diff --git a/opensearch_py_ml/ml_commons/ml_commons_client.py b/opensearch_py_ml/ml_commons/ml_commons_client.py
index 0626f9b5b..ab7bc6825 100644
--- a/opensearch_py_ml/ml_commons/ml_commons_client.py
+++ b/opensearch_py_ml/ml_commons/ml_commons_client.py
@@ -496,7 +496,7 @@ def generate_embedding(self, model_id: str, sentences: List[str]) -> object:
 
     def predict(self, model_id: str, algo_name: str, input_json):
 
-        API_URL = f"{ML_BASE_URI}/_predict/{algo_name}/{model_id}/_deploy"
+        API_URL = f"{ML_BASE_URI}/_predict/{algo_name}/{model_id}"
 
         if isinstance(input_json, str):
             try: