diff --git a/sdk/ai/azure-ai-inference/azure/ai/inference/_patch.py b/sdk/ai/azure-ai-inference/azure/ai/inference/_patch.py
index 29d0d0dbad99..b9386d5a8eb9 100644
--- a/sdk/ai/azure-ai-inference/azure/ai/inference/_patch.py
+++ b/sdk/ai/azure-ai-inference/azure/ai/inference/_patch.py
@@ -294,6 +294,7 @@ def __init__(
         seed: Optional[int] = None,
         model: Optional[str] = None,
         model_extras: Optional[Dict[str, Any]] = None,
+        store: Optional[bool] = None,
         **kwargs: Any,
     ) -> None:
 
@@ -313,6 +314,7 @@ def __init__(
         self._seed = seed
         self._model = model
         self._model_extras = model_extras
+        self._store = store
 
         # For Key auth, we need to send these two auth HTTP request headers simultaneously:
         # 1. "Authorization: Bearer <key>"
@@ -349,6 +351,7 @@ def complete(
         seed: Optional[int] = None,
         model: Optional[str] = None,
         model_extras: Optional[Dict[str, Any]] = None,
+        store: Optional[bool] = None,
         **kwargs: Any,
     ) -> _models.ChatCompletions: ...
 
@@ -372,6 +375,7 @@ def complete(
         seed: Optional[int] = None,
         model: Optional[str] = None,
         model_extras: Optional[Dict[str, Any]] = None,
+        store: Optional[bool] = None,
         **kwargs: Any,
     ) -> Iterable[_models.StreamingChatCompletionsUpdate]: ...
 
@@ -395,6 +399,7 @@ def complete(
         seed: Optional[int] = None,
         model: Optional[str] = None,
         model_extras: Optional[Dict[str, Any]] = None,
+        store: Optional[bool] = None,
         **kwargs: Any,
     ) -> Union[Iterable[_models.StreamingChatCompletionsUpdate], _models.ChatCompletions]:
         # pylint: disable=line-too-long
@@ -558,6 +563,7 @@ def complete(
         seed: Optional[int] = None,
         model: Optional[str] = None,
         model_extras: Optional[Dict[str, Any]] = None,
+        store: Optional[bool] = None,
         **kwargs: Any,
     ) -> Union[Iterable[_models.StreamingChatCompletionsUpdate], _models.ChatCompletions]:
         # pylint: disable=line-too-long
@@ -687,6 +693,7 @@ def complete(
                 "tool_choice": tool_choice if tool_choice is not None else self._tool_choice,
                 "tools": tools if tools is not None else self._tools,
                 "top_p": top_p if top_p is not None else self._top_p,
+                "store": store if store is not None else self._store,
             }
             if model_extras is not None and bool(model_extras):
                 body.update(model_extras)
diff --git a/sdk/ai/azure-ai-inference/tests/test_chat_completions_client.py b/sdk/ai/azure-ai-inference/tests/test_chat_completions_client.py
index 688c64ac715b..58feba9af22c 100644
--- a/sdk/ai/azure-ai-inference/tests/test_chat_completions_client.py
+++ b/sdk/ai/azure-ai-inference/tests/test_chat_completions_client.py
@@ -94,6 +94,7 @@ def test_chat_completions_request_payload(self, **kwargs):
                     tools=[ModelClientTestBase.TOOL1, ModelClientTestBase.TOOL2],
                     top_p=9.876,
                     raw_request_hook=self.request_callback,
+                    store=True,
                 )
                 assert False
             except ServiceRequestError as _:
@@ -129,6 +130,7 @@ def test_chat_completions_request_payload_with_defaults(self, **kwargs):
             tool_choice=sdk.models.ChatCompletionsToolChoicePreset.AUTO,
             tools=[ModelClientTestBase.TOOL1, ModelClientTestBase.TOOL2],
             top_p=9.876,
+            store=True,
         )
 
         for _ in range(2):
@@ -206,6 +208,7 @@ def test_chat_completions_request_payload_with_defaults_and_overrides(self, **kw
             ),
             tools=[ModelClientTestBase.TOOL2],
             top_p=3.456,
+            store=False,
         )
 
         for _ in range(2):
@@ -265,6 +268,7 @@ def test_chat_completions_request_payload_with_defaults_and_overrides(self, **kw
                     tools=[ModelClientTestBase.TOOL1, ModelClientTestBase.TOOL2],
                     top_p=9.876,
                     raw_request_hook=self.request_callback,
+                    store=True
                 )
                 assert False
             except ServiceRequestError as _: