diff --git a/.stats.yml b/.stats.yml
index 903c159960..de3167f3a8 100644
--- a/.stats.yml
+++ b/.stats.yml
@@ -1,2 +1,2 @@
 configured_endpoints: 68
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-85a85e0c08de456441431c0ae4e9c078cc8f9748c29430b9a9058340db6389ee.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-501122aa32adaa2abb3d4487880ab9cdf2141addce2e6c3d1bd9bb6b44c318a8.yml
diff --git a/src/openai/resources/beta/assistants.py b/src/openai/resources/beta/assistants.py
index 1e57944eb3..5d8c6ec331 100644
--- a/src/openai/resources/beta/assistants.py
+++ b/src/openai/resources/beta/assistants.py
@@ -100,11 +100,11 @@ def create(
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -250,11 +250,11 @@ def update(
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -486,11 +486,11 @@ async def create(
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -636,11 +636,11 @@ async def update(
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
diff --git a/src/openai/resources/beta/threads/runs/runs.py b/src/openai/resources/beta/threads/runs/runs.py
index a17e0016c7..ef0edf0e36 100644
--- a/src/openai/resources/beta/threads/runs/runs.py
+++ b/src/openai/resources/beta/threads/runs/runs.py
@@ -156,11 +156,11 @@ def create(
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -300,11 +300,11 @@ def create(
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -440,11 +440,11 @@ def create(
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -1004,11 +1004,11 @@ async def create(
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -1148,11 +1148,11 @@ async def create(
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -1288,11 +1288,11 @@ async def create(
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
diff --git a/src/openai/resources/beta/threads/threads.py b/src/openai/resources/beta/threads/threads.py
index 27777251ad..3b0e310e4f 100644
--- a/src/openai/resources/beta/threads/threads.py
+++ b/src/openai/resources/beta/threads/threads.py
@@ -326,11 +326,11 @@ def create_and_run(
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -460,11 +460,11 @@ def create_and_run(
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -590,11 +590,11 @@ def create_and_run(
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -980,11 +980,11 @@ async def create_and_run(
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -1114,11 +1114,11 @@ async def create_and_run(
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -1244,11 +1244,11 @@ async def create_and_run(
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
diff --git a/src/openai/resources/chat/completions.py b/src/openai/resources/chat/completions.py
index 29fd69947a..d25a8c4dfb 100644
--- a/src/openai/resources/chat/completions.py
+++ b/src/openai/resources/chat/completions.py
@@ -62,6 +62,7 @@ def create(
         functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN,
         logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
         logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
@@ -130,13 +131,17 @@ def create(
               returns the log probabilities of each output token returned in the `content` of
               `message`.
 
+          max_completion_tokens: An upper bound for the number of tokens that can be generated for a completion,
+              including visible output tokens and
+              [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
+
           max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat
-              completion.
+              completion. This value can be used to control
+              [costs](https://openai.com/api/pricing/) for text generated via API.
 
-              The total length of input tokens and generated tokens is limited by the model's
-              context length.
-              [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
-              for counting tokens.
+              This value is now deprecated in favor of `max_completion_tokens`, and is not
+              compatible with
+              [o1 series models](https://platform.openai.com/docs/guides/reasoning).
 
           n: How many chat completion choices to generate for each input message. Note that
               you will be charged based on the number of generated tokens across all of the
@@ -159,11 +164,11 @@ def create(
               all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -183,8 +188,11 @@ def create(
           service_tier: Specifies the latency tier to use for processing the request. This parameter is
               relevant for customers subscribed to the scale tier service:
 
-              - If set to 'auto', the system will utilize scale tier credits until they are
-                exhausted.
+              - If set to 'auto', and the Project is Scale tier enabled, the system will
+                utilize scale tier credits until they are exhausted.
+              - If set to 'auto', and the Project is not Scale tier enabled, the request will
+                be processed using the default service tier with a lower uptime SLA and no
+                latency guarentee.
               - If set to 'default', the request will be processed using the default service
                 tier with a lower uptime SLA and no latency guarentee.
               - When not set, the default behavior is 'auto'.
@@ -259,6 +267,7 @@ def create(
         functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN,
         logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
         logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
@@ -333,13 +342,17 @@ def create(
               returns the log probabilities of each output token returned in the `content` of
               `message`.
 
+          max_completion_tokens: An upper bound for the number of tokens that can be generated for a completion,
+              including visible output tokens and
+              [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
+
           max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat
-              completion.
+              completion. This value can be used to control
+              [costs](https://openai.com/api/pricing/) for text generated via API.
 
-              The total length of input tokens and generated tokens is limited by the model's
-              context length.
-              [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
-              for counting tokens.
+              This value is now deprecated in favor of `max_completion_tokens`, and is not
+              compatible with
+              [o1 series models](https://platform.openai.com/docs/guides/reasoning).
 
           n: How many chat completion choices to generate for each input message. Note that
               you will be charged based on the number of generated tokens across all of the
@@ -362,11 +375,11 @@ def create(
               all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -386,8 +399,11 @@ def create(
           service_tier: Specifies the latency tier to use for processing the request. This parameter is
               relevant for customers subscribed to the scale tier service:
 
-              - If set to 'auto', the system will utilize scale tier credits until they are
-                exhausted.
+              - If set to 'auto', and the Project is Scale tier enabled, the system will
+                utilize scale tier credits until they are exhausted.
+              - If set to 'auto', and the Project is not Scale tier enabled, the request will
+                be processed using the default service tier with a lower uptime SLA and no
+                latency guarentee.
               - If set to 'default', the request will be processed using the default service
                 tier with a lower uptime SLA and no latency guarentee.
               - When not set, the default behavior is 'auto'.
@@ -455,6 +471,7 @@ def create(
         functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN,
         logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
         logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
@@ -529,13 +546,17 @@ def create(
               returns the log probabilities of each output token returned in the `content` of
               `message`.
 
+          max_completion_tokens: An upper bound for the number of tokens that can be generated for a completion,
+              including visible output tokens and
+              [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
+
           max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat
-              completion.
+              completion. This value can be used to control
+              [costs](https://openai.com/api/pricing/) for text generated via API.
 
-              The total length of input tokens and generated tokens is limited by the model's
-              context length.
-              [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
-              for counting tokens.
+              This value is now deprecated in favor of `max_completion_tokens`, and is not
+              compatible with
+              [o1 series models](https://platform.openai.com/docs/guides/reasoning).
 
           n: How many chat completion choices to generate for each input message. Note that
               you will be charged based on the number of generated tokens across all of the
@@ -558,11 +579,11 @@ def create(
               all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -582,8 +603,11 @@ def create(
           service_tier: Specifies the latency tier to use for processing the request. This parameter is
               relevant for customers subscribed to the scale tier service:
 
-              - If set to 'auto', the system will utilize scale tier credits until they are
-                exhausted.
+              - If set to 'auto', and the Project is Scale tier enabled, the system will
+                utilize scale tier credits until they are exhausted.
+              - If set to 'auto', and the Project is not Scale tier enabled, the request will
+                be processed using the default service tier with a lower uptime SLA and no
+                latency guarentee.
               - If set to 'default', the request will be processed using the default service
                 tier with a lower uptime SLA and no latency guarentee.
               - When not set, the default behavior is 'auto'.
@@ -650,6 +674,7 @@ def create(
         functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN,
         logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
         logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
@@ -684,6 +709,7 @@ def create(
                     "functions": functions,
                     "logit_bias": logit_bias,
                     "logprobs": logprobs,
+                    "max_completion_tokens": max_completion_tokens,
                     "max_tokens": max_tokens,
                     "n": n,
                     "parallel_tool_calls": parallel_tool_calls,
@@ -743,6 +769,7 @@ async def create(
         functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN,
         logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
         logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
@@ -811,13 +838,17 @@ async def create(
               returns the log probabilities of each output token returned in the `content` of
               `message`.
 
+          max_completion_tokens: An upper bound for the number of tokens that can be generated for a completion,
+              including visible output tokens and
+              [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
+
           max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat
-              completion.
+              completion. This value can be used to control
+              [costs](https://openai.com/api/pricing/) for text generated via API.
 
-              The total length of input tokens and generated tokens is limited by the model's
-              context length.
-              [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
-              for counting tokens.
+              This value is now deprecated in favor of `max_completion_tokens`, and is not
+              compatible with
+              [o1 series models](https://platform.openai.com/docs/guides/reasoning).
 
           n: How many chat completion choices to generate for each input message. Note that
               you will be charged based on the number of generated tokens across all of the
@@ -840,11 +871,11 @@ async def create(
               all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -864,8 +895,11 @@ async def create(
           service_tier: Specifies the latency tier to use for processing the request. This parameter is
               relevant for customers subscribed to the scale tier service:
 
-              - If set to 'auto', the system will utilize scale tier credits until they are
-                exhausted.
+              - If set to 'auto', and the Project is Scale tier enabled, the system will
+                utilize scale tier credits until they are exhausted.
+              - If set to 'auto', and the Project is not Scale tier enabled, the request will
+                be processed using the default service tier with a lower uptime SLA and no
+                latency guarentee.
               - If set to 'default', the request will be processed using the default service
                 tier with a lower uptime SLA and no latency guarentee.
               - When not set, the default behavior is 'auto'.
@@ -940,6 +974,7 @@ async def create(
         functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN,
         logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
         logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
@@ -1014,13 +1049,17 @@ async def create(
               returns the log probabilities of each output token returned in the `content` of
               `message`.
 
+          max_completion_tokens: An upper bound for the number of tokens that can be generated for a completion,
+              including visible output tokens and
+              [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
+
           max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat
-              completion.
+              completion. This value can be used to control
+              [costs](https://openai.com/api/pricing/) for text generated via API.
 
-              The total length of input tokens and generated tokens is limited by the model's
-              context length.
-              [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
-              for counting tokens.
+              This value is now deprecated in favor of `max_completion_tokens`, and is not
+              compatible with
+              [o1 series models](https://platform.openai.com/docs/guides/reasoning).
 
           n: How many chat completion choices to generate for each input message. Note that
               you will be charged based on the number of generated tokens across all of the
@@ -1043,11 +1082,11 @@ async def create(
               all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -1067,8 +1106,11 @@ async def create(
           service_tier: Specifies the latency tier to use for processing the request. This parameter is
               relevant for customers subscribed to the scale tier service:
 
-              - If set to 'auto', the system will utilize scale tier credits until they are
-                exhausted.
+              - If set to 'auto', and the Project is Scale tier enabled, the system will
+                utilize scale tier credits until they are exhausted.
+              - If set to 'auto', and the Project is not Scale tier enabled, the request will
+                be processed using the default service tier with a lower uptime SLA and no
+                latency guarentee.
               - If set to 'default', the request will be processed using the default service
                 tier with a lower uptime SLA and no latency guarentee.
               - When not set, the default behavior is 'auto'.
@@ -1136,6 +1178,7 @@ async def create(
         functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN,
         logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
         logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
@@ -1210,13 +1253,17 @@ async def create(
               returns the log probabilities of each output token returned in the `content` of
               `message`.
 
+          max_completion_tokens: An upper bound for the number of tokens that can be generated for a completion,
+              including visible output tokens and
+              [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
+
           max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat
-              completion.
+              completion. This value can be used to control
+              [costs](https://openai.com/api/pricing/) for text generated via API.
 
-              The total length of input tokens and generated tokens is limited by the model's
-              context length.
-              [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
-              for counting tokens.
+              This value is now deprecated in favor of `max_completion_tokens`, and is not
+              compatible with
+              [o1 series models](https://platform.openai.com/docs/guides/reasoning).
 
           n: How many chat completion choices to generate for each input message. Note that
               you will be charged based on the number of generated tokens across all of the
@@ -1239,11 +1286,11 @@ async def create(
               all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-              Outputs which guarantees the model will match your supplied JSON schema. Learn
-              more in the
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
               [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-              Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+              Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
               message the model generates is valid JSON.
 
               **Important:** when using JSON mode, you **must** also instruct the model to
@@ -1263,8 +1310,11 @@ async def create(
           service_tier: Specifies the latency tier to use for processing the request. This parameter is
               relevant for customers subscribed to the scale tier service:
 
-              - If set to 'auto', the system will utilize scale tier credits until they are
-                exhausted.
+              - If set to 'auto', and the Project is Scale tier enabled, the system will
+                utilize scale tier credits until they are exhausted.
+              - If set to 'auto', and the Project is not Scale tier enabled, the request will
+                be processed using the default service tier with a lower uptime SLA and no
+                latency guarentee.
               - If set to 'default', the request will be processed using the default service
                 tier with a lower uptime SLA and no latency guarentee.
               - When not set, the default behavior is 'auto'.
@@ -1331,6 +1381,7 @@ async def create(
         functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN,
         logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
         logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
@@ -1365,6 +1416,7 @@ async def create(
                     "functions": functions,
                     "logit_bias": logit_bias,
                     "logprobs": logprobs,
+                    "max_completion_tokens": max_completion_tokens,
                     "max_tokens": max_tokens,
                     "n": n,
                     "parallel_tool_calls": parallel_tool_calls,
diff --git a/src/openai/resources/fine_tuning/jobs/jobs.py b/src/openai/resources/fine_tuning/jobs/jobs.py
index 88ac6107a4..7eb0c5dbfc 100644
--- a/src/openai/resources/fine_tuning/jobs/jobs.py
+++ b/src/openai/resources/fine_tuning/jobs/jobs.py
@@ -111,7 +111,7 @@ def create(
               job parameters should produce the same results, but may differ in rare cases. If
               a seed is not specified, one will be generated for you.
 
-          suffix: A string of up to 18 characters that will be added to your fine-tuned model
+          suffix: A string of up to 64 characters that will be added to your fine-tuned model
               name.
 
               For example, a `suffix` of "custom-model-name" would produce a model name like
@@ -402,7 +402,7 @@ async def create(
               job parameters should produce the same results, but may differ in rare cases. If
               a seed is not specified, one will be generated for you.
 
-          suffix: A string of up to 18 characters that will be added to your fine-tuned model
+          suffix: A string of up to 64 characters that will be added to your fine-tuned model
               name.
 
               For example, a `suffix` of "custom-model-name" would produce a model name like
diff --git a/src/openai/types/beta/assistant.py b/src/openai/types/beta/assistant.py
index c6a0a4cfcf..b4da08745d 100644
--- a/src/openai/types/beta/assistant.py
+++ b/src/openai/types/beta/assistant.py
@@ -90,11 +90,11 @@ class Assistant(BaseModel):
     and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
     Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-    Outputs which guarantees the model will match your supplied JSON schema. Learn
-    more in the
+    Outputs which ensures the model will match your supplied JSON schema. Learn more
+    in the
     [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-    Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+    Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
     message the model generates is valid JSON.
 
     **Important:** when using JSON mode, you **must** also instruct the model to
diff --git a/src/openai/types/beta/assistant_create_params.py b/src/openai/types/beta/assistant_create_params.py
index c1360b5b66..eca4da0a2b 100644
--- a/src/openai/types/beta/assistant_create_params.py
+++ b/src/openai/types/beta/assistant_create_params.py
@@ -58,11 +58,11 @@ class AssistantCreateParams(TypedDict, total=False):
     and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
     Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-    Outputs which guarantees the model will match your supplied JSON schema. Learn
-    more in the
+    Outputs which ensures the model will match your supplied JSON schema. Learn more
+    in the
     [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-    Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+    Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
     message the model generates is valid JSON.
 
     **Important:** when using JSON mode, you **must** also instruct the model to
diff --git a/src/openai/types/beta/assistant_update_params.py b/src/openai/types/beta/assistant_update_params.py
index ade565819f..5396233937 100644
--- a/src/openai/types/beta/assistant_update_params.py
+++ b/src/openai/types/beta/assistant_update_params.py
@@ -50,11 +50,11 @@ class AssistantUpdateParams(TypedDict, total=False):
     and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
     Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-    Outputs which guarantees the model will match your supplied JSON schema. Learn
-    more in the
+    Outputs which ensures the model will match your supplied JSON schema. Learn more
+    in the
     [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-    Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+    Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
     message the model generates is valid JSON.
 
     **Important:** when using JSON mode, you **must** also instruct the model to
diff --git a/src/openai/types/beta/file_search_tool.py b/src/openai/types/beta/file_search_tool.py
index 4015b3da09..aee6593e89 100644
--- a/src/openai/types/beta/file_search_tool.py
+++ b/src/openai/types/beta/file_search_tool.py
@@ -9,16 +9,16 @@
 
 
 class FileSearchRankingOptions(BaseModel):
-    ranker: Optional[Literal["auto", "default_2024_08_21"]] = None
-    """The ranker to use for the file search.
+    score_threshold: float
+    """The score threshold for the file search.
 
-    If not specified will use the `auto` ranker.
+    All values must be a floating point number between 0 and 1.
     """
 
-    score_threshold: Optional[float] = None
-    """The score threshold for the file search.
+    ranker: Optional[Literal["auto", "default_2024_08_21"]] = None
+    """The ranker to use for the file search.
 
-    All values must be a floating point number between 0 and 1.
+    If not specified will use the `auto` ranker.
     """
 
 
@@ -38,6 +38,9 @@ class FileSearch(BaseModel):
     ranking_options: Optional[FileSearchRankingOptions] = None
     """The ranking options for the file search.
 
+    If not specified, the file search tool will use the `auto` ranker and a
+    score_threshold of 0.
+
     See the
     [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
     for more information.
diff --git a/src/openai/types/beta/file_search_tool_param.py b/src/openai/types/beta/file_search_tool_param.py
index 97e651b0da..5ce91207ba 100644
--- a/src/openai/types/beta/file_search_tool_param.py
+++ b/src/openai/types/beta/file_search_tool_param.py
@@ -8,16 +8,16 @@
 
 
 class FileSearchRankingOptions(TypedDict, total=False):
-    ranker: Literal["auto", "default_2024_08_21"]
-    """The ranker to use for the file search.
+    score_threshold: Required[float]
+    """The score threshold for the file search.
 
-    If not specified will use the `auto` ranker.
+    All values must be a floating point number between 0 and 1.
     """
 
-    score_threshold: float
-    """The score threshold for the file search.
+    ranker: Literal["auto", "default_2024_08_21"]
+    """The ranker to use for the file search.
 
-    All values must be a floating point number between 0 and 1.
+    If not specified will use the `auto` ranker.
     """
 
 
@@ -37,6 +37,9 @@ class FileSearch(TypedDict, total=False):
     ranking_options: FileSearchRankingOptions
     """The ranking options for the file search.
 
+    If not specified, the file search tool will use the `auto` ranker and a
+    score_threshold of 0.
+
     See the
     [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
     for more information.
diff --git a/src/openai/types/beta/thread_create_and_run_params.py b/src/openai/types/beta/thread_create_and_run_params.py
index 370c2f9bce..20d525fa1a 100644
--- a/src/openai/types/beta/thread_create_and_run_params.py
+++ b/src/openai/types/beta/thread_create_and_run_params.py
@@ -98,11 +98,11 @@ class ThreadCreateAndRunParamsBase(TypedDict, total=False):
     and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
     Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-    Outputs which guarantees the model will match your supplied JSON schema. Learn
-    more in the
+    Outputs which ensures the model will match your supplied JSON schema. Learn more
+    in the
     [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-    Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+    Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
     message the model generates is valid JSON.
 
     **Important:** when using JSON mode, you **must** also instruct the model to
diff --git a/src/openai/types/beta/threads/run.py b/src/openai/types/beta/threads/run.py
index 0579e229d8..5abc1de295 100644
--- a/src/openai/types/beta/threads/run.py
+++ b/src/openai/types/beta/threads/run.py
@@ -172,11 +172,11 @@ class Run(BaseModel):
     and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
     Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-    Outputs which guarantees the model will match your supplied JSON schema. Learn
-    more in the
+    Outputs which ensures the model will match your supplied JSON schema. Learn more
+    in the
     [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-    Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+    Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
     message the model generates is valid JSON.
 
     **Important:** when using JSON mode, you **must** also instruct the model to
diff --git a/src/openai/types/beta/threads/run_create_params.py b/src/openai/types/beta/threads/run_create_params.py
index 7c5f571d58..824cb1a041 100644
--- a/src/openai/types/beta/threads/run_create_params.py
+++ b/src/openai/types/beta/threads/run_create_params.py
@@ -111,11 +111,11 @@ class RunCreateParamsBase(TypedDict, total=False):
     and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
     Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-    Outputs which guarantees the model will match your supplied JSON schema. Learn
-    more in the
+    Outputs which ensures the model will match your supplied JSON schema. Learn more
+    in the
     [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-    Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+    Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
     message the model generates is valid JSON.
 
     **Important:** when using JSON mode, you **must** also instruct the model to
diff --git a/src/openai/types/chat/completion_create_params.py b/src/openai/types/chat/completion_create_params.py
index b86dab742b..4ed89b00f5 100644
--- a/src/openai/types/chat/completion_create_params.py
+++ b/src/openai/types/chat/completion_create_params.py
@@ -87,15 +87,22 @@ class CompletionCreateParamsBase(TypedDict, total=False):
     `content` of `message`.
     """
 
+    max_completion_tokens: Optional[int]
+    """
+    An upper bound for the number of tokens that can be generated for a completion,
+    including visible output tokens and
+    [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
+    """
+
     max_tokens: Optional[int]
     """
     The maximum number of [tokens](/tokenizer) that can be generated in the chat
-    completion.
+    completion. This value can be used to control
+    [costs](https://openai.com/api/pricing/) for text generated via API.
 
-    The total length of input tokens and generated tokens is limited by the model's
-    context length.
-    [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
-    for counting tokens.
+    This value is now deprecated in favor of `max_completion_tokens`, and is not
+    compatible with
+    [o1 series models](https://platform.openai.com/docs/guides/reasoning).
     """
 
     n: Optional[int]
@@ -130,11 +137,11 @@ class CompletionCreateParamsBase(TypedDict, total=False):
     all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.
 
     Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
-    Outputs which guarantees the model will match your supplied JSON schema. Learn
-    more in the
+    Outputs which ensures the model will match your supplied JSON schema. Learn more
+    in the
     [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
 
-    Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+    Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the
     message the model generates is valid JSON.
 
     **Important:** when using JSON mode, you **must** also instruct the model to
@@ -160,8 +167,11 @@ class CompletionCreateParamsBase(TypedDict, total=False):
 
     This parameter is relevant for customers subscribed to the scale tier service:
 
-    - If set to 'auto', the system will utilize scale tier credits until they are
-      exhausted.
+    - If set to 'auto', and the Project is Scale tier enabled, the system will
+      utilize scale tier credits until they are exhausted.
+    - If set to 'auto', and the Project is not Scale tier enabled, the request will
+      be processed using the default service tier with a lower uptime SLA and no
+      latency guarentee.
     - If set to 'default', the request will be processed using the default service
       tier with a lower uptime SLA and no latency guarentee.
     - When not set, the default behavior is 'auto'.
diff --git a/src/openai/types/chat_model.py b/src/openai/types/chat_model.py
index 2372d5e14e..f8438c75c8 100644
--- a/src/openai/types/chat_model.py
+++ b/src/openai/types/chat_model.py
@@ -5,9 +5,13 @@
 __all__ = ["ChatModel"]
 
 ChatModel: TypeAlias = Literal[
+    "o1-preview",
+    "o1-preview-2024-09-12",
+    "o1-mini",
+    "o1-mini-2024-09-12",
     "gpt-4o",
-    "gpt-4o-2024-05-13",
     "gpt-4o-2024-08-06",
+    "gpt-4o-2024-05-13",
     "chatgpt-4o-latest",
     "gpt-4o-mini",
     "gpt-4o-mini-2024-07-18",
diff --git a/src/openai/types/completion_usage.py b/src/openai/types/completion_usage.py
index 0d57b96595..a4b9116e35 100644
--- a/src/openai/types/completion_usage.py
+++ b/src/openai/types/completion_usage.py
@@ -1,10 +1,15 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
-
+from typing import Optional
 
 from .._models import BaseModel
 
-__all__ = ["CompletionUsage"]
+__all__ = ["CompletionUsage", "CompletionTokensDetails"]
+
+
+class CompletionTokensDetails(BaseModel):
+    reasoning_tokens: Optional[int] = None
+    """Tokens generated by the model for reasoning."""
 
 
 class CompletionUsage(BaseModel):
@@ -16,3 +21,6 @@ class CompletionUsage(BaseModel):
 
     total_tokens: int
     """Total number of tokens used in the request (prompt + completion)."""
+
+    completion_tokens_details: Optional[CompletionTokensDetails] = None
+    """Breakdown of tokens used in a completion."""
diff --git a/src/openai/types/fine_tuning/job_create_params.py b/src/openai/types/fine_tuning/job_create_params.py
index e9be2ef1ca..8f5ea86274 100644
--- a/src/openai/types/fine_tuning/job_create_params.py
+++ b/src/openai/types/fine_tuning/job_create_params.py
@@ -50,7 +50,7 @@ class JobCreateParams(TypedDict, total=False):
 
     suffix: Optional[str]
     """
-    A string of up to 18 characters that will be added to your fine-tuned model
+    A string of up to 64 characters that will be added to your fine-tuned model
     name.
 
     For example, a `suffix` of "custom-model-name" would produce a model name like
diff --git a/tests/api_resources/chat/test_completions.py b/tests/api_resources/chat/test_completions.py
index 01ce3f1b0d..df7bc799df 100644
--- a/tests/api_resources/chat/test_completions.py
+++ b/tests/api_resources/chat/test_completions.py
@@ -54,6 +54,7 @@ def test_method_create_with_all_params_overload_1(self, client: OpenAI) -> None:
             ],
             logit_bias={"foo": 0},
             logprobs=True,
+            max_completion_tokens=0,
             max_tokens=0,
             n=1,
             parallel_tool_calls=True,
@@ -174,6 +175,7 @@ def test_method_create_with_all_params_overload_2(self, client: OpenAI) -> None:
             ],
             logit_bias={"foo": 0},
             logprobs=True,
+            max_completion_tokens=0,
             max_tokens=0,
             n=1,
             parallel_tool_calls=True,
@@ -296,6 +298,7 @@ async def test_method_create_with_all_params_overload_1(self, async_client: Asyn
             ],
             logit_bias={"foo": 0},
             logprobs=True,
+            max_completion_tokens=0,
             max_tokens=0,
             n=1,
             parallel_tool_calls=True,
@@ -416,6 +419,7 @@ async def test_method_create_with_all_params_overload_2(self, async_client: Asyn
             ],
             logit_bias={"foo": 0},
             logprobs=True,
+            max_completion_tokens=0,
             max_tokens=0,
             n=1,
             parallel_tool_calls=True,