diff --git a/.stats.yml b/.stats.yml
index df7877dfd0..8a5d2c06b2 100644
--- a/.stats.yml
+++ b/.stats.yml
@@ -1,2 +1,2 @@
 configured_endpoints: 69
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-fc5dbc19505b0035f9e7f88868619f4fb519b048bde011f6154f3132d4be71fb.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-7c699d4503077d06a4a44f52c0c1f902d19a87c766b8be75b97c8dfd484ad4aa.yml
diff --git a/src/openai/resources/beta/assistants.py b/src/openai/resources/beta/assistants.py
index 65b7c9cfc2..462086f74b 100644
--- a/src/openai/resources/beta/assistants.py
+++ b/src/openai/resources/beta/assistants.py
@@ -61,6 +61,7 @@ def create(
         instructions: Optional[str] | NotGiven = NOT_GIVEN,
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         name: Optional[str] | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
         tool_resources: Optional[assistant_create_params.ToolResources] | NotGiven = NOT_GIVEN,
@@ -97,6 +98,13 @@ def create(
 
           name: The name of the assistant. The maximum length is 256 characters.
 
+          reasoning_effort: **o1 and o3-mini models only**
+
+              Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
+              result in faster responses and fewer tokens used on reasoning in a response.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -155,6 +163,7 @@ def create(
                     "instructions": instructions,
                     "metadata": metadata,
                     "name": name,
+                    "reasoning_effort": reasoning_effort,
                     "response_format": response_format,
                     "temperature": temperature,
                     "tool_resources": tool_resources,
@@ -210,8 +219,42 @@ def update(
         description: Optional[str] | NotGiven = NOT_GIVEN,
         instructions: Optional[str] | NotGiven = NOT_GIVEN,
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
-        model: str | NotGiven = NOT_GIVEN,
+        model: Union[
+            str,
+            Literal[
+                "o3-mini",
+                "o3-mini-2025-01-31",
+                "o1",
+                "o1-2024-12-17",
+                "gpt-4o",
+                "gpt-4o-2024-11-20",
+                "gpt-4o-2024-08-06",
+                "gpt-4o-2024-05-13",
+                "gpt-4o-mini",
+                "gpt-4o-mini-2024-07-18",
+                "gpt-4-turbo",
+                "gpt-4-turbo-2024-04-09",
+                "gpt-4-0125-preview",
+                "gpt-4-turbo-preview",
+                "gpt-4-1106-preview",
+                "gpt-4-vision-preview",
+                "gpt-4",
+                "gpt-4-0314",
+                "gpt-4-0613",
+                "gpt-4-32k",
+                "gpt-4-32k-0314",
+                "gpt-4-32k-0613",
+                "gpt-3.5-turbo",
+                "gpt-3.5-turbo-16k",
+                "gpt-3.5-turbo-0613",
+                "gpt-3.5-turbo-1106",
+                "gpt-3.5-turbo-0125",
+                "gpt-3.5-turbo-16k-0613",
+            ],
+        ]
+        | NotGiven = NOT_GIVEN,
         name: Optional[str] | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
         tool_resources: Optional[assistant_update_params.ToolResources] | NotGiven = NOT_GIVEN,
@@ -249,6 +292,13 @@ def update(
 
           name: The name of the assistant. The maximum length is 256 characters.
 
+          reasoning_effort: **o1 and o3-mini models only**
+
+              Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
+              result in faster responses and fewer tokens used on reasoning in a response.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -309,6 +359,7 @@ def update(
                     "metadata": metadata,
                     "model": model,
                     "name": name,
+                    "reasoning_effort": reasoning_effort,
                     "response_format": response_format,
                     "temperature": temperature,
                     "tool_resources": tool_resources,
@@ -451,6 +502,7 @@ async def create(
         instructions: Optional[str] | NotGiven = NOT_GIVEN,
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         name: Optional[str] | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
         tool_resources: Optional[assistant_create_params.ToolResources] | NotGiven = NOT_GIVEN,
@@ -487,6 +539,13 @@ async def create(
 
           name: The name of the assistant. The maximum length is 256 characters.
 
+          reasoning_effort: **o1 and o3-mini models only**
+
+              Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
+              result in faster responses and fewer tokens used on reasoning in a response.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -545,6 +604,7 @@ async def create(
                     "instructions": instructions,
                     "metadata": metadata,
                     "name": name,
+                    "reasoning_effort": reasoning_effort,
                     "response_format": response_format,
                     "temperature": temperature,
                     "tool_resources": tool_resources,
@@ -600,8 +660,42 @@ async def update(
         description: Optional[str] | NotGiven = NOT_GIVEN,
         instructions: Optional[str] | NotGiven = NOT_GIVEN,
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
-        model: str | NotGiven = NOT_GIVEN,
+        model: Union[
+            str,
+            Literal[
+                "o3-mini",
+                "o3-mini-2025-01-31",
+                "o1",
+                "o1-2024-12-17",
+                "gpt-4o",
+                "gpt-4o-2024-11-20",
+                "gpt-4o-2024-08-06",
+                "gpt-4o-2024-05-13",
+                "gpt-4o-mini",
+                "gpt-4o-mini-2024-07-18",
+                "gpt-4-turbo",
+                "gpt-4-turbo-2024-04-09",
+                "gpt-4-0125-preview",
+                "gpt-4-turbo-preview",
+                "gpt-4-1106-preview",
+                "gpt-4-vision-preview",
+                "gpt-4",
+                "gpt-4-0314",
+                "gpt-4-0613",
+                "gpt-4-32k",
+                "gpt-4-32k-0314",
+                "gpt-4-32k-0613",
+                "gpt-3.5-turbo",
+                "gpt-3.5-turbo-16k",
+                "gpt-3.5-turbo-0613",
+                "gpt-3.5-turbo-1106",
+                "gpt-3.5-turbo-0125",
+                "gpt-3.5-turbo-16k-0613",
+            ],
+        ]
+        | NotGiven = NOT_GIVEN,
         name: Optional[str] | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
         tool_resources: Optional[assistant_update_params.ToolResources] | NotGiven = NOT_GIVEN,
@@ -639,6 +733,13 @@ async def update(
 
           name: The name of the assistant. The maximum length is 256 characters.
 
+          reasoning_effort: **o1 and o3-mini models only**
+
+              Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
+              result in faster responses and fewer tokens used on reasoning in a response.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -699,6 +800,7 @@ async def update(
                     "metadata": metadata,
                     "model": model,
                     "name": name,
+                    "reasoning_effort": reasoning_effort,
                     "response_format": response_format,
                     "temperature": temperature,
                     "tool_resources": tool_resources,
diff --git a/src/openai/resources/beta/threads/runs/runs.py b/src/openai/resources/beta/threads/runs/runs.py
index a1c93d0382..3a9add5b3c 100644
--- a/src/openai/resources/beta/threads/runs/runs.py
+++ b/src/openai/resources/beta/threads/runs/runs.py
@@ -85,6 +85,7 @@ def create(
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
@@ -153,6 +154,13 @@ def create(
               [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
+          reasoning_effort: **o1 and o3-mini models only**
+
+              Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
+              result in faster responses and fewer tokens used on reasoning in a response.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -228,6 +236,7 @@ def create(
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
         tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
@@ -299,6 +308,13 @@ def create(
               [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
+          reasoning_effort: **o1 and o3-mini models only**
+
+              Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
+              result in faster responses and fewer tokens used on reasoning in a response.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -370,6 +386,7 @@ def create(
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
         tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
@@ -441,6 +458,13 @@ def create(
               [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
+          reasoning_effort: **o1 and o3-mini models only**
+
+              Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
+              result in faster responses and fewer tokens used on reasoning in a response.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -511,6 +535,7 @@ def create(
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
@@ -541,6 +566,7 @@ def create(
                     "metadata": metadata,
                     "model": model,
                     "parallel_tool_calls": parallel_tool_calls,
+                    "reasoning_effort": reasoning_effort,
                     "response_format": response_format,
                     "stream": stream,
                     "temperature": temperature,
@@ -941,6 +967,7 @@ async def create(
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
@@ -1009,6 +1036,13 @@ async def create(
               [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
+          reasoning_effort: **o1 and o3-mini models only**
+
+              Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
+              result in faster responses and fewer tokens used on reasoning in a response.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -1084,6 +1118,7 @@ async def create(
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
         tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
@@ -1155,6 +1190,13 @@ async def create(
               [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
+          reasoning_effort: **o1 and o3-mini models only**
+
+              Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
+              result in faster responses and fewer tokens used on reasoning in a response.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -1226,6 +1268,7 @@ async def create(
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
         tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
@@ -1297,6 +1340,13 @@ async def create(
               [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
+          reasoning_effort: **o1 and o3-mini models only**
+
+              Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
+              result in faster responses and fewer tokens used on reasoning in a response.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -1367,6 +1417,7 @@ async def create(
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
@@ -1397,6 +1448,7 @@ async def create(
                     "metadata": metadata,
                     "model": model,
                     "parallel_tool_calls": parallel_tool_calls,
+                    "reasoning_effort": reasoning_effort,
                     "response_format": response_format,
                     "stream": stream,
                     "temperature": temperature,
diff --git a/src/openai/resources/chat/completions.py b/src/openai/resources/chat/completions.py
index 2b91659950..99f26238d9 100644
--- a/src/openai/resources/chat/completions.py
+++ b/src/openai/resources/chat/completions.py
@@ -80,7 +80,7 @@ def create(
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
         prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
-        reasoning_effort: ChatCompletionReasoningEffort | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[ChatCompletionReasoningEffort] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
         service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN,
@@ -211,7 +211,7 @@ def create(
               whether they appear in the text so far, increasing the model's likelihood to
               talk about new topics.
 
-          reasoning_effort: **o1 models only**
+          reasoning_effort: **o1 and o3-mini models only**
 
               Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
@@ -333,7 +333,7 @@ def create(
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
         prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
-        reasoning_effort: ChatCompletionReasoningEffort | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[ChatCompletionReasoningEffort] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
         service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN,
@@ -470,7 +470,7 @@ def create(
               whether they appear in the text so far, increasing the model's likelihood to
               talk about new topics.
 
-          reasoning_effort: **o1 models only**
+          reasoning_effort: **o1 and o3-mini models only**
 
               Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
@@ -585,7 +585,7 @@ def create(
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
         prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
-        reasoning_effort: ChatCompletionReasoningEffort | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[ChatCompletionReasoningEffort] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
         service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN,
@@ -722,7 +722,7 @@ def create(
               whether they appear in the text so far, increasing the model's likelihood to
               talk about new topics.
 
-          reasoning_effort: **o1 models only**
+          reasoning_effort: **o1 and o3-mini models only**
 
               Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
@@ -836,7 +836,7 @@ def create(
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
         prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
-        reasoning_effort: ChatCompletionReasoningEffort | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[ChatCompletionReasoningEffort] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
         service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN,
@@ -943,7 +943,7 @@ async def create(
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
         prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
-        reasoning_effort: ChatCompletionReasoningEffort | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[ChatCompletionReasoningEffort] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
         service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN,
@@ -1074,7 +1074,7 @@ async def create(
               whether they appear in the text so far, increasing the model's likelihood to
               talk about new topics.
 
-          reasoning_effort: **o1 models only**
+          reasoning_effort: **o1 and o3-mini models only**
 
               Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
@@ -1196,7 +1196,7 @@ async def create(
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
         prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
-        reasoning_effort: ChatCompletionReasoningEffort | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[ChatCompletionReasoningEffort] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
         service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN,
@@ -1333,7 +1333,7 @@ async def create(
               whether they appear in the text so far, increasing the model's likelihood to
               talk about new topics.
 
-          reasoning_effort: **o1 models only**
+          reasoning_effort: **o1 and o3-mini models only**
 
               Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
@@ -1448,7 +1448,7 @@ async def create(
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
         prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
-        reasoning_effort: ChatCompletionReasoningEffort | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[ChatCompletionReasoningEffort] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
         service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN,
@@ -1585,7 +1585,7 @@ async def create(
               whether they appear in the text so far, increasing the model's likelihood to
               talk about new topics.
 
-          reasoning_effort: **o1 models only**
+          reasoning_effort: **o1 and o3-mini models only**
 
               Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
@@ -1699,7 +1699,7 @@ async def create(
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
         prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
-        reasoning_effort: ChatCompletionReasoningEffort | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[ChatCompletionReasoningEffort] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
         service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN,
diff --git a/src/openai/types/beta/assistant_create_params.py b/src/openai/types/beta/assistant_create_params.py
index e205856395..66bef02ced 100644
--- a/src/openai/types/beta/assistant_create_params.py
+++ b/src/openai/types/beta/assistant_create_params.py
@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 from typing import List, Union, Iterable, Optional
-from typing_extensions import Required, TypedDict
+from typing_extensions import Literal, Required, TypedDict
 
 from ..chat_model import ChatModel
 from .assistant_tool_param import AssistantToolParam
@@ -53,6 +53,15 @@ class AssistantCreateParams(TypedDict, total=False):
     name: Optional[str]
     """The name of the assistant. The maximum length is 256 characters."""
 
+    reasoning_effort: Optional[Literal["low", "medium", "high"]]
+    """**o1 and o3-mini models only**
+
+    Constrains effort on reasoning for
+    [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+    supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
+    result in faster responses and fewer tokens used on reasoning in a response.
+    """
+
     response_format: Optional[AssistantResponseFormatOptionParam]
     """Specifies the format that the model must output.
 
diff --git a/src/openai/types/beta/assistant_update_params.py b/src/openai/types/beta/assistant_update_params.py
index 35065ef61b..80fec110cd 100644
--- a/src/openai/types/beta/assistant_update_params.py
+++ b/src/openai/types/beta/assistant_update_params.py
@@ -2,8 +2,8 @@
 
 from __future__ import annotations
 
-from typing import List, Iterable, Optional
-from typing_extensions import TypedDict
+from typing import List, Union, Iterable, Optional
+from typing_extensions import Literal, TypedDict
 
 from .assistant_tool_param import AssistantToolParam
 from ..shared_params.metadata import Metadata
@@ -32,7 +32,39 @@ class AssistantUpdateParams(TypedDict, total=False):
     a maximum length of 512 characters.
     """
 
-    model: str
+    model: Union[
+        str,
+        Literal[
+            "o3-mini",
+            "o3-mini-2025-01-31",
+            "o1",
+            "o1-2024-12-17",
+            "gpt-4o",
+            "gpt-4o-2024-11-20",
+            "gpt-4o-2024-08-06",
+            "gpt-4o-2024-05-13",
+            "gpt-4o-mini",
+            "gpt-4o-mini-2024-07-18",
+            "gpt-4-turbo",
+            "gpt-4-turbo-2024-04-09",
+            "gpt-4-0125-preview",
+            "gpt-4-turbo-preview",
+            "gpt-4-1106-preview",
+            "gpt-4-vision-preview",
+            "gpt-4",
+            "gpt-4-0314",
+            "gpt-4-0613",
+            "gpt-4-32k",
+            "gpt-4-32k-0314",
+            "gpt-4-32k-0613",
+            "gpt-3.5-turbo",
+            "gpt-3.5-turbo-16k",
+            "gpt-3.5-turbo-0613",
+            "gpt-3.5-turbo-1106",
+            "gpt-3.5-turbo-0125",
+            "gpt-3.5-turbo-16k-0613",
+        ],
+    ]
     """ID of the model to use.
 
     You can use the
@@ -45,6 +77,15 @@ class AssistantUpdateParams(TypedDict, total=False):
     name: Optional[str]
     """The name of the assistant. The maximum length is 256 characters."""
 
+    reasoning_effort: Optional[Literal["low", "medium", "high"]]
+    """**o1 and o3-mini models only**
+
+    Constrains effort on reasoning for
+    [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+    supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
+    result in faster responses and fewer tokens used on reasoning in a response.
+    """
+
     response_format: Optional[AssistantResponseFormatOptionParam]
     """Specifies the format that the model must output.
 
diff --git a/src/openai/types/beta/threads/run_create_params.py b/src/openai/types/beta/threads/run_create_params.py
index 091dd3da66..093b4ce321 100644
--- a/src/openai/types/beta/threads/run_create_params.py
+++ b/src/openai/types/beta/threads/run_create_params.py
@@ -106,6 +106,15 @@ class RunCreateParamsBase(TypedDict, total=False):
     during tool use.
     """
 
+    reasoning_effort: Optional[Literal["low", "medium", "high"]]
+    """**o1 and o3-mini models only**
+
+    Constrains effort on reasoning for
+    [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+    supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
+    result in faster responses and fewer tokens used on reasoning in a response.
+    """
+
     response_format: Optional[AssistantResponseFormatOptionParam]
     """Specifies the format that the model must output.
 
diff --git a/src/openai/types/chat/chat_completion_reasoning_effort.py b/src/openai/types/chat/chat_completion_reasoning_effort.py
index 9e7946974a..85249c53b1 100644
--- a/src/openai/types/chat/chat_completion_reasoning_effort.py
+++ b/src/openai/types/chat/chat_completion_reasoning_effort.py
@@ -1,7 +1,8 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
+from typing import Optional
 from typing_extensions import Literal, TypeAlias
 
 __all__ = ["ChatCompletionReasoningEffort"]
 
-ChatCompletionReasoningEffort: TypeAlias = Literal["low", "medium", "high"]
+ChatCompletionReasoningEffort: TypeAlias = Optional[Literal["low", "medium", "high"]]
diff --git a/src/openai/types/chat/completion_create_params.py b/src/openai/types/chat/completion_create_params.py
index ec88ea1fb0..c761cbe07b 100644
--- a/src/openai/types/chat/completion_create_params.py
+++ b/src/openai/types/chat/completion_create_params.py
@@ -174,8 +174,8 @@ class CompletionCreateParamsBase(TypedDict, total=False):
     far, increasing the model's likelihood to talk about new topics.
     """
 
-    reasoning_effort: ChatCompletionReasoningEffort
-    """**o1 models only**
+    reasoning_effort: Optional[ChatCompletionReasoningEffort]
+    """**o1 and o3-mini models only**
 
     Constrains effort on reasoning for
     [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
diff --git a/tests/api_resources/beta/test_assistants.py b/tests/api_resources/beta/test_assistants.py
index 458e3f5e90..82aaf87b1c 100644
--- a/tests/api_resources/beta/test_assistants.py
+++ b/tests/api_resources/beta/test_assistants.py
@@ -36,6 +36,7 @@ def test_method_create_with_all_params(self, client: OpenAI) -> None:
             instructions="instructions",
             metadata={"foo": "string"},
             name="name",
+            reasoning_effort="low",
             response_format="auto",
             temperature=1,
             tool_resources={
@@ -132,8 +133,9 @@ def test_method_update_with_all_params(self, client: OpenAI) -> None:
             description="description",
             instructions="instructions",
             metadata={"foo": "string"},
-            model="model",
+            model="string",
             name="name",
+            reasoning_effort="low",
             response_format="auto",
             temperature=1,
             tool_resources={
@@ -268,6 +270,7 @@ async def test_method_create_with_all_params(self, async_client: AsyncOpenAI) ->
             instructions="instructions",
             metadata={"foo": "string"},
             name="name",
+            reasoning_effort="low",
             response_format="auto",
             temperature=1,
             tool_resources={
@@ -364,8 +367,9 @@ async def test_method_update_with_all_params(self, async_client: AsyncOpenAI) ->
             description="description",
             instructions="instructions",
             metadata={"foo": "string"},
-            model="model",
+            model="string",
             name="name",
+            reasoning_effort="low",
             response_format="auto",
             temperature=1,
             tool_resources={
diff --git a/tests/api_resources/beta/threads/test_runs.py b/tests/api_resources/beta/threads/test_runs.py
index 1509d5e9ab..01a1ce9ea4 100644
--- a/tests/api_resources/beta/threads/test_runs.py
+++ b/tests/api_resources/beta/threads/test_runs.py
@@ -54,6 +54,7 @@ def test_method_create_with_all_params_overload_1(self, client: OpenAI) -> None:
             metadata={"foo": "string"},
             model="gpt-4o",
             parallel_tool_calls=True,
+            reasoning_effort="low",
             response_format="auto",
             stream=False,
             temperature=1,
@@ -137,6 +138,7 @@ def test_method_create_with_all_params_overload_2(self, client: OpenAI) -> None:
             metadata={"foo": "string"},
             model="gpt-4o",
             parallel_tool_calls=True,
+            reasoning_effort="low",
             response_format="auto",
             temperature=1,
             tool_choice="none",
@@ -550,6 +552,7 @@ async def test_method_create_with_all_params_overload_1(self, async_client: Asyn
             metadata={"foo": "string"},
             model="gpt-4o",
             parallel_tool_calls=True,
+            reasoning_effort="low",
             response_format="auto",
             stream=False,
             temperature=1,
@@ -633,6 +636,7 @@ async def test_method_create_with_all_params_overload_2(self, async_client: Asyn
             metadata={"foo": "string"},
             model="gpt-4o",
             parallel_tool_calls=True,
+            reasoning_effort="low",
             response_format="auto",
             temperature=1,
             tool_choice="none",