diff --git a/litellm/responses/litellm_completion_transformation/handler.py b/litellm/responses/litellm_completion_transformation/handler.py
index 505b5b09433..93481ba4493 100644
--- a/litellm/responses/litellm_completion_transformation/handler.py
+++ b/litellm/responses/litellm_completion_transformation/handler.py
@@ -6,6 +6,7 @@ from collections.abc import Coroutine, Mapping
 from typing import Final
 
 import litellm
+from litellm._internal_context import is_internal_call
 from litellm.responses.additional_tools import hoist_additional_tools
 from litellm.responses.litellm_completion_transformation.streaming_iterator import (
     LiteLLMCompletionStreamingIterator,
@@ -113,9 +114,13 @@ class LiteLLMCompletionTransformationHandler:
         acompletion_args.update(litellm_completion_request)
         acompletion_args["_skip_responses_api_bridge"] = True
 
-        litellm_completion_response: Final[ModelResponse | litellm.CustomStreamWrapper] = await litellm.acompletion(
-            **acompletion_args,
-        )
+        token: Final = is_internal_call.set(True)
+        try:
+            litellm_completion_response: Final[ModelResponse | litellm.CustomStreamWrapper] = await litellm.acompletion(
+                **acompletion_args
+            )
+        finally:
+            is_internal_call.reset(token)
 
         if isinstance(litellm_completion_response, ModelResponse):
             responses_api_response: Final[ResponsesAPIResponse] = (
diff --git a/tests/unit/responses/litellm_completion_transformation/test_handler.py b/tests/unit/responses/litellm_completion_transformation/test_handler.py
index bb374b90f4e..33c52d04289 100644
--- a/tests/unit/responses/litellm_completion_transformation/test_handler.py
+++ b/tests/unit/responses/litellm_completion_transformation/test_handler.py
@@ -21,6 +21,7 @@ import httpx
 import pytest
 
 import litellm
+from litellm._internal_context import is_internal_call
 from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler
 from litellm.responses.litellm_completion_transformation.handler import (
     LiteLLMCompletionTransformationHandler,
@@ -55,12 +56,13 @@ def test_sync_fallback_tags_skip_responses_api_bridge():
 
 
 @pytest.mark.asyncio
-async def test_async_fallback_tags_skip_responses_api_bridge():
+async def test_async_fallback_tags_internal_call_and_skip_responses_api_bridge():
     handler = LiteLLMCompletionTransformationHandler()
     captured: dict = {}
 
     async def fake_acompletion(**kwargs):
         captured.update(kwargs)
+        captured["is_internal_call"] = is_internal_call.get()
         raise _StopForwarding()
 
     with patch("litellm.acompletion", fake_acompletion):
@@ -75,6 +77,8 @@ async def test_async_fallback_tags_skip_responses_api_bridge():
             await coro
 
     assert captured.get("_skip_responses_api_bridge") is True
+    assert captured["is_internal_call"] is True
+    assert is_internal_call.get() is False
 
 
 _CODEX_ADDITIONAL_TOOLS_ITEM = {