_No response_