openai · stainless-app · Aug 18, 2025 · Aug 15, 2025 · Aug 18, 2025
@@ -1,3 +1,3 @@
 {
-  ".": "1.99.9"
+  ".": "1.100.0"
 }
@@ -1,4 +1,4 @@
 configured_endpoints: 111
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-9cadfad609f94f20ebf74fdc06a80302f1a324dc69700a309a8056aabca82fd2.yml
-openapi_spec_hash: 3eb8d86c06f0bb5e1190983e5acfc9ba
-config_hash: 68337b532875626269c304372a669f67
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-24be531010b354303d741fc9247c1f84f75978f9f7de68aca92cb4f240a04722.yml
+openapi_spec_hash: 3e46f439f6a863beadc71577eb4efa15
+config_hash: ed87b9139ac595a04a2162d754df2fed
@@ -1,5 +1,13 @@
 # Changelog
 
+## 1.100.0 (2025-08-18)
+
+Full Changelog: [v1.99.9...v1.100.0](https://github.com/openai/openai-python/compare/v1.99.9...v1.100.0)
+
+### Features
+
+* **api:** add new text parameters, expiration options ([e3dfa7c](https://github.com/openai/openai-python/commit/e3dfa7c417b8c750ff62d98650e75e72ad9b1477))
+
 ## 1.99.9 (2025-08-12)
 
 Full Changelog: [v1.99.8...v1.99.9](https://github.com/openai/openai-python/compare/v1.99.8...v1.99.9)

@@ -1,6 +1,6 @@
 [project]
 name = "openai"
-version = "1.99.9"
+version = "1.100.0"
 description = "The official Python library for the openai API"
 dynamic = ["readme"]
 license = "Apache-2.0"

@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "openai"
-__version__ = "1.99.9"  # x-release-please-version
+__version__ = "1.100.0"  # x-release-please-version
@@ -49,6 +49,7 @@ def create(
         endpoint: Literal["/v1/responses", "/v1/chat/completions", "/v1/embeddings", "/v1/completions"],
         input_file_id: str,
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
+        output_expires_after: batch_create_params.OutputExpiresAfter | NotGiven = NOT_GIVEN,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -85,6 +86,9 @@ def create(
               Keys are strings with a maximum length of 64 characters. Values are strings with
               a maximum length of 512 characters.
 
+          output_expires_after: The expiration policy for the output and/or error file that are generated for a
+              batch.
+
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -101,6 +105,7 @@ def create(
                     "endpoint": endpoint,
                     "input_file_id": input_file_id,
                     "metadata": metadata,
+                    "output_expires_after": output_expires_after,
                 },
                 batch_create_params.BatchCreateParams,
             ),
@@ -259,6 +264,7 @@ async def create(
         endpoint: Literal["/v1/responses", "/v1/chat/completions", "/v1/embeddings", "/v1/completions"],
         input_file_id: str,
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
+        output_expires_after: batch_create_params.OutputExpiresAfter | NotGiven = NOT_GIVEN,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -295,6 +301,9 @@ async def create(
               Keys are strings with a maximum length of 64 characters. Values are strings with
               a maximum length of 512 characters.
 
+          output_expires_after: The expiration policy for the output and/or error file that are generated for a
+              batch.
+
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -311,6 +320,7 @@ async def create(
                     "endpoint": endpoint,
                     "input_file_id": input_file_id,
                     "metadata": metadata,
+                    "output_expires_after": output_expires_after,
                 },
                 batch_create_params.BatchCreateParams,
             ),

@@ -652,8 +652,8 @@ def cancel(self, *, event_id: str | NotGiven = NOT_GIVEN, response_id: str | Not
         """Send this event to cancel an in-progress response.
 
         The server will respond
-        with a `response.cancelled` event or an error if there is no response to
-        cancel.
+        with a `response.done` event with a status of `response.status=cancelled`. If
+        there is no response to cancel, the server will respond with an error.
         """
         self._connection.send(
             cast(
@@ -904,8 +904,8 @@ async def cancel(self, *, event_id: str | NotGiven = NOT_GIVEN, response_id: str
         """Send this event to cancel an in-progress response.
 
         The server will respond
-        with a `response.cancelled` event or an error if there is no response to
-        cancel.
+        with a `response.done` event with a status of `response.status=cancelled`. If
+        there is no response to cancel, the server will respond with an error.
         """
         await self._connection.send(
             cast(

@@ -152,7 +152,7 @@ def create(
               set to `null` to turn off, in which case the client must manually trigger model
               response. Server VAD means that the model will detect the start and end of
               speech based on audio volume and respond at the end of user speech. Semantic VAD
-              is more advanced and uses a turn detection model (in conjuction with VAD) to
+              is more advanced and uses a turn detection model (in conjunction with VAD) to
               semantically estimate whether the user has finished speaking, then dynamically
               sets a timeout based on this probability. For example, if user audio trails off
               with "uhhm", the model will score a low probability of turn end and wait longer
@@ -334,7 +334,7 @@ async def create(
               set to `null` to turn off, in which case the client must manually trigger model
               response. Server VAD means that the model will detect the start and end of
               speech based on audio volume and respond at the end of user speech. Semantic VAD
-              is more advanced and uses a turn detection model (in conjuction with VAD) to
+              is more advanced and uses a turn detection model (in conjunction with VAD) to
               semantically estimate whether the user has finished speaking, then dynamically
               sets a timeout based on this probability. For example, if user audio trails off
               with "uhhm", the model will score a low probability of turn end and wait longer

@@ -96,7 +96,7 @@ def create(
               set to `null` to turn off, in which case the client must manually trigger model
               response. Server VAD means that the model will detect the start and end of
               speech based on audio volume and respond at the end of user speech. Semantic VAD
-              is more advanced and uses a turn detection model (in conjuction with VAD) to
+              is more advanced and uses a turn detection model (in conjunction with VAD) to
               semantically estimate whether the user has finished speaking, then dynamically
               sets a timeout based on this probability. For example, if user audio trails off
               with "uhhm", the model will score a low probability of turn end and wait longer
@@ -209,7 +209,7 @@ async def create(
               set to `null` to turn off, in which case the client must manually trigger model
               response. Server VAD means that the model will detect the start and end of
               speech based on audio volume and respond at the end of user speech. Semantic VAD
-              is more advanced and uses a turn detection model (in conjuction with VAD) to
+              is more advanced and uses a turn detection model (in conjunction with VAD) to
               semantically estimate whether the user has finished speaking, then dynamically
               sets a timeout based on this probability. For example, if user audio trails off
               with "uhhm", the model will score a low probability of turn end and wait longer

@@ -220,7 +220,7 @@ def create(
               We generally recommend altering this or temperature but not both.
 
           truncation_strategy: Controls for how a thread will be truncated prior to the run. Use this to
-              control the intial context window of the run.
+              control the initial context window of the run.
 
           extra_headers: Send extra headers
 
@@ -370,7 +370,7 @@ def create(
               We generally recommend altering this or temperature but not both.
 
           truncation_strategy: Controls for how a thread will be truncated prior to the run. Use this to
-              control the intial context window of the run.
+              control the initial context window of the run.
 
           extra_headers: Send extra headers
 
@@ -520,7 +520,7 @@ def create(
               We generally recommend altering this or temperature but not both.
 
           truncation_strategy: Controls for how a thread will be truncated prior to the run. Use this to
-              control the intial context window of the run.
+              control the initial context window of the run.
 
           extra_headers: Send extra headers
 
@@ -1650,7 +1650,7 @@ async def create(
               We generally recommend altering this or temperature but not both.
 
           truncation_strategy: Controls for how a thread will be truncated prior to the run. Use this to
-              control the intial context window of the run.
+              control the initial context window of the run.
 
           extra_headers: Send extra headers
 
@@ -1800,7 +1800,7 @@ async def create(
               We generally recommend altering this or temperature but not both.
 
           truncation_strategy: Controls for how a thread will be truncated prior to the run. Use this to
-              control the intial context window of the run.
+              control the initial context window of the run.
 
           extra_headers: Send extra headers
 
@@ -1950,7 +1950,7 @@ async def create(
               We generally recommend altering this or temperature but not both.
 
           truncation_strategy: Controls for how a thread will be truncated prior to the run. Use this to
-              control the intial context window of the run.
+              control the initial context window of the run.
 
           extra_headers: Send extra headers
 

@@ -393,7 +393,7 @@ def create_and_run(
               We generally recommend altering this or temperature but not both.
 
           truncation_strategy: Controls for how a thread will be truncated prior to the run. Use this to
-              control the intial context window of the run.
+              control the initial context window of the run.
 
           extra_headers: Send extra headers
 
@@ -527,7 +527,7 @@ def create_and_run(
               We generally recommend altering this or temperature but not both.
 
           truncation_strategy: Controls for how a thread will be truncated prior to the run. Use this to
-              control the intial context window of the run.
+              control the initial context window of the run.
 
           extra_headers: Send extra headers
 
@@ -661,7 +661,7 @@ def create_and_run(
               We generally recommend altering this or temperature but not both.
 
           truncation_strategy: Controls for how a thread will be truncated prior to the run. Use this to
-              control the intial context window of the run.
+              control the initial context window of the run.
 
           extra_headers: Send extra headers
 
@@ -1251,7 +1251,7 @@ async def create_and_run(
               We generally recommend altering this or temperature but not both.
 
           truncation_strategy: Controls for how a thread will be truncated prior to the run. Use this to
-              control the intial context window of the run.
+              control the initial context window of the run.
 
           extra_headers: Send extra headers
 
@@ -1385,7 +1385,7 @@ async def create_and_run(
               We generally recommend altering this or temperature but not both.
 
           truncation_strategy: Controls for how a thread will be truncated prior to the run. Use this to
-              control the intial context window of the run.
+              control the initial context window of the run.
 
           extra_headers: Send extra headers
 
@@ -1519,7 +1519,7 @@ async def create_and_run(
               We generally recommend altering this or temperature but not both.
 
           truncation_strategy: Controls for how a thread will be truncated prior to the run. Use this to
-              control the intial context window of the run.
+              control the initial context window of the run.
 
           extra_headers: Send extra headers