diff --git a/litellm/llms/custom_httpx/llm_http_handler.py b/litellm/llms/custom_httpx/llm_http_handler.py
index 01fe36acda..fa4cd5dcc6 100644
--- a/litellm/llms/custom_httpx/llm_http_handler.py
+++ b/litellm/llms/custom_httpx/llm_http_handler.py
@@ -978,6 +978,7 @@ class BaseLLMHTTPHandler:
         timeout: Optional[Union[float, httpx.Timeout]] = None,
         client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
         _is_async: bool = False,
+        fake_stream: bool = False,
     ) -> Union[
         ResponsesAPIResponse,
         BaseResponsesAPIStreamingIterator,
@@ -1100,6 +1101,7 @@ class BaseLLMHTTPHandler:
         extra_body: Optional[Dict[str, Any]] = None,
         timeout: Optional[Union[float, httpx.Timeout]] = None,
         client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
+        fake_stream: bool = False,
     ) -> Union[ResponsesAPIResponse, BaseResponsesAPIStreamingIterator]:
         """
         Async version of the responses API handler.
diff --git a/litellm/responses/main.py b/litellm/responses/main.py
index 43f37bdbc6..aec2f8fe4a 100644
--- a/litellm/responses/main.py
+++ b/litellm/responses/main.py
@@ -232,6 +232,9 @@ def responses(
             timeout=timeout or request_timeout,
             _is_async=_is_async,
             client=kwargs.get("client"),
+            fake_stream=responses_api_provider_config.should_fake_stream(
+                model=model, stream=stream, custom_llm_provider=custom_llm_provider
+            ),
         )
 
         return response