diff --git a/litellm/llms/anthropic/chat/guardrail_translation/handler.py b/litellm/llms/anthropic/chat/guardrail_translation/handler.py
index 6f502e9870b..656eab5c17b 100644
--- a/litellm/llms/anthropic/chat/guardrail_translation/handler.py
+++ b/litellm/llms/anthropic/chat/guardrail_translation/handler.py
@@ -395,6 +395,8 @@ class AnthropicMessagesHandler(BaseTranslation):
                     input_type="response",
                     logging_obj=litellm_logging_obj,
                 )
+            else:
+                verbose_proxy_logger.debug("Skipping output guardrail - model response has no choices")
             return responses_so_far
 
         string_so_far = self.get_streaming_string_so_far(responses_so_far)
diff --git a/litellm/llms/openai/responses/guardrail_translation/handler.py b/litellm/llms/openai/responses/guardrail_translation/handler.py
index 523becfd89a..ad3d4c932d4 100644
--- a/litellm/llms/openai/responses/guardrail_translation/handler.py
+++ b/litellm/llms/openai/responses/guardrail_translation/handler.py
@@ -447,6 +447,8 @@ class OpenAIResponsesHandler(BaseTranslation):
                         logging_obj=litellm_logging_obj,
                     )
                     return responses_so_far
+            else:
+                verbose_proxy_logger.debug("Skipping output guardrail - model response has no choices")
         # model_response_stream = OpenAiResponsesToChatCompletionStreamIterator.translate_responses_chunk_to_openai_stream(final_chunk)
         # tool_calls = model_response_stream.choices[0].tool_calls
         # convert openai response to model response