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 678877c0721..818dc8d45f0 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
@@ -1380,6 +1380,8 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
             _content_str = ""
             if "text" in part:
                 text_content = part["text"]
+                if text_content is None:
+                    continue
                 # Check if text content is audio data URI - if so, exclude from text content
                 if text_content.startswith("data:audio") and ";base64," in text_content:
                     try:
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 20e7aec377b..4e323fa2821 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
@@ -441,6 +441,25 @@ def test_vertex_ai_empty_content():
     assert reasoning_content is None
 
 
+def test_vertex_ai_null_text_part_is_ignored():
+    from litellm.llms.vertex_ai.gemini.vertex_and_google_ai_studio_gemini import (
+        VertexGeminiConfig,
+    )
+    from litellm.types.llms.vertex_ai import HttpxPartType
+
+    v = VertexGeminiConfig()
+    parts = cast(
+        List[HttpxPartType],
+        [
+            {"text": None},
+            {"text": "Generated image"},
+        ],
+    )
+    content, reasoning_content = v.get_assistant_content_message(parts=parts)
+    assert content == "Generated image"
+    assert reasoning_content is None
+
+
 @pytest.mark.parametrize(
     "usage_metadata, inclusive, expected_usage",
     [