openai · kwhinnery-openai · Jun 16, 2025 · Jun 13, 2025 · Jun 16, 2025 · Jun 16, 2025
@@ -1,3 +1,3 @@
 {
-  ".": "1.86.0"
+  ".": "1.87.0"
 }
@@ -1,4 +1,4 @@
 configured_endpoints: 111
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-3ae9c18dd7ccfc3ac5206f24394665f563a19015cfa8847b2801a2694d012abc.yml
-openapi_spec_hash: 48175b03b58805cd5c80793c66fd54e5
-config_hash: 4caff63b74a41f71006987db702f2918
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-9e41d2d5471d2c28bff0d616f4476f5b0e6c541ef4cb51bdaaef5fdf5e13c8b2.yml
+openapi_spec_hash: 86f765e18d00e32cf2ce9db7ab84d946
+config_hash: fd2af1d5eff0995bb7dc02ac9a34851d
@@ -1,5 +1,25 @@
 # Changelog
 
+## 1.87.0 (2025-06-16)
+
+Full Changelog: [v1.86.0...v1.87.0](https://github.com/openai/openai-python/compare/v1.86.0...v1.87.0)
+
+### Features
+
+* **api:** add reusable prompt IDs ([36bfe6e](https://github.com/openai/openai-python/commit/36bfe6e8ae12a31624ba1a360d9260f0aeec448a))
+
+
+### Bug Fixes
+
+* **client:** update service_tier on `client.beta.chat.completions` ([aa488d5](https://github.com/openai/openai-python/commit/aa488d5cf210d8640f87216538d4ff79d7181f2a))
+
+
+### Chores
+
+* **internal:** codegen related update ([b1a31e5](https://github.com/openai/openai-python/commit/b1a31e5ef4387d9f82cf33f9461371651788d381))
+* **internal:** update conftest.py ([bba0213](https://github.com/openai/openai-python/commit/bba0213842a4c161f2235e526d50901a336eecef))
+* **tests:** add tests for httpx client instantiation & proxies ([bc93712](https://github.com/openai/openai-python/commit/bc9371204f457aee9ed9b6ec1b61c2084f32faf1))
+
 ## 1.86.0 (2025-06-10)
 
 Full Changelog: [v1.85.0...v1.86.0](https://github.com/openai/openai-python/compare/v1.85.0...v1.86.0)

@@ -750,6 +750,7 @@ from openai.types.responses import (
     ResponseOutputRefusal,
     ResponseOutputText,
     ResponseOutputTextAnnotationAddedEvent,
+    ResponsePrompt,
     ResponseQueuedEvent,
     ResponseReasoningDeltaEvent,
     ResponseReasoningDoneEvent,

@@ -1,6 +1,6 @@
 [project]
 name = "openai"
-version = "1.86.0"
+version = "1.87.0"
 description = "The official Python library for the openai API"
 dynamic = ["readme"]
 license = "Apache-2.0"
@@ -68,6 +68,7 @@ dev-dependencies = [
     "types-pyaudio > 0",
     "trio >=0.22.2",
     "nest_asyncio==1.6.0",
+    "pytest-xdist>=3.6.1",
 ]
 
 [tool.rye.scripts]
@@ -139,7 +140,7 @@ replacement = '[\1](https://github.com/openai/openai-python/tree/main/\g<2>)'
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]
-addopts = "--tb=short"
+addopts = "--tb=short -n auto"
 xfail_strict = true
 asyncio_mode = "auto"
 asyncio_default_fixture_loop_scope = "session"

@@ -54,6 +54,8 @@ exceptiongroup==1.2.2
     # via anyio
     # via pytest
     # via trio
+execnet==2.1.1
+    # via pytest-xdist
 executing==2.1.0
     # via inline-snapshot
 filelock==3.12.4
@@ -129,7 +131,9 @@ pyjwt==2.8.0
 pyright==1.1.399
 pytest==8.3.3
     # via pytest-asyncio
+    # via pytest-xdist
 pytest-asyncio==0.24.0
+pytest-xdist==3.7.0
 python-dateutil==2.8.2
     # via pandas
     # via time-machine

@@ -1088,7 +1088,14 @@ def _process_response(
 
         origin = get_origin(cast_to) or cast_to
 
-        if inspect.isclass(origin) and issubclass(origin, BaseAPIResponse):
+        if (
+            inspect.isclass(origin)
+            and issubclass(origin, BaseAPIResponse)
+            # we only want to actually return the custom BaseAPIResponse class if we're
+            # returning the raw response, or if we're not streaming SSE, as if we're streaming
+            # SSE then `cast_to` doesn't actively reflect the type we need to parse into
+            and (not stream or bool(response.request.headers.get(RAW_RESPONSE_HEADER)))
+        ):
             if not issubclass(origin, APIResponse):
                 raise TypeError(f"API Response types must subclass {APIResponse}; Received {origin}")
 
@@ -1606,7 +1613,14 @@ async def _process_response(
 
         origin = get_origin(cast_to) or cast_to
 
-        if inspect.isclass(origin) and issubclass(origin, BaseAPIResponse):
+        if (
+            inspect.isclass(origin)
+            and issubclass(origin, BaseAPIResponse)
+            # we only want to actually return the custom BaseAPIResponse class if we're
+            # returning the raw response, or if we're not streaming SSE, as if we're streaming
+            # SSE then `cast_to` doesn't actively reflect the type we need to parse into
+            and (not stream or bool(response.request.headers.get(RAW_RESPONSE_HEADER)))
+        ):
             if not issubclass(origin, AsyncAPIResponse):
                 raise TypeError(f"API Response types must subclass {AsyncAPIResponse}; Received {origin}")
 

@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "openai"
-__version__ = "1.86.0"  # x-release-please-version
+__version__ = "1.87.0"  # x-release-please-version
@@ -81,7 +81,7 @@ def parse(
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         reasoning_effort: Optional[ReasoningEffort] | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
-        service_tier: Optional[Literal["auto", "default", "flex"]] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         store: Optional[bool] | NotGiven = NOT_GIVEN,
         stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN,
@@ -228,7 +228,7 @@ def stream(
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         reasoning_effort: Optional[ReasoningEffort] | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
-        service_tier: Optional[Literal["auto", "default", "flex"]] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         store: Optional[bool] | NotGiven = NOT_GIVEN,
         stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN,
@@ -360,7 +360,7 @@ async def parse(
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         reasoning_effort: Optional[ReasoningEffort] | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
-        service_tier: Optional[Literal["auto", "default", "flex"]] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         store: Optional[bool] | NotGiven = NOT_GIVEN,
         stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN,
@@ -507,7 +507,7 @@ def stream(
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         reasoning_effort: Optional[ReasoningEffort] | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
-        service_tier: Optional[Literal["auto", "default", "flex"]] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         store: Optional[bool] | NotGiven = NOT_GIVEN,
         stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN,

@@ -95,7 +95,7 @@ def create(
         reasoning_effort: Optional[ReasoningEffort] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
-        service_tier: Optional[Literal["auto", "default", "flex"]] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         store: Optional[bool] | NotGiven = NOT_GIVEN,
         stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
@@ -365,7 +365,7 @@ def create(
         reasoning_effort: Optional[ReasoningEffort] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
-        service_tier: Optional[Literal["auto", "default", "flex"]] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         store: Optional[bool] | NotGiven = NOT_GIVEN,
         stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN,
@@ -634,7 +634,7 @@ def create(
         reasoning_effort: Optional[ReasoningEffort] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
-        service_tier: Optional[Literal["auto", "default", "flex"]] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         store: Optional[bool] | NotGiven = NOT_GIVEN,
         stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN,
@@ -902,7 +902,7 @@ def create(
         reasoning_effort: Optional[ReasoningEffort] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
-        service_tier: Optional[Literal["auto", "default", "flex"]] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         store: Optional[bool] | NotGiven = NOT_GIVEN,
         stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
@@ -1198,7 +1198,7 @@ async def create(
         reasoning_effort: Optional[ReasoningEffort] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
-        service_tier: Optional[Literal["auto", "default", "flex"]] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         store: Optional[bool] | NotGiven = NOT_GIVEN,
         stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
@@ -1468,7 +1468,7 @@ async def create(
         reasoning_effort: Optional[ReasoningEffort] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
-        service_tier: Optional[Literal["auto", "default", "flex"]] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         store: Optional[bool] | NotGiven = NOT_GIVEN,
         stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN,
@@ -1737,7 +1737,7 @@ async def create(
         reasoning_effort: Optional[ReasoningEffort] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
-        service_tier: Optional[Literal["auto", "default", "flex"]] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         store: Optional[bool] | NotGiven = NOT_GIVEN,
         stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN,
@@ -2005,7 +2005,7 @@ async def create(
         reasoning_effort: Optional[ReasoningEffort] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
-        service_tier: Optional[Literal["auto", "default", "flex"]] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         store: Optional[bool] | NotGiven = NOT_GIVEN,
         stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,

@@ -84,7 +84,7 @@ def create(
         Response includes details of the enqueued job including job status and the name
         of the fine-tuned models once complete.
 
-        [Learn more about fine-tuning](https://platform.openai.com/docs/guides/fine-tuning)
+        [Learn more about fine-tuning](https://platform.openai.com/docs/guides/model-optimization)
 
         Args:
           model: The name of the model to fine-tune. You can select one of the
@@ -105,7 +105,8 @@ def create(
               [preference](https://platform.openai.com/docs/api-reference/fine-tuning/preference-input)
               format.
 
-              See the [fine-tuning guide](https://platform.openai.com/docs/guides/fine-tuning)
+              See the
+              [fine-tuning guide](https://platform.openai.com/docs/guides/model-optimization)
               for more details.
 
           hyperparameters: The hyperparameters used for the fine-tuning job. This value is now deprecated
@@ -142,7 +143,8 @@ def create(
               Your dataset must be formatted as a JSONL file. You must upload your file with
               the purpose `fine-tune`.
 
-              See the [fine-tuning guide](https://platform.openai.com/docs/guides/fine-tuning)
+              See the
+              [fine-tuning guide](https://platform.openai.com/docs/guides/model-optimization)
               for more details.
 
           extra_headers: Send extra headers
@@ -189,7 +191,7 @@ def retrieve(
         """
         Get info about a fine-tuning job.
 
-        [Learn more about fine-tuning](https://platform.openai.com/docs/guides/fine-tuning)
+        [Learn more about fine-tuning](https://platform.openai.com/docs/guides/model-optimization)
 
         Args:
           extra_headers: Send extra headers
@@ -462,7 +464,7 @@ async def create(
         Response includes details of the enqueued job including job status and the name
         of the fine-tuned models once complete.
 
-        [Learn more about fine-tuning](https://platform.openai.com/docs/guides/fine-tuning)
+        [Learn more about fine-tuning](https://platform.openai.com/docs/guides/model-optimization)
 
         Args:
           model: The name of the model to fine-tune. You can select one of the
@@ -483,7 +485,8 @@ async def create(
               [preference](https://platform.openai.com/docs/api-reference/fine-tuning/preference-input)
               format.
 
-              See the [fine-tuning guide](https://platform.openai.com/docs/guides/fine-tuning)
+              See the
+              [fine-tuning guide](https://platform.openai.com/docs/guides/model-optimization)
               for more details.
 
           hyperparameters: The hyperparameters used for the fine-tuning job. This value is now deprecated
@@ -520,7 +523,8 @@ async def create(
               Your dataset must be formatted as a JSONL file. You must upload your file with
               the purpose `fine-tune`.
 
-              See the [fine-tuning guide](https://platform.openai.com/docs/guides/fine-tuning)
+              See the
+              [fine-tuning guide](https://platform.openai.com/docs/guides/model-optimization)
               for more details.
 
           extra_headers: Send extra headers
@@ -567,7 +571,7 @@ async def retrieve(
         """
         Get info about a fine-tuning job.
 
-        [Learn more about fine-tuning](https://platform.openai.com/docs/guides/fine-tuning)
+        [Learn more about fine-tuning](https://platform.openai.com/docs/guides/model-optimization)
 
         Args:
           extra_headers: Send extra headers

@@ -123,6 +123,8 @@ def edit(
         mask: FileTypes | NotGiven = NOT_GIVEN,
         model: Union[str, ImageModel, None] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
+        output_compression: Optional[int] | NotGiven = NOT_GIVEN,
+        output_format: Optional[Literal["png", "jpeg", "webp"]] | NotGiven = NOT_GIVEN,
         quality: Optional[Literal["standard", "low", "medium", "high", "auto"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[Literal["url", "b64_json"]] | NotGiven = NOT_GIVEN,
         size: Optional[Literal["256x256", "512x512", "1024x1024", "1536x1024", "1024x1536", "auto"]]
@@ -171,6 +173,14 @@ def edit(
 
           n: The number of images to generate. Must be between 1 and 10.
 
+          output_compression: The compression level (0-100%) for the generated images. This parameter is only
+              supported for `gpt-image-1` with the `webp` or `jpeg` output formats, and
+              defaults to 100.
+
+          output_format: The format in which the generated images are returned. This parameter is only
+              supported for `gpt-image-1`. Must be one of `png`, `jpeg`, or `webp`. The
+              default value is `png`.
+
           quality: The quality of the image that will be generated. `high`, `medium` and `low` are
               only supported for `gpt-image-1`. `dall-e-2` only supports `standard` quality.
               Defaults to `auto`.
@@ -204,6 +214,8 @@ def edit(
                 "mask": mask,
                 "model": model,
                 "n": n,
+                "output_compression": output_compression,
+                "output_format": output_format,
                 "quality": quality,
                 "response_format": response_format,
                 "size": size,
@@ -447,6 +459,8 @@ async def edit(
         mask: FileTypes | NotGiven = NOT_GIVEN,
         model: Union[str, ImageModel, None] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
+        output_compression: Optional[int] | NotGiven = NOT_GIVEN,
+        output_format: Optional[Literal["png", "jpeg", "webp"]] | NotGiven = NOT_GIVEN,
         quality: Optional[Literal["standard", "low", "medium", "high", "auto"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[Literal["url", "b64_json"]] | NotGiven = NOT_GIVEN,
         size: Optional[Literal["256x256", "512x512", "1024x1024", "1536x1024", "1024x1536", "auto"]]
@@ -495,6 +509,14 @@ async def edit(
 
           n: The number of images to generate. Must be between 1 and 10.
 
+          output_compression: The compression level (0-100%) for the generated images. This parameter is only
+              supported for `gpt-image-1` with the `webp` or `jpeg` output formats, and
+              defaults to 100.
+
+          output_format: The format in which the generated images are returned. This parameter is only
+              supported for `gpt-image-1`. Must be one of `png`, `jpeg`, or `webp`. The
+              default value is `png`.
+
           quality: The quality of the image that will be generated. `high`, `medium` and `low` are
               only supported for `gpt-image-1`. `dall-e-2` only supports `standard` quality.
               Defaults to `auto`.
@@ -528,6 +550,8 @@ async def edit(
                 "mask": mask,
                 "model": model,
                 "n": n,
+                "output_compression": output_compression,
+                "output_format": output_format,
                 "quality": quality,
                 "response_format": response_format,
                 "size": size,