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 e5b78aaef8..be9f5d5eb6 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
@@ -980,9 +980,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
         if "promptTokensDetails" in usage_metadata:
             for detail in usage_metadata["promptTokensDetails"]:
                 if detail["modality"] == "AUDIO":
-                    audio_tokens = detail["tokenCount"]
+                    audio_tokens = detail.get("tokenCount", 0)
                 elif detail["modality"] == "TEXT":
-                    text_tokens = detail["tokenCount"]
+                    text_tokens = detail.get("tokenCount", 0)
         if "thoughtsTokenCount" in usage_metadata:
             reasoning_tokens = usage_metadata["thoughtsTokenCount"]
         prompt_tokens_details = PromptTokensDetailsWrapper(