diff --git a/litellm/tests/test_streaming.py b/litellm/tests/test_streaming.py
index eec6929f2..fa9e49f87 100644
--- a/litellm/tests/test_streaming.py
+++ b/litellm/tests/test_streaming.py
@@ -1265,6 +1265,8 @@ async def test_completion_replicate_llama3_streaming(sync_mode):
                 raise Exception("finish reason not set")
             if complete_response.strip() == "":
                 raise Exception("Empty response received")
+    except litellm.UnprocessableEntityError as e:
+        pass
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
diff --git a/litellm/utils.py b/litellm/utils.py
index 70d077063..fef4976ca 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -6160,7 +6160,6 @@ def exception_type(
                         )
                     elif (
                         original_exception.status_code == 400
-                        or original_exception.status_code == 422
                         or original_exception.status_code == 413
                     ):
                         exception_mapping_worked = True
@@ -6170,6 +6169,14 @@ def exception_type(
                             llm_provider="replicate",
                             response=original_exception.response,
                         )
+                    elif original_exception.status_code == 422:
+                        exception_mapping_worked = True
+                        raise UnprocessableEntityError(
+                            message=f"ReplicateException - {original_exception.message}",
+                            model=model,
+                            llm_provider="replicate",
+                            response=original_exception.response,
+                        )
                     elif original_exception.status_code == 408:
                         exception_mapping_worked = True
                         raise Timeout(