Merge branch 'main' into main

Author: aaaugustine29

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "2.1.0"
+  ".": "2.8.1"
 }

.stats.yml

@@ -1,4 +1,4 @@
-configured_endpoints: 123
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-fadefdc7c7e30df47c09df323669b242ff90ee08e51f304175ace5274e0aab49.yml
-openapi_spec_hash: 6d20f639d9ff8a097a34962da6218231
-config_hash: 902654e60f5d659f2bfcfd903e17c46d
+configured_endpoints: 136
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-a7e92d12ebe89ca019a7ac5b29759064eefa2c38fe08d03516f2620e66abb32b.yml
+openapi_spec_hash: acbc703b2739447abc6312b2d753631c
+config_hash: b876221dfb213df9f0a999e75d38a65e

CHANGELOG.md

@@ -1,5 +1,148 @@
 # Changelog
 
+## 2.8.1 (2025-11-17)
+
+Full Changelog: [v2.8.0...v2.8.1](https://github.com/openai/openai-python/compare/v2.8.0...v2.8.1)
+
+### Bug Fixes
+
+* **api:** align types of input items / output items for typescript ([64c9fb3](https://github.com/openai/openai-python/commit/64c9fb3fcc79f0049b3a36bd429faf0600d969f6))
+
+## 2.8.0 (2025-11-13)
+
+Full Changelog: [v2.7.2...v2.8.0](https://github.com/openai/openai-python/compare/v2.7.2...v2.8.0)
+
+### Features
+
+* **api:** gpt 5.1 ([8d9f2ca](https://github.com/openai/openai-python/commit/8d9f2cab4cb2e12f6e2ab1de967f858736a656ac))
+
+
+### Bug Fixes
+
+* **compat:** update signatures of `model_dump` and `model_dump_json` for Pydantic v1 ([c7bd234](https://github.com/openai/openai-python/commit/c7bd234b18239fcdbf0edb1b51ca9116c0ac7251))
+
+## 2.7.2 (2025-11-10)
+
+Full Changelog: [v2.7.1...v2.7.2](https://github.com/openai/openai-python/compare/v2.7.1...v2.7.2)
+
+### Bug Fixes
+
+* compat with Python 3.14 ([15a7ec8](https://github.com/openai/openai-python/commit/15a7ec8a753d7f57d525fca60c547fd5331cb214))
+
+
+### Chores
+
+* **package:** drop Python 3.8 support ([afc14f2](https://github.com/openai/openai-python/commit/afc14f2e42e7a8174f2ff1a5672829b808a716bf))
+
+## 2.7.1 (2025-11-04)
+
+Full Changelog: [v2.7.0...v2.7.1](https://github.com/openai/openai-python/compare/v2.7.0...v2.7.1)
+
+### Bug Fixes
+
+* **api:** fix nullability of logprobs ([373b7f6](https://github.com/openai/openai-python/commit/373b7f6e4255dfef3ccd92520011e8ba44e8b7f0))
+
+## 2.7.0 (2025-11-03)
+
+Full Changelog: [v2.6.1...v2.7.0](https://github.com/openai/openai-python/compare/v2.6.1...v2.7.0)
+
+### Features
+
+* **api:** Realtime API token_limits, Hybrid searching ranking options ([5b43992](https://github.com/openai/openai-python/commit/5b4399219d7ed326411aec524d25ef2b8e3152fc))
+* **api:** remove InputAudio from ResponseInputContent ([bd70a33](https://github.com/openai/openai-python/commit/bd70a33234741fa68c185105e4f53cc0275a2a50))
+
+
+### Bug Fixes
+
+* **client:** close streams without requiring full consumption ([d8bb7d6](https://github.com/openai/openai-python/commit/d8bb7d6d728c5481de4198eebe668b67803ae14a))
+* **readme:** update realtime examples ([#2714](https://github.com/openai/openai-python/issues/2714)) ([d0370a8](https://github.com/openai/openai-python/commit/d0370a8d61fc2f710a34d8aad48f649a9683106d))
+* **uploads:** avoid file handle leak ([4f1b691](https://github.com/openai/openai-python/commit/4f1b691ab4db41aebd397ec41942b43fb0f0743c))
+
+
+### Chores
+
+* **internal/tests:** avoid race condition with implicit client cleanup ([933d23b](https://github.com/openai/openai-python/commit/933d23bd8d7809c77e0796becfe052167d44d40a))
+* **internal:** grammar fix (it's -> its) ([f7e9e9e](https://github.com/openai/openai-python/commit/f7e9e9e4f43039f19a41375a6d2b2bdc2264dad7))
+
+## 2.6.1 (2025-10-24)
+
+Full Changelog: [v2.6.0...v2.6.1](https://github.com/openai/openai-python/compare/v2.6.0...v2.6.1)
+
+### Bug Fixes
+
+* **api:** docs updates ([d01a0c9](https://github.com/openai/openai-python/commit/d01a0c96ecb94c78b7e16546790c573704b7515b))
+
+
+### Chores
+
+* **client:** clean up custom translations code ([cfb9e25](https://github.com/openai/openai-python/commit/cfb9e25855b8eb020abe02cdd99566adf474e821))
+
+## 2.6.0 (2025-10-20)
+
+Full Changelog: [v2.5.0...v2.6.0](https://github.com/openai/openai-python/compare/v2.5.0...v2.6.0)
+
+### Features
+
+* **api:** Add responses.input_tokens.count ([6dd09e2](https://github.com/openai/openai-python/commit/6dd09e2829f385f72b28620888d91a4493c96772))
+
+
+### Bug Fixes
+
+* **api:** internal openapi updates ([caabd7c](https://github.com/openai/openai-python/commit/caabd7c81f0f557f66dc0089af460185a5816c11))
+
+## 2.5.0 (2025-10-17)
+
+Full Changelog: [v2.4.0...v2.5.0](https://github.com/openai/openai-python/compare/v2.4.0...v2.5.0)
+
+### Features
+
+* **api:** api update ([8b280d5](https://github.com/openai/openai-python/commit/8b280d57d6d361bc3a032e030158f6859c445291))
+
+
+### Chores
+
+* bump `httpx-aiohttp` version to 0.1.9 ([67f2f0a](https://github.com/openai/openai-python/commit/67f2f0afe51dab9d5899fe18b1a4e86b2c774d10))
+
+## 2.4.0 (2025-10-16)
+
+Full Changelog: [v2.3.0...v2.4.0](https://github.com/openai/openai-python/compare/v2.3.0...v2.4.0)
+
+### Features
+
+* **api:** Add support for gpt-4o-transcribe-diarize on audio/transcriptions endpoint ([bdbe9b8](https://github.com/openai/openai-python/commit/bdbe9b8f440209afa2979db4a9eda9579b3d2550))
+
+
+### Chores
+
+* fix dangling comment ([da14e99](https://github.com/openai/openai-python/commit/da14e9960608f7ade6f5cdf91967830c8a6c1657))
+* **internal:** detect missing future annotations with ruff ([2672b8f](https://github.com/openai/openai-python/commit/2672b8f0726300f7c62c356f25545ef0b3c0bb2e))
+
+## 2.3.0 (2025-10-10)
+
+Full Changelog: [v2.2.0...v2.3.0](https://github.com/openai/openai-python/compare/v2.2.0...v2.3.0)
+
+### Features
+
+* **api:** comparison filter in/not in ([aa49f62](https://github.com/openai/openai-python/commit/aa49f626a6ea9d77ad008badfb3741e16232d62f))
+
+
+### Chores
+
+* **package:** bump jiter to >=0.10.0 to support Python 3.14 ([#2618](https://github.com/openai/openai-python/issues/2618)) ([aa445ca](https://github.com/openai/openai-python/commit/aa445cab5c93c6908697fe98e73e16963330b141))
+
+## 2.2.0 (2025-10-06)
+
+Full Changelog: [v2.1.0...v2.2.0](https://github.com/openai/openai-python/compare/v2.1.0...v2.2.0)
+
+### Features
+
+* **api:** dev day 2025 launches ([38ac009](https://github.com/openai/openai-python/commit/38ac0093ebb3419b1e2280d0dc2d26c74a2bbbec))
+
+
+### Bug Fixes
+
+* **client:** add chatkit to beta resource ([de3e561](https://github.com/openai/openai-python/commit/de3e5619d0a85b17906a9416039ef309e820dc0f))
+
 ## 2.1.0 (2025-10-02)
 
 Full Changelog: [v2.0.1...v2.1.0](https://github.com/openai/openai-python/compare/v2.0.1...v2.1.0)

README.md

@@ -3,7 +3,7 @@
 <!-- prettier-ignore -->
 [![PyPI version](https://img.shields.io/pypi/v/openai.svg?label=pypi%20(stable))](https://pypi.org/project/openai/)
 
-The OpenAI Python library provides convenient access to the OpenAI REST API from any Python 3.8+
+The OpenAI Python library provides convenient access to the OpenAI REST API from any Python 3.9+
 application. The library includes type definitions for all request params and response fields,
 and offers both synchronous and asynchronous clients powered by [httpx](https://github.com/encode/httpx).
 
@@ -244,7 +244,9 @@ async def main():
     client = AsyncOpenAI()
 
     async with client.realtime.connect(model="gpt-realtime") as connection:
-        await connection.session.update(session={'modalities': ['text']})
+        await connection.session.update(
+            session={"type": "realtime", "output_modalities": ["text"]}
+        )
 
         await connection.conversation.item.create(
             item={
@@ -256,10 +258,10 @@ async def main():
         await connection.response.create()
 
         async for event in connection:
-            if event.type == 'response.text.delta':
+            if event.type == "response.output_text.delta":
                 print(event.delta, flush=True, end="")
 
-            elif event.type == 'response.text.done':
+            elif event.type == "response.output_text.done":
                 print()
 
             elif event.type == "response.done":
@@ -861,7 +863,7 @@ print(openai.__version__)
 
 ## Requirements
 
-Python 3.8 or higher.
+Python 3.9 or higher.
 
 ## Contributing
 

api.md

@@ -171,11 +171,14 @@ Types:
 ```python
 from openai.types.audio import (
     Transcription,
+    TranscriptionDiarized,
+    TranscriptionDiarizedSegment,
     TranscriptionInclude,
     TranscriptionSegment,
     TranscriptionStreamEvent,
     TranscriptionTextDeltaEvent,
     TranscriptionTextDoneEvent,
+    TranscriptionTextSegmentEvent,
     TranscriptionVerbose,
     TranscriptionWord,
     TranscriptionCreateResponse,
@@ -729,12 +732,16 @@ Types:
 
 ```python
 from openai.types.responses import (
+    ApplyPatchTool,
     ComputerTool,
     CustomTool,
     EasyInputMessage,
     FileSearchTool,
+    FunctionShellTool,
     FunctionTool,
     Response,
+    ResponseApplyPatchToolCall,
+    ResponseApplyPatchToolCallOutput,
     ResponseAudioDeltaEvent,
     ResponseAudioDoneEvent,
     ResponseAudioTranscriptDeltaEvent,
@@ -771,6 +778,9 @@ from openai.types.responses import (
     ResponseFunctionCallArgumentsDoneEvent,
     ResponseFunctionCallOutputItem,
     ResponseFunctionCallOutputItemList,
+    ResponseFunctionShellCallOutputContent,
+    ResponseFunctionShellToolCall,
+    ResponseFunctionShellToolCallOutput,
     ResponseFunctionToolCall,
     ResponseFunctionToolCallItem,
     ResponseFunctionToolCallOutputItem,
@@ -833,10 +843,12 @@ from openai.types.responses import (
     ResponseWebSearchCallSearchingEvent,
     Tool,
     ToolChoiceAllowed,
+    ToolChoiceApplyPatch,
     ToolChoiceCustom,
     ToolChoiceFunction,
     ToolChoiceMcp,
     ToolChoiceOptions,
+    ToolChoiceShell,
     ToolChoiceTypes,
     WebSearchPreviewTool,
     WebSearchTool,
@@ -862,6 +874,18 @@ Methods:
 
 - <code title="get /responses/{response_id}/input_items">client.responses.input_items.<a href="./src/openai/resources/responses/input_items.py">list</a>(response_id, \*\*<a href="src/openai/types/responses/input_item_list_params.py">params</a>) -> <a href="./src/openai/types/responses/response_item.py">SyncCursorPage[ResponseItem]</a></code>
 
+## InputTokens
+
+Types:
+
+```python
+from openai.types.responses import InputTokenCountResponse
+```
+
+Methods:
+
+- <code title="post /responses/input_tokens">client.responses.input_tokens.<a href="./src/openai/resources/responses/input_tokens.py">count</a>(\*\*<a href="src/openai/types/responses/input_token_count_params.py">params</a>) -> <a href="./src/openai/types/responses/input_token_count_response.py">InputTokenCountResponse</a></code>
+
 # Realtime
 
 Types:
@@ -1139,3 +1163,29 @@ Methods:
 Methods:
 
 - <code title="get /containers/{container_id}/files/{file_id}/content">client.containers.files.content.<a href="./src/openai/resources/containers/files/content.py">retrieve</a>(file_id, \*, container_id) -> HttpxBinaryResponseContent</code>
+
+# Videos
+
+Types:
+
+```python
+from openai.types import (
+    Video,
+    VideoCreateError,
+    VideoModel,
+    VideoSeconds,
+    VideoSize,
+    VideoDeleteResponse,
+)
+```
+
+Methods:
+
+- <code title="post /videos">client.videos.<a href="./src/openai/resources/videos.py">create</a>(\*\*<a href="src/openai/types/video_create_params.py">params</a>) -> <a href="./src/openai/types/video.py">Video</a></code>
+- <code title="get /videos/{video_id}">client.videos.<a href="./src/openai/resources/videos.py">retrieve</a>(video_id) -> <a href="./src/openai/types/video.py">Video</a></code>
+- <code title="get /videos">client.videos.<a href="./src/openai/resources/videos.py">list</a>(\*\*<a href="src/openai/types/video_list_params.py">params</a>) -> <a href="./src/openai/types/video.py">SyncConversationCursorPage[Video]</a></code>
+- <code title="delete /videos/{video_id}">client.videos.<a href="./src/openai/resources/videos.py">delete</a>(video_id) -> <a href="./src/openai/types/video_delete_response.py">VideoDeleteResponse</a></code>
+- <code title="get /videos/{video_id}/content">client.videos.<a href="./src/openai/resources/videos.py">download_content</a>(video_id, \*\*<a href="src/openai/types/video_download_content_params.py">params</a>) -> HttpxBinaryResponseContent</code>
+- <code title="post /videos/{video_id}/remix">client.videos.<a href="./src/openai/resources/videos.py">remix</a>(video_id, \*\*<a href="src/openai/types/video_remix_params.py">params</a>) -> <a href="./src/openai/types/video.py">Video</a></code>
+- <code>client.videos.<a href="./src/openai/resources/videos.py">create_and_poll</a>(\*args) -> Video</code>
+

examples/responses_input_tokens.py

@@ -0,0 +1,54 @@
+from typing import List
+
+from openai import OpenAI
+from openai.types.responses.tool_param import ToolParam
+from openai.types.responses.response_input_item_param import ResponseInputItemParam
+
+
+def main() -> None:
+    client = OpenAI()
+    tools: List[ToolParam] = [
+        {
+            "type": "function",
+            "name": "get_current_weather",
+            "description": "Get current weather in a given location",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "location": {
+                        "type": "string",
+                        "description": "City and state, e.g. San Francisco, CA",
+                    },
+                    "unit": {
+                        "type": "string",
+                        "enum": ["c", "f"],
+                        "description": "Temperature unit to use",
+                    },
+                },
+                "required": ["location", "unit"],
+                "additionalProperties": False,
+            },
+            "strict": True,
+        }
+    ]
+
+    input_items: List[ResponseInputItemParam] = [
+        {
+            "type": "message",
+            "role": "user",
+            "content": [{"type": "input_text", "text": "What's the weather in San Francisco today?"}],
+        }
+    ]
+
+    response = client.responses.input_tokens.count(
+        model="gpt-5",
+        instructions="You are a concise assistant.",
+        input=input_items,
+        tools=tools,
+        tool_choice={"type": "function", "name": "get_current_weather"},
+    )
+    print(f"input tokens: {response.input_tokens}")
+
+
+if __name__ == "__main__":
+    main()

examples/video.py

@@ -0,0 +1,22 @@
+#!/usr/bin/env -S poetry run python
+
+import asyncio
+
+from openai import AsyncOpenAI
+
+client = AsyncOpenAI()
+
+
+async def main() -> None:
+    video = await client.videos.create_and_poll(
+        model="sora-2",
+        prompt="A video of the words 'Thank you' in sparkling letters",
+    )
+
+    if video.status == "completed":
+        print("Video successfully completed: ", video)
+    else:
+        print("Video creation failed. Status: ", video.status)
+
+
+asyncio.run(main())

helpers.md

@@ -514,4 +514,5 @@ client.beta.vector_stores.files.upload_and_poll(...)
 client.beta.vector_stores.files.create_and_poll(...)
 client.beta.vector_stores.file_batches.create_and_poll(...)
 client.beta.vector_stores.file_batches.upload_and_poll(...)
+client.videos.create_and_poll(...)
 ```