### Check for existing issues

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

### The Feature

Would it be possible to support configuring different context-compression trigger thresholds and compression target thresholds for different models?

### Motivation, pitch

I have multiple models, each with a different context window—some are 128K, and some are 64K. The configuration in the current documentation seems to apply uniformly to all models (https://docs.litellm.ai/docs/completion/prompt_compression), which appears to be quite unfavorable for models with larger context windows.

### What part of LiteLLM is this about?

Proxy

### 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_