diff --git a/litellm/assistants/main.py b/litellm/assistants/main.py
index 33568a5f48..acb37b1e6f 100644
--- a/litellm/assistants/main.py
+++ b/litellm/assistants/main.py
@@ -131,10 +131,6 @@ def get_assistants(
             timeout=timeout,
             max_retries=optional_params.max_retries,
             organization=organization,
-            order=getattr(optional_params, "order", "desc"),
-            limit=getattr(optional_params, "limit", 20),
-            before=getattr(optional_params, "before", None),
-            after=getattr(optional_params, "after", None),
             client=client,
             aget_assistants=aget_assistants,  # type: ignore
         )  # type: ignore
diff --git a/litellm/llms/openai/openai.py b/litellm/llms/openai/openai.py
index 1a6a278a1f..a7ab3a72e0 100644
--- a/litellm/llms/openai/openai.py
+++ b/litellm/llms/openai/openai.py
@@ -1928,10 +1928,6 @@ class OpenAIAssistantsAPI(BaseLLM):
         max_retries: Optional[int],
         organization: Optional[str],
         client: Optional[AsyncOpenAI],
-        order: Optional[str] = 'desc',
-        limit: Optional[int] = 20,
-        before: Optional[str] = None,
-        after: Optional[str] = None,
     ) -> AsyncCursorPage[Assistant]:
         openai_client = self.async_get_openai_client(
             api_key=api_key,
@@ -1941,16 +1937,8 @@ class OpenAIAssistantsAPI(BaseLLM):
             organization=organization,
             client=client,
         )
-        request_params = {
-            "order": order,
-            "limit": limit,
-        }
-        if before:
-            request_params["before"] = before
-        if after:
-            request_params["after"] = after
-            
-        response = await openai_client.beta.assistants.list(**request_params)
+
+        response = await openai_client.beta.assistants.list()
 
         return response
 
@@ -1965,11 +1953,7 @@ class OpenAIAssistantsAPI(BaseLLM):
         max_retries: Optional[int],
         organization: Optional[str],
         client: Optional[AsyncOpenAI],
-        aget_assistants: Literal[True],
-        order: Optional[str] = 'desc',
-        limit: Optional[int] = 20,
-        before: Optional[str] = None,
-        after: Optional[str] = None,
+        aget_assistants: Literal[True], 
     ) -> Coroutine[None, None, AsyncCursorPage[Assistant]]:
         ...
 
@@ -1982,11 +1966,7 @@ class OpenAIAssistantsAPI(BaseLLM):
         max_retries: Optional[int],
         organization: Optional[str],
         client: Optional[OpenAI],
-        aget_assistants: Optional[Literal[False]],
-        order: Optional[str] = 'desc',
-        limit: Optional[int] = 20,
-        before: Optional[str] = None,
-        after: Optional[str] = None,
+        aget_assistants: Optional[Literal[False]], 
     ) -> SyncCursorPage[Assistant]: 
         ...
 
@@ -2001,10 +1981,6 @@ class OpenAIAssistantsAPI(BaseLLM):
         organization: Optional[str],
         client=None,
         aget_assistants=None,
-        order: Optional[str] = 'desc',
-        limit: Optional[int] = 20,
-        before: Optional[str] = None,
-        after: Optional[str] = None,
     ):
         if aget_assistants is not None and aget_assistants is True:
             return self.async_get_assistants(
@@ -2014,10 +1990,6 @@ class OpenAIAssistantsAPI(BaseLLM):
                 max_retries=max_retries,
                 organization=organization,
                 client=client,
-                order=order,
-                limit=limit,
-                before=before,
-                after=after,
             )
         openai_client = self.get_openai_client(
             api_key=api_key,
@@ -2028,18 +2000,7 @@ class OpenAIAssistantsAPI(BaseLLM):
             client=client,
         )
 
-        request_params = {
-            "order": order,
-            "limit": limit,
-        }
-
-        if before:
-            request_params["before"] = before
-        if after:
-            request_params["after"] = after
-
-
-        response = openai_client.beta.assistants.list(**request_params)
+        response = openai_client.beta.assistants.list()
 
         return response
 
diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py
index 2435fb92cf..0e614b0ae3 100644
--- a/litellm/proxy/proxy_server.py
+++ b/litellm/proxy/proxy_server.py
@@ -4434,10 +4434,6 @@ async def get_assistants(
     request: Request,
     fastapi_response: Response,
     user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
-    order: Optional[str] = Query(None, description="Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order."),
-    limit: Optional[int] = Query(None, description="A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20."),
-    after: Optional[str] = Query(None, description="A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list."),
-    before: Optional[str] = Query(None, description="A cursor for use in pagination. before is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list."),
 ):
     """
     Returns a list of assistants.
@@ -4460,28 +4456,6 @@ async def get_assistants(
             proxy_config=proxy_config,
         )
 
-        # Validate `order` parameter
-        if order and order not in ["asc", "desc"]:
-            raise HTTPException(
-                status_code=400, detail={"error": "order must be 'asc' or 'desc'"}
-            )
-        if order:
-            data["order"] = order
-
-        # Validate `limit` parameter
-        if limit is not None:
-            if not (1 <= limit <= 100):
-                raise HTTPException(
-                    status_code=400, detail={"error": "limit must be between 1 and 100"}
-                )
-            data["limit"] = limit
-
-        # Add pagination cursors if provided
-        if after:
-            data["after"] = after
-        if before:
-            data["before"] = before
-
         # for now use custom_llm_provider=="openai" -> this will change as LiteLLM adds more providers for acreate_batch
         if llm_router is None:
             raise HTTPException(