release: 2.35.0

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "2.34.0"
+  ".": "2.35.0"
 }

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 233
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai/openai-21ecab7aeb61612b9da5e52ea4c0cb75a33d443d975022934b9305e97d1a7d62.yml
-openapi_spec_hash: cfc868a0bb3567183510c9b5629c510f
-config_hash: dd484e2cc01206d26516338d0f4596b0
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai/openai-5002c7ce1688cf372f6c268507494c5e6396f38db8d85d79029d949b7bb06fe3.yml
+openapi_spec_hash: 92713b0825f6b8760836778e6d27e837
+config_hash: c6cf65d9b19a16ce4313602a2204d48f

CHANGELOG.md

@@ -1,5 +1,14 @@
 # Changelog
 
+## 2.35.0 (2026-05-05)
+
+Full Changelog: [v2.34.0...v2.35.0](https://github.com/openai/openai-python/compare/v2.34.0...v2.35.0)
+
+### Features
+
+* **api:** launch realtime translate + update image 2 ([0ba55d7](https://github.com/openai/openai-python/commit/0ba55d7569565045426e1587906a70d5682a4bba))
+* **api:** manual updates ([72bf67a](https://github.com/openai/openai-python/commit/72bf67acbc9f030c20db3d5a1a74ea6d67d55f51))
+
 ## 2.34.0 (2026-05-04)
 
 Full Changelog: [v2.33.0...v2.34.0](https://github.com/openai/openai-python/compare/v2.33.0...v2.34.0)

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "openai"
-version = "2.34.0"
+version = "2.35.0"
 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__ = "2.34.0"  # x-release-please-version
+__version__ = "2.35.0"  # x-release-please-version

src/openai/types/image_edit_params.py

@@ -15,10 +15,10 @@ class ImageEditParamsBase(TypedDict, total=False):
     image: Required[Union[FileTypes, SequenceNotStr[FileTypes]]]
     """The image(s) to edit. Must be a supported image file or an array of images.
 
-    For the GPT image models (`gpt-image-1`, `gpt-image-1-mini`, and
-    `gpt-image-1.5`), each image should be a `png`, `webp`, or `jpg` file less than
-    50MB. You can provide up to 16 images. `chatgpt-image-latest` follows the same
-    input constraints as GPT image models.
+    For the GPT image models (`gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`,
+    `gpt-image-2`, `gpt-image-2-2026-04-21`, and `chatgpt-image-latest`), each image
+    should be a `png`, `webp`, or `jpg` file less than 50MB. You can provide up to
+    16 images.
 
     For `dall-e-2`, you can only provide one image, and it should be a square `png`
     file less than 4MB.
@@ -34,9 +34,14 @@ class ImageEditParamsBase(TypedDict, total=False):
     background: Optional[Literal["transparent", "opaque", "auto"]]
     """
     Allows to set transparency for the background of the generated image(s). This
-    parameter is only supported for the GPT image models. Must be one of
-    `transparent`, `opaque` or `auto` (default value). When `auto` is used, the
-    model will automatically determine the best background for the image.
+    parameter is only supported for GPT image models that support transparent
+    backgrounds. Must be one of `transparent`, `opaque`, or `auto` (default value).
+    When `auto` is used, the model will automatically determine the best background
+    for the image.
+
+    `gpt-image-2` and `gpt-image-2-2026-04-21` do not support transparent
+    backgrounds. Requests with `background` set to `transparent` will return an
+    error for these models; use `opaque` or `auto` instead.
 
     If `transparent`, the output format needs to support transparency, so it should
     be set to either `png` (default value) or `webp`.
@@ -59,7 +64,12 @@ class ImageEditParamsBase(TypedDict, total=False):
     """
 
     model: Union[str, ImageModel, None]
-    """The model to use for image generation. Defaults to `gpt-image-1.5`."""
+    """The model to use for image generation.
+
+    One of `dall-e-2` or a GPT image model (`gpt-image-1`, `gpt-image-1-mini`,
+    `gpt-image-1.5`, `gpt-image-2`, `gpt-image-2-2026-04-21`, or
+    `chatgpt-image-latest`). Defaults to `gpt-image-1.5`.
+    """
 
     n: Optional[int]
     """The number of images to generate. Must be between 1 and 10."""
@@ -104,12 +114,19 @@ class ImageEditParamsBase(TypedDict, total=False):
     base64-encoded images.
     """
 
-    size: Optional[Literal["256x256", "512x512", "1024x1024", "1536x1024", "1024x1536", "auto"]]
+    size: Optional[str]
     """The size of the generated images.
 
-    Must be one of `1024x1024`, `1536x1024` (landscape), `1024x1536` (portrait), or
-    `auto` (default value) for the GPT image models, and one of `256x256`,
-    `512x512`, or `1024x1024` for `dall-e-2`.
+    For `gpt-image-2` and `gpt-image-2-2026-04-21`, arbitrary resolutions are
+    supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height
+    must both be divisible by 16 and the requested aspect ratio must be between 1:3
+    and 3:1. Resolutions above `2560x1440` are experimental, and the maximum
+    supported resolution is `3840x2160`. The requested size must also satisfy the
+    model's current pixel and edge limits. The standard sizes `1024x1024`,
+    `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is
+    supported for models that allow automatic sizing. For `dall-e-2`, use one of
+    `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`,
+    `1792x1024`, or `1024x1792`.
     """
 
     user: str

src/openai/types/image_generate_params.py

@@ -21,9 +21,14 @@ class ImageGenerateParamsBase(TypedDict, total=False):
     background: Optional[Literal["transparent", "opaque", "auto"]]
     """
     Allows to set transparency for the background of the generated image(s). This
-    parameter is only supported for the GPT image models. Must be one of
-    `transparent`, `opaque` or `auto` (default value). When `auto` is used, the
-    model will automatically determine the best background for the image.
+    parameter is only supported for GPT image models that support transparent
+    backgrounds. Must be one of `transparent`, `opaque`, or `auto` (default value).
+    When `auto` is used, the model will automatically determine the best background
+    for the image.
+
+    `gpt-image-2` and `gpt-image-2-2026-04-21` do not support transparent
+    backgrounds. Requests with `background` set to `transparent` will return an
+    error for these models; use `opaque` or `auto` instead.
 
     If `transparent`, the output format needs to support transparency, so it should
     be set to either `png` (default value) or `webp`.
@@ -33,8 +38,9 @@ class ImageGenerateParamsBase(TypedDict, total=False):
     """The model to use for image generation.
 
     One of `dall-e-2`, `dall-e-3`, or a GPT image model (`gpt-image-1`,
-    `gpt-image-1-mini`, `gpt-image-1.5`). Defaults to `dall-e-2` unless a parameter
-    specific to the GPT image models is used.
+    `gpt-image-1-mini`, `gpt-image-1.5`, `gpt-image-2`, or
+    `gpt-image-2-2026-04-21`). Defaults to `dall-e-2` unless a parameter specific to
+    the GPT image models is used.
     """
 
     moderation: Optional[Literal["low", "auto"]]
@@ -94,15 +100,19 @@ class ImageGenerateParamsBase(TypedDict, total=False):
     models, which always return base64-encoded images.
     """
 
-    size: Optional[
-        Literal["auto", "1024x1024", "1536x1024", "1024x1536", "256x256", "512x512", "1792x1024", "1024x1792"]
-    ]
+    size: Optional[str]
     """The size of the generated images.
 
-    Must be one of `1024x1024`, `1536x1024` (landscape), `1024x1536` (portrait), or
-    `auto` (default value) for the GPT image models, one of `256x256`, `512x512`, or
-    `1024x1024` for `dall-e-2`, and one of `1024x1024`, `1792x1024`, or `1024x1792`
-    for `dall-e-3`.
+    For `gpt-image-2` and `gpt-image-2-2026-04-21`, arbitrary resolutions are
+    supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height
+    must both be divisible by 16 and the requested aspect ratio must be between 1:3
+    and 3:1. Resolutions above `2560x1440` are experimental, and the maximum
+    supported resolution is `3840x2160`. The requested size must also satisfy the
+    model's current pixel and edge limits. The standard sizes `1024x1024`,
+    `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is
+    supported for models that allow automatic sizing. For `dall-e-2`, use one of
+    `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`,
+    `1792x1024`, or `1024x1792`.
     """
 
     style: Optional[Literal["vivid", "natural"]]

src/openai/types/image_model.py

@@ -4,4 +4,13 @@
 
 __all__ = ["ImageModel"]
 
-ImageModel: TypeAlias = Literal["gpt-image-1.5", "dall-e-2", "dall-e-3", "gpt-image-1", "gpt-image-1-mini"]
+ImageModel: TypeAlias = Literal[
+    "gpt-image-1",
+    "gpt-image-1-mini",
+    "gpt-image-2",
+    "gpt-image-2-2026-04-21",
+    "gpt-image-1.5",
+    "chatgpt-image-latest",
+    "dall-e-2",
+    "dall-e-3",
+]

src/openai/types/responses/tool.py

@@ -248,9 +248,19 @@ class ImageGeneration(BaseModel):
     """Whether to generate a new image or edit an existing image. Default: `auto`."""
 
     background: Optional[Literal["transparent", "opaque", "auto"]] = None
-    """Background type for the generated image.
-
-    One of `transparent`, `opaque`, or `auto`. Default: `auto`.
+    """
+    Allows to set transparency for the background of the generated image(s). This
+    parameter is only supported for GPT image models that support transparent
+    backgrounds. Must be one of `transparent`, `opaque`, or `auto` (default value).
+    When `auto` is used, the model will automatically determine the best background
+    for the image.
+
+    `gpt-image-2` and `gpt-image-2-2026-04-21` do not support transparent
+    backgrounds. Requests with `background` set to `transparent` will return an
+    error for these models; use `opaque` or `auto` instead.
+
+    If `transparent`, the output format needs to support transparency, so it should
+    be set to either `png` (default value) or `webp`.
     """
 
     input_fidelity: Optional[Literal["high", "low"]] = None
@@ -267,7 +277,18 @@ class ImageGeneration(BaseModel):
     Contains `image_url` (string, optional) and `file_id` (string, optional).
     """
 
-    model: Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-1.5"], None] = None
+    model: Union[
+        str,
+        Literal[
+            "gpt-image-1",
+            "gpt-image-1-mini",
+            "gpt-image-2",
+            "gpt-image-2-2026-04-21",
+            "gpt-image-1.5",
+            "chatgpt-image-latest",
+        ],
+        None,
+    ] = None
     """The image generation model to use. Default: `gpt-image-1`."""
 
     moderation: Optional[Literal["auto", "low"]] = None
@@ -294,10 +315,19 @@ class ImageGeneration(BaseModel):
     One of `low`, `medium`, `high`, or `auto`. Default: `auto`.
     """
 
-    size: Optional[Literal["1024x1024", "1024x1536", "1536x1024", "auto"]] = None
-    """The size of the generated image.
-
-    One of `1024x1024`, `1024x1536`, `1536x1024`, or `auto`. Default: `auto`.
+    size: Optional[str] = None
+    """The size of the generated images.
+
+    For `gpt-image-2` and `gpt-image-2-2026-04-21`, arbitrary resolutions are
+    supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height
+    must both be divisible by 16 and the requested aspect ratio must be between 1:3
+    and 3:1. Resolutions above `2560x1440` are experimental, and the maximum
+    supported resolution is `3840x2160`. The requested size must also satisfy the
+    model's current pixel and edge limits. The standard sizes `1024x1024`,
+    `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is
+    supported for models that allow automatic sizing. For `dall-e-2`, use one of
+    `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`,
+    `1792x1024`, or `1024x1792`.
     """
 
 

src/openai/types/responses/tool_param.py

@@ -248,9 +248,19 @@ class ImageGeneration(TypedDict, total=False):
     """Whether to generate a new image or edit an existing image. Default: `auto`."""
 
     background: Literal["transparent", "opaque", "auto"]
-    """Background type for the generated image.
-
-    One of `transparent`, `opaque`, or `auto`. Default: `auto`.
+    """
+    Allows to set transparency for the background of the generated image(s). This
+    parameter is only supported for GPT image models that support transparent
+    backgrounds. Must be one of `transparent`, `opaque`, or `auto` (default value).
+    When `auto` is used, the model will automatically determine the best background
+    for the image.
+
+    `gpt-image-2` and `gpt-image-2-2026-04-21` do not support transparent
+    backgrounds. Requests with `background` set to `transparent` will return an
+    error for these models; use `opaque` or `auto` instead.
+
+    If `transparent`, the output format needs to support transparency, so it should
+    be set to either `png` (default value) or `webp`.
     """
 
     input_fidelity: Optional[Literal["high", "low"]]
@@ -267,7 +277,17 @@ class ImageGeneration(TypedDict, total=False):
     Contains `image_url` (string, optional) and `file_id` (string, optional).
     """
 
-    model: Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-1.5"]]
+    model: Union[
+        str,
+        Literal[
+            "gpt-image-1",
+            "gpt-image-1-mini",
+            "gpt-image-2",
+            "gpt-image-2-2026-04-21",
+            "gpt-image-1.5",
+            "chatgpt-image-latest",
+        ],
+    ]
     """The image generation model to use. Default: `gpt-image-1`."""
 
     moderation: Literal["auto", "low"]
@@ -294,10 +314,19 @@ class ImageGeneration(TypedDict, total=False):
     One of `low`, `medium`, `high`, or `auto`. Default: `auto`.
     """
 
-    size: Literal["1024x1024", "1024x1536", "1536x1024", "auto"]
-    """The size of the generated image.
-
-    One of `1024x1024`, `1024x1536`, `1536x1024`, or `auto`. Default: `auto`.
+    size: str
+    """The size of the generated images.
+
+    For `gpt-image-2` and `gpt-image-2-2026-04-21`, arbitrary resolutions are
+    supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height
+    must both be divisible by 16 and the requested aspect ratio must be between 1:3
+    and 3:1. Resolutions above `2560x1440` are experimental, and the maximum
+    supported resolution is `3840x2160`. The requested size must also satisfy the
+    model's current pixel and edge limits. The standard sizes `1024x1024`,
+    `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is
+    supported for models that allow automatic sizing. For `dall-e-2`, use one of
+    `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`,
+    `1792x1024`, or `1024x1792`.
     """