### What happened?

Here is a minimal example to reproduce the problem:

`litellm_config.yaml`:

```yaml model_list: - model_name: elevenlabs-eleven-multilingual-v2 litellm_params: model: elevenlabs/eleven_multilingual_v2 api_key: ... general_settings: master_key: sk-1234 litellm_settings: callbacks: custom_callbacks.proxy_handler_instance ```

`custom_callbacks.py`:

```python import litellm from litellm.integrations.custom_logger import CustomLogger

class MyCustomHandler(CustomLogger): async def async_log_success_event(self, kwargs, response_obj, start_time, end_time): cost_in_usd = litellm.completion_cost(completion_response=response_obj) print(cost_in_usd)

proxy_handler_instance = MyCustomHandler() ```

Run the proxy:

```bash docker run \ -v $(pwd)/litellm_config.yaml:/app/config.yaml \ -v $(pwd)/custom_callbacks.py:/app/custom_callbacks.py \ -p 4000:4000 \ ghcr.io/berriai/litellm:v1.80.10.rc.2 \ --config /app/config.yaml ```

Python script to send a request:

```python from openai import OpenAI

client = OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000")

response = client.audio.speech.create( model="e…