diff --git a/litellm/llms/anthropic.py b/litellm/llms/anthropic.py
index d836ed8db54..24d889b0f46 100644
--- a/litellm/llms/anthropic.py
+++ b/litellm/llms/anthropic.py
@@ -258,8 +258,9 @@ class AnthropicChatCompletion(BaseLLM):
         self.async_handler = AsyncHTTPHandler(
             timeout=httpx.Timeout(timeout=600.0, connect=5.0)
         )
+        data["stream"] = True
         response = await self.async_handler.post(
-            api_base, headers=headers, data=json.dumps(data)
+            api_base, headers=headers, data=json.dumps(data), stream=True
         )
 
         if response.status_code != 200:
diff --git a/litellm/llms/custom_httpx/http_handler.py b/litellm/llms/custom_httpx/http_handler.py
index dd03e7dbecd..3ab85772362 100644
--- a/litellm/llms/custom_httpx/http_handler.py
+++ b/litellm/llms/custom_httpx/http_handler.py
@@ -41,13 +41,16 @@ class AsyncHTTPHandler:
         data: Optional[Union[dict, str]] = None,  # type: ignore
         params: Optional[dict] = None,
         headers: Optional[dict] = None,
+        stream: Optional[bool] = False
     ):
-        response = await self.client.post(
+        req = self.client.build_request(
+            "POST",
             url,
             data=data,  # type: ignore
             params=params,
-            headers=headers,
+            headers=headers
         )
+        response = await self.client.send(req, stream=stream)
         return response
 
     def __del__(self) -> None: