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 f9ed8cea9b5..8c4bb1aa0c5 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
@@ -998,6 +998,8 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                 response_modalities.append("IMAGE")
             elif modality == "audio":
                 response_modalities.append("AUDIO")
+            elif modality == "video":
+                response_modalities.append("VIDEO")
             else:
                 response_modalities.append("MODALITY_UNSPECIFIED")
         return response_modalities
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 51f13affa3f..40f9f4e7910 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
@@ -880,6 +880,12 @@ def test_vertex_ai_usage_metadata_with_image_tokens_in_prompt():
     )
 
 
+def test_map_response_modalities_video():
+    """The video modality maps to VIDEO instead of MODALITY_UNSPECIFIED, which Gemini rejects."""
+    v = VertexGeminiConfig()
+    assert v.map_response_modalities(["text", "video"]) == ["TEXT", "VIDEO"]
+
+
 def test_vertex_ai_usage_metadata_accumulates_duplicate_modalities():
     """Ensure _calculate_usage accumulates repeated modality entries."""
     v = VertexGeminiConfig()