### Check for existing issues

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

### What happened?

A bug happened! I would like to reopen this ticket with same issue.. https://github.com/BerriAI/litellm/issues/6954

### Steps to Reproduce

1. any prompt with exact match hash value will work , doesnt call the llm 2nd time. 2. Semantic cache worked only 1 time rest failed. Prompt with slight mismatch will call llm backend everytime.. Cache miss happened most of the time

### Relevant log output

```shell

```

### What part of LiteLLM is this about?

_No response_

### What LiteLLM version are you on ?

LiteLLM: Current Version = 1.90.0

### Twitter / LinkedIn details

_No response_