diff --git a/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py b/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py
index f4932508458..36cb9cd49b2 100644
--- a/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py
+++ b/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py
@@ -3168,12 +3168,12 @@ class ModelResponseIterator:
                         "provider_specific_fields", {}
                     )["traffic_type"] = traffic_type
 
-            service_tier = self.response_headers.get("x-gemini-service-tier")
-            if service_tier:
-                if service_tier.lower() == "standard":
-                    setattr(model_response, "service_tier", "default")
-                else:
-                    setattr(model_response, "service_tier", service_tier.lower())
+                service_tier = self.response_headers.get("x-gemini-service-tier")
+                if service_tier:
+                    if service_tier.lower() == "standard":
+                        setattr(model_response, "service_tier", "default")
+                    else:
+                        setattr(model_response, "service_tier", service_tier.lower())
 
             setattr(model_response, "usage", usage)  # type: ignore
 
diff --git a/tests/test_litellm/llms/vertex_ai/gemini/test_vertex_and_google_ai_studio_gemini.py b/tests/test_litellm/llms/vertex_ai/gemini/test_vertex_and_google_ai_studio_gemini.py
index 479f94130d4..ddc404cb8c7 100644
--- a/tests/test_litellm/llms/vertex_ai/gemini/test_vertex_and_google_ai_studio_gemini.py
+++ b/tests/test_litellm/llms/vertex_ai/gemini/test_vertex_and_google_ai_studio_gemini.py
@@ -3520,9 +3520,16 @@ def test_vertex_ai_service_tier_streaming():
         logging_obj=MagicMock(),
         response_headers={"x-gemini-service-tier": "FLEX"},
     )
+    # Undefined when usageMetadata is missing
     result = iterator.chunk_parser(chunk)
 
-    assert result.service_tier == "flex"
+    # But definitely set when usageMetadata is present
+    chunk_with_usage = {
+        "candidates": [{"content": {"parts": [{"text": "hi"}]}}],
+        "usageMetadata": {"promptTokenCount": 1, "candidatesTokenCount": 1, "totalTokenCount": 2}
+    }
+    result_with_usage = iterator.chunk_parser(chunk_with_usage)
+    assert result_with_usage.service_tier == "flex"
 
 
 def test_vertex_ai_service_tier_non_streaming():