diff --git a/litellm/__pycache__/main.cpython-311.pyc b/litellm/__pycache__/main.cpython-311.pyc
index 8a8060b8d..322d57454 100644
Binary files a/litellm/__pycache__/main.cpython-311.pyc and b/litellm/__pycache__/main.cpython-311.pyc differ
diff --git a/litellm/__pycache__/utils.cpython-311.pyc b/litellm/__pycache__/utils.cpython-311.pyc
index 57a8d8591..bbb8e3fd3 100644
Binary files a/litellm/__pycache__/utils.cpython-311.pyc and b/litellm/__pycache__/utils.cpython-311.pyc differ
diff --git a/litellm/utils.py b/litellm/utils.py
index 874d91b9f..90f0b7c4c 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -1908,6 +1908,7 @@ def exception_type(model, original_exception, custom_llm_provider):
             elif custom_llm_provider == "vllm":
                 if hasattr(original_exception, "status_code"):
                     if original_exception.status_code == 0:
+                        exception_mapping_worked = True
                         raise APIConnectionError(
                             message=f"VLLMException - {original_exception.message}",
                             llm_provider="vllm",
@@ -1931,7 +1932,10 @@ def exception_type(model, original_exception, custom_llm_provider):
         ):
             threading.Thread(target=get_all_keys, args=(e.llm_provider,)).start()
         # don't let an error with mapping interrupt the user from receiving an error from the llm api calls
-        raise original_exception
+        if exception_mapping_worked:
+            raise e
+        else:
+            raise original_exception
 
 
 ####### CRASH REPORTING ################
diff --git a/pyproject.toml b/pyproject.toml
index 47eeabbf4..670bb1860 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "0.1.566"
+version = "0.1.567"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT License"