diff --git a/litellm/tests/test_completion.py b/litellm/tests/test_completion.py
index 45a53ca56..d08a4ae3b 100644
--- a/litellm/tests/test_completion.py
+++ b/litellm/tests/test_completion.py
@@ -3342,6 +3342,8 @@ def test_completion_watsonx():
         print(response)
     except litellm.APIError as e:
         pass
+    except litellm.RateLimitError as e:
+        pass
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
diff --git a/litellm/utils.py b/litellm/utils.py
index 14534147b..4a8e7e691 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -8514,7 +8514,7 @@ def exception_type(
                     request=original_exception.request,
                 )
             elif custom_llm_provider == "watsonx":
-                if "token_quota_reached" in error_response:
+                if "token_quota_reached" in error_str:
                     exception_mapping_worked = True
                     raise RateLimitError(
                         message=f"WatsonxException: Rate Limit Errror - {error_str}",