diff --git a/litellm/cost_calculator.py b/litellm/cost_calculator.py
index 5d976483a..0bc65a7f1 100644
--- a/litellm/cost_calculator.py
+++ b/litellm/cost_calculator.py
@@ -18,6 +18,7 @@ from litellm.litellm_core_utils.llm_cost_calc.google import (
 from litellm.litellm_core_utils.llm_cost_calc.utils import _generic_cost_per_character
 from litellm.types.llms.openai import HttpxBinaryResponseContent
 from litellm.types.router import SPECIAL_MODEL_INFO_PARAMS
+
 from litellm.utils import (
     CallTypes,
     CostPerToken,
diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py
index 521ded627..f954b9dd5 100644
--- a/litellm/proxy/proxy_server.py
+++ b/litellm/proxy/proxy_server.py
@@ -3382,8 +3382,9 @@ async def embeddings(
         )
         verbose_proxy_logger.debug(traceback.format_exc())
         if isinstance(e, HTTPException):
+            message = get_error_message_str(e)
             raise ProxyException(
-                message=getattr(e, "message", str(e)),
+                message=message,
                 type=getattr(e, "type", "None"),
                 param=getattr(e, "param", "None"),
                 code=getattr(e, "status_code", status.HTTP_400_BAD_REQUEST),
diff --git a/litellm/proxy/utils.py b/litellm/proxy/utils.py
index 32b74be7c..ba1a61080 100644
--- a/litellm/proxy/utils.py
+++ b/litellm/proxy/utils.py
@@ -2888,6 +2888,11 @@ def get_error_message_str(e: Exception) -> str:
             error_message = e.detail
         elif isinstance(e.detail, dict):
             error_message = json.dumps(e.detail)
+        elif hasattr(e, "message"):
+            if isinstance(e.message, "str"):
+                error_message = e.message
+            elif isinstance(e.message, dict):
+                error_message = json.dumps(e.message)
         else:
             error_message = str(e)
     else:
diff --git a/litellm/utils.py b/litellm/utils.py
index d17ba8911..62386b1d2 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -7521,7 +7521,7 @@ def exception_type(
                     if original_exception.status_code == 400:
                         exception_mapping_worked = True
                         raise BadRequestError(
-                            message=f"{exception_provider} - {message}",
+                            message=f"{exception_provider} - {error_str}",
                             llm_provider=custom_llm_provider,
                             model=model,
                             response=original_exception.response,
@@ -7530,7 +7530,7 @@ def exception_type(
                     elif original_exception.status_code == 401:
                         exception_mapping_worked = True
                         raise AuthenticationError(
-                            message=f"AuthenticationError: {exception_provider} - {message}",
+                            message=f"AuthenticationError: {exception_provider} - {error_str}",
                             llm_provider=custom_llm_provider,
                             model=model,
                             response=original_exception.response,
@@ -7539,7 +7539,7 @@ def exception_type(
                     elif original_exception.status_code == 404:
                         exception_mapping_worked = True
                         raise NotFoundError(
-                            message=f"NotFoundError: {exception_provider} - {message}",
+                            message=f"NotFoundError: {exception_provider} - {error_str}",
                             model=model,
                             llm_provider=custom_llm_provider,
                             response=original_exception.response,
@@ -7548,7 +7548,7 @@ def exception_type(
                     elif original_exception.status_code == 408:
                         exception_mapping_worked = True
                         raise Timeout(
-                            message=f"Timeout Error: {exception_provider} - {message}",
+                            message=f"Timeout Error: {exception_provider} - {error_str}",
                             model=model,
                             llm_provider=custom_llm_provider,
                             litellm_debug_info=extra_information,
@@ -7556,7 +7556,7 @@ def exception_type(
                     elif original_exception.status_code == 422:
                         exception_mapping_worked = True
                         raise BadRequestError(
-                            message=f"BadRequestError: {exception_provider} - {message}",
+                            message=f"BadRequestError: {exception_provider} - {error_str}",
                             model=model,
                             llm_provider=custom_llm_provider,
                             response=original_exception.response,
@@ -7565,7 +7565,7 @@ def exception_type(
                     elif original_exception.status_code == 429:
                         exception_mapping_worked = True
                         raise RateLimitError(
-                            message=f"RateLimitError: {exception_provider} - {message}",
+                            message=f"RateLimitError: {exception_provider} - {error_str}",
                             model=model,
                             llm_provider=custom_llm_provider,
                             response=original_exception.response,
@@ -7574,7 +7574,7 @@ def exception_type(
                     elif original_exception.status_code == 503:
                         exception_mapping_worked = True
                         raise ServiceUnavailableError(
-                            message=f"ServiceUnavailableError: {exception_provider} - {message}",
+                            message=f"ServiceUnavailableError: {exception_provider} - {error_str}",
                             model=model,
                             llm_provider=custom_llm_provider,
                             response=original_exception.response,
@@ -7583,7 +7583,7 @@ def exception_type(
                     elif original_exception.status_code == 504:  # gateway timeout error
                         exception_mapping_worked = True
                         raise Timeout(
-                            message=f"Timeout Error: {exception_provider} - {message}",
+                            message=f"Timeout Error: {exception_provider} - {error_str}",
                             model=model,
                             llm_provider=custom_llm_provider,
                             litellm_debug_info=extra_information,
@@ -7592,7 +7592,7 @@ def exception_type(
                         exception_mapping_worked = True
                         raise APIError(
                             status_code=original_exception.status_code,
-                            message=f"APIError: {exception_provider} - {message}",
+                            message=f"APIError: {exception_provider} - {error_str}",
                             llm_provider=custom_llm_provider,
                             model=model,
                             request=original_exception.request,
@@ -7601,7 +7601,7 @@ def exception_type(
                 else:
                     # if no status code then it is an APIConnectionError: https://github.com/openai/openai-python#handling-errors
                     raise APIConnectionError(
-                        message=f"APIConnectionError: {exception_provider} - {message}",
+                        message=f"APIConnectionError: {exception_provider} - {error_str}",
                         llm_provider=custom_llm_provider,
                         model=model,
                         litellm_debug_info=extra_information,