diff --git a/litellm/litellm_core_utils/exception_mapping_utils.py b/litellm/litellm_core_utils/exception_mapping_utils.py
index a4a30fc31..ca1de75be 100644
--- a/litellm/litellm_core_utils/exception_mapping_utils.py
+++ b/litellm/litellm_core_utils/exception_mapping_utils.py
@@ -1124,10 +1124,13 @@ def exception_type(  # type: ignore  # noqa: PLR0915
                             ),
                         ),
                     )
-                elif "500 Internal Server Error" in error_str:
+                elif (
+                    "500 Internal Server Error" in error_str
+                    or "The model is overloaded." in error_str
+                ):
                     exception_mapping_worked = True
-                    raise ServiceUnavailableError(
-                        message=f"litellm.ServiceUnavailableError: VertexAIException - {error_str}",
+                    raise litellm.InternalServerError(
+                        message=f"litellm.InternalServerError: VertexAIException - {error_str}",
                         model=model,
                         llm_provider="vertex_ai",
                         litellm_debug_info=extra_information,
diff --git a/tests/local_testing/test_stream_chunk_builder.py b/tests/local_testing/test_stream_chunk_builder.py
index a65d440a7..2548abdb7 100644
--- a/tests/local_testing/test_stream_chunk_builder.py
+++ b/tests/local_testing/test_stream_chunk_builder.py
@@ -205,8 +205,8 @@ def test_stream_chunk_builder_litellm_usage_chunks():
             complete_response=True,
             stream_options={"include_usage": True},
         )
-    except litellm.ServiceUnavailableError as e:
-        pytest.skip(f"ServiceUnavailableError - {str(e)}")
+    except litellm.InternalServerError as e:
+        pytest.skip(f"Skipping test due to internal server error - {str(e)}")
 
     usage: litellm.Usage = response.usage