import litellm from litellm import CustomLLM, completion, get_llm_provider class MyCustomLLM(CustomLLM): def completion(self, *args, **kwargs) -> litellm.ModelResponse: return litellm.completion( model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hello world"}], mock_response="Hi!", ) # type: ignore async def acompletion(self, *args, **kwargs) -> litellm.ModelResponse: return litellm.completion( model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hello world"}], mock_response="Hi!", ) # type: ignore my_custom_llm = MyCustomLLM()