### Check for existing issues

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

### What happened?

### Bug Description

For Fireworks AI models, the `cache_read_input_token_cost` field is correctly loaded from `model_info` configuration (visible in `model_map_information`), but it is **not applied** in the actual cost calculation. All input tokens are charged at full `input_cost_per_token` price regardless of `cached_tokens` count.

### Expected Behavior

When `cached_tokens` > 0, the cost calculation should be: ``` input_cost = (prompt_tokens - cached_tokens) * input_cost_per_token + cached_tokens * cache_read_input_token_cost ```

### Actual Behavior

The `input_cost` is calculated as if all tokens were non-cached: ``` input_cost = prompt_tokens * input_cost_per_token ```

### Steps to Reproduce

1. Configure a Fireworks AI model with prompt caching enabled 2. Set `cache_read_input_token_cost` in `model_info` 3. Send a request with cache hits (verified by `cached_tokens` > 0 in response) 4. Observe `cost_breakdown.input_cost` ignores cached token pricing

### Configuration

```yaml model_list: - model_name: GLM-5p1 litellm_params: …