diff --git a/litellm/constants.py b/litellm/constants.py
index 0288c45e40..b4551a78f5 100644
--- a/litellm/constants.py
+++ b/litellm/constants.py
@@ -18,6 +18,7 @@ SINGLE_DEPLOYMENT_TRAFFIC_FAILURE_THRESHOLD = 1000  # Minimum number of requests
 REPEATED_STREAMING_CHUNK_LIMIT = 100  # catch if model starts looping the same chunk while streaming. Uses high default to prevent false positives.
 #### Networking settings ####
 request_timeout: float = 6000  # time in seconds
+STREAM_SSE_DONE_STRING: str = "[DONE]"
 
 LITELLM_CHAT_PROVIDERS = [
     "openai",
diff --git a/litellm/responses/streaming_iterator.py b/litellm/responses/streaming_iterator.py
index 13112e3647..7325e4e645 100644
--- a/litellm/responses/streaming_iterator.py
+++ b/litellm/responses/streaming_iterator.py
@@ -5,17 +5,15 @@ from typing import Any, AsyncIterator, Dict, Optional, Union
 
 import httpx
 
+from litellm.constants import STREAM_SSE_DONE_STRING
 from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
 from litellm.llms.base_llm.responses.transformation import BaseResponsesAPIConfig
 from litellm.types.llms.openai import (
-    ResponsesAPIResponse,
     ResponsesAPIStreamEvents,
     ResponsesAPIStreamingResponse,
 )
 from litellm.utils import CustomStreamWrapper
 
-COMPLETED_OPENAI_CHUNK_TYPE = "response.completed"
-
 
 class BaseResponsesAPIStreamingIterator:
     """
@@ -50,7 +48,7 @@ class BaseResponsesAPIStreamingIterator:
             return None
 
         # Handle "[DONE]" marker
-        if chunk == "[DONE]":
+        if chunk == STREAM_SSE_DONE_STRING:
             self.finished = True
             return None