Merge pull request #3359 from openai/release-please--branches--main--changes--next

release: 2.41.0

Author: apcha-oai

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "2.40.0"
+  ".": "2.41.0"
 }

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 262
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai/openai-a6fedde02dc6241719ebb2589062ba2892baa8dbe928a2d718643beede85e7b3.yml
-openapi_spec_hash: a712e4ee68f829570b3f5b267afa5a05
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai/openai-0161cb2a0faadedfc17ff59c7fcad9671962dbd170f83811003c23702148cf36.yml
+openapi_spec_hash: 1023c7442d0e2e7e213e8b3a253921c5
 config_hash: e02ca1082421dfe55b145c45e95d6126

CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## 2.41.0 (2026-06-03)
+
+Full Changelog: [v2.40.0...v2.41.0](https://github.com/openai/openai-python/compare/v2.40.0...v2.41.0)
+
+### Features
+
+* **api:** responses.moderation and chat_completions.moderation ([87e46c2](https://github.com/openai/openai-python/commit/87e46c25ac9ca8cff407b52ad9fb33e326c059d6))
+
 ## 2.40.0 (2026-06-01)
 
 Full Changelog: [v2.39.0...v2.40.0](https://github.com/openai/openai-python/compare/v2.39.0...v2.40.0)

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "openai"
-version = "2.40.0"
+version = "2.41.0"
 description = "The official Python library for the openai API"
 dynamic = ["readme"]
 license = "Apache-2.0"

src/openai/_version.py

@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "openai"
-__version__ = "2.40.0"  # x-release-please-version
+__version__ = "2.41.0"  # x-release-please-version

src/openai/auth/_workload.py

@@ -28,6 +28,7 @@ class SubjectTokenProvider(TypedDict):
 
 class WorkloadIdentity(TypedDict):
     """Identity provider resource id in WIFAPI."""
+
     identity_provider_id: str
 
     """Service account id to bind the verified external identity to."""

src/openai/resources/chat/completions/completions.py

@@ -104,6 +104,7 @@ def parse(
         max_tokens: Optional[int] | Omit = omit,
         metadata: Optional[Metadata] | Omit = omit,
         modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        moderation: Optional[completion_create_params.Moderation] | Omit = omit,
         n: Optional[int] | Omit = omit,
         parallel_tool_calls: bool | Omit = omit,
         prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
@@ -204,6 +205,7 @@ def parser(raw_completion: ChatCompletion) -> ParsedChatCompletion[ResponseForma
                     "max_tokens": max_tokens,
                     "metadata": metadata,
                     "modalities": modalities,
+                    "moderation": moderation,
                     "n": n,
                     "parallel_tool_calls": parallel_tool_calls,
                     "prediction": prediction,
@@ -260,6 +262,7 @@ def create(
         max_tokens: Optional[int] | Omit = omit,
         metadata: Optional[Metadata] | Omit = omit,
         modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        moderation: Optional[completion_create_params.Moderation] | Omit = omit,
         n: Optional[int] | Omit = omit,
         parallel_tool_calls: bool | Omit = omit,
         prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
@@ -396,6 +399,8 @@ def create(
 
               `["text", "audio"]`
 
+          moderation: Configuration for running moderation on the request input and generated output.
+
           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
               choices. Keep `n` as `1` to minimize costs.
@@ -576,6 +581,7 @@ def create(
         max_tokens: Optional[int] | Omit = omit,
         metadata: Optional[Metadata] | Omit = omit,
         modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        moderation: Optional[completion_create_params.Moderation] | Omit = omit,
         n: Optional[int] | Omit = omit,
         parallel_tool_calls: bool | Omit = omit,
         prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
@@ -720,6 +726,8 @@ def create(
 
               `["text", "audio"]`
 
+          moderation: Configuration for running moderation on the request input and generated output.
+
           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
               choices. Keep `n` as `1` to minimize costs.
@@ -891,6 +899,7 @@ def create(
         max_tokens: Optional[int] | Omit = omit,
         metadata: Optional[Metadata] | Omit = omit,
         modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        moderation: Optional[completion_create_params.Moderation] | Omit = omit,
         n: Optional[int] | Omit = omit,
         parallel_tool_calls: bool | Omit = omit,
         prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
@@ -1035,6 +1044,8 @@ def create(
 
               `["text", "audio"]`
 
+          moderation: Configuration for running moderation on the request input and generated output.
+
           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
               choices. Keep `n` as `1` to minimize costs.
@@ -1205,6 +1216,7 @@ def create(
         max_tokens: Optional[int] | Omit = omit,
         metadata: Optional[Metadata] | Omit = omit,
         modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        moderation: Optional[completion_create_params.Moderation] | Omit = omit,
         n: Optional[int] | Omit = omit,
         parallel_tool_calls: bool | Omit = omit,
         prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
@@ -1252,6 +1264,7 @@ def create(
                     "max_tokens": max_tokens,
                     "metadata": metadata,
                     "modalities": modalities,
+                    "moderation": moderation,
                     "n": n,
                     "parallel_tool_calls": parallel_tool_calls,
                     "prediction": prediction,
@@ -1501,6 +1514,7 @@ def stream(
         max_tokens: Optional[int] | Omit = omit,
         metadata: Optional[Metadata] | Omit = omit,
         modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        moderation: Optional[completion_create_params.Moderation] | Omit = omit,
         n: Optional[int] | Omit = omit,
         parallel_tool_calls: bool | Omit = omit,
         prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
@@ -1572,6 +1586,7 @@ def stream(
             max_tokens=max_tokens,
             metadata=metadata,
             modalities=modalities,
+            moderation=moderation,
             n=n,
             parallel_tool_calls=parallel_tool_calls,
             prediction=prediction,
@@ -1652,6 +1667,7 @@ async def parse(
         max_tokens: Optional[int] | Omit = omit,
         metadata: Optional[Metadata] | Omit = omit,
         modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        moderation: Optional[completion_create_params.Moderation] | Omit = omit,
         n: Optional[int] | Omit = omit,
         parallel_tool_calls: bool | Omit = omit,
         prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
@@ -1752,6 +1768,7 @@ def parser(raw_completion: ChatCompletion) -> ParsedChatCompletion[ResponseForma
                     "max_tokens": max_tokens,
                     "metadata": metadata,
                     "modalities": modalities,
+                    "moderation": moderation,
                     "n": n,
                     "parallel_tool_calls": parallel_tool_calls,
                     "prediction": prediction,
@@ -1808,6 +1825,7 @@ async def create(
         max_tokens: Optional[int] | Omit = omit,
         metadata: Optional[Metadata] | Omit = omit,
         modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        moderation: Optional[completion_create_params.Moderation] | Omit = omit,
         n: Optional[int] | Omit = omit,
         parallel_tool_calls: bool | Omit = omit,
         prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
@@ -1944,6 +1962,8 @@ async def create(
 
               `["text", "audio"]`
 
+          moderation: Configuration for running moderation on the request input and generated output.
+
           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
               choices. Keep `n` as `1` to minimize costs.
@@ -2124,6 +2144,7 @@ async def create(
         max_tokens: Optional[int] | Omit = omit,
         metadata: Optional[Metadata] | Omit = omit,
         modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        moderation: Optional[completion_create_params.Moderation] | Omit = omit,
         n: Optional[int] | Omit = omit,
         parallel_tool_calls: bool | Omit = omit,
         prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
@@ -2268,6 +2289,8 @@ async def create(
 
               `["text", "audio"]`
 
+          moderation: Configuration for running moderation on the request input and generated output.
+
           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
               choices. Keep `n` as `1` to minimize costs.
@@ -2439,6 +2462,7 @@ async def create(
         max_tokens: Optional[int] | Omit = omit,
         metadata: Optional[Metadata] | Omit = omit,
         modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        moderation: Optional[completion_create_params.Moderation] | Omit = omit,
         n: Optional[int] | Omit = omit,
         parallel_tool_calls: bool | Omit = omit,
         prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
@@ -2583,6 +2607,8 @@ async def create(
 
               `["text", "audio"]`
 
+          moderation: Configuration for running moderation on the request input and generated output.
+
           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
               choices. Keep `n` as `1` to minimize costs.
@@ -2753,6 +2779,7 @@ async def create(
         max_tokens: Optional[int] | Omit = omit,
         metadata: Optional[Metadata] | Omit = omit,
         modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        moderation: Optional[completion_create_params.Moderation] | Omit = omit,
         n: Optional[int] | Omit = omit,
         parallel_tool_calls: bool | Omit = omit,
         prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
@@ -2800,6 +2827,7 @@ async def create(
                     "max_tokens": max_tokens,
                     "metadata": metadata,
                     "modalities": modalities,
+                    "moderation": moderation,
                     "n": n,
                     "parallel_tool_calls": parallel_tool_calls,
                     "prediction": prediction,
@@ -3049,6 +3077,7 @@ def stream(
         max_tokens: Optional[int] | Omit = omit,
         metadata: Optional[Metadata] | Omit = omit,
         modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        moderation: Optional[completion_create_params.Moderation] | Omit = omit,
         n: Optional[int] | Omit = omit,
         parallel_tool_calls: bool | Omit = omit,
         prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
@@ -3121,6 +3150,7 @@ def stream(
             max_tokens=max_tokens,
             metadata=metadata,
             modalities=modalities,
+            moderation=moderation,
             n=n,
             parallel_tool_calls=parallel_tool_calls,
             prediction=prediction,