openai · stainless-app · Jan 22, 2025 · Jan 21, 2025 · Jan 22, 2025 · Jan 22, 2025
@@ -1,3 +1,3 @@
 {
-  ".": "1.59.9"
+  ".": "1.60.0"
 }
@@ -1,2 +1,2 @@
 configured_endpoints: 69
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-b5b0e2c794b012919701c3fd43286af10fa25d33ceb8a881bec2636028f446e0.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-3904ef6b29a89c98f93a9b7da19879695f3c440564be6384db7af1b734611ede.yml
@@ -1,5 +1,23 @@
 # Changelog
 
+## 1.60.0 (2025-01-22)
+
+Full Changelog: [v1.59.9...v1.60.0](https://github.com/openai/openai-python/compare/v1.59.9...v1.60.0)
+
+### Features
+
+* **api:** update enum values, comments, and examples ([#2045](https://github.com/openai/openai-python/issues/2045)) ([e8205fd](https://github.com/openai/openai-python/commit/e8205fd58f0d677f476c577a8d9afb90f5710506))
+
+
+### Chores
+
+* **internal:** minor style changes ([#2043](https://github.com/openai/openai-python/issues/2043)) ([89a9dd8](https://github.com/openai/openai-python/commit/89a9dd821eaf5300ad11b0270b61fdfa4fd6e9b6))
+
+
+### Documentation
+
+* **readme:** mention failed requests in request IDs ([5f7c30b](https://github.com/openai/openai-python/commit/5f7c30bc006ffb666c324011a68aae357cb33e35))
+
 ## 1.59.9 (2025-01-20)
 
 Full Changelog: [v1.59.8...v1.59.9](https://github.com/openai/openai-python/compare/v1.59.8...v1.59.9)

@@ -499,6 +499,21 @@ Note that unlike other properties that use an `_` prefix, the `_request_id` prop
 *is* public. Unless documented otherwise, *all* other `_` prefix properties,
 methods and modules are *private*.
 
+> [!IMPORTANT]  
+> If you need to access request IDs for failed requests you must catch the `APIStatusError` exception
+
+```python
+import openai
+
+try:
+    completion = await client.chat.completions.create(
+        messages=[{"role": "user", "content": "Say this is a test"}], model="gpt-4"
+    )
+except openai.APIStatusError as exc:
+    print(exc.request_id)  # req_123
+    raise exc
+```
+
 
 ### Retries
 

@@ -1,6 +1,6 @@
 [project]
 name = "openai"
-version = "1.59.9"
+version = "1.60.0"
 description = "The official Python library for the openai API"
 dynamic = ["readme"]
 license = "Apache-2.0"

@@ -205,6 +205,8 @@ def _parse(self, *, to: type[_T] | None = None) -> R | _T:
         if cast_to and is_annotated_type(cast_to):
             cast_to = extract_type_arg(cast_to, 0)
 
+        origin = get_origin(cast_to) or cast_to
+
         if self._stream:
             if to:
                 if not is_stream_class_type(to):
@@ -261,8 +263,6 @@ def _parse(self, *, to: type[_T] | None = None) -> R | _T:
         if cast_to == bool:
             return cast(R, response.text.lower() == "true")
 
-        origin = get_origin(cast_to) or cast_to
-
         if inspect.isclass(origin) and issubclass(origin, HttpxBinaryResponseContent):
             return cast(R, cast_to(response))  # type: ignore
 

@@ -136,6 +136,8 @@ def _parse(self, *, to: type[_T] | None = None) -> R | _T:
         if cast_to and is_annotated_type(cast_to):
             cast_to = extract_type_arg(cast_to, 0)
 
+        origin = get_origin(cast_to) or cast_to
+
         if self._is_sse_stream:
             if to:
                 if not is_stream_class_type(to):
@@ -195,8 +197,6 @@ def _parse(self, *, to: type[_T] | None = None) -> R | _T:
         if cast_to == bool:
             return cast(R, response.text.lower() == "true")
 
-        origin = get_origin(cast_to) or cast_to
-
         # handle the legacy binary response case
         if inspect.isclass(cast_to) and cast_to.__name__ == "HttpxBinaryResponseContent":
             return cast(R, cast_to(response))  # type: ignore

@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "openai"
-__version__ = "1.59.9"  # x-release-please-version
+__version__ = "1.60.0"  # x-release-please-version
@@ -53,7 +53,7 @@ def create(
         *,
         input: str,
         model: Union[str, SpeechModel],
-        voice: Literal["alloy", "echo", "fable", "onyx", "nova", "shimmer"],
+        voice: Literal["alloy", "ash", "coral", "echo", "fable", "onyx", "nova", "sage", "shimmer"],
         response_format: Literal["mp3", "opus", "aac", "flac", "wav", "pcm"] | NotGiven = NOT_GIVEN,
         speed: float | NotGiven = NOT_GIVEN,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
@@ -73,9 +73,9 @@ def create(
               One of the available [TTS models](https://platform.openai.com/docs/models#tts):
               `tts-1` or `tts-1-hd`
 
-          voice: The voice to use when generating the audio. Supported voices are `alloy`,
-              `echo`, `fable`, `onyx`, `nova`, and `shimmer`. Previews of the voices are
-              available in the
+          voice: The voice to use when generating the audio. Supported voices are `alloy`, `ash`,
+              `coral`, `echo`, `fable`, `onyx`, `nova`, `sage` and `shimmer`. Previews of the
+              voices are available in the
               [Text to speech guide](https://platform.openai.com/docs/guides/text-to-speech#voice-options).
 
           response_format: The format to audio in. Supported formats are `mp3`, `opus`, `aac`, `flac`,
@@ -137,7 +137,7 @@ async def create(
         *,
         input: str,
         model: Union[str, SpeechModel],
-        voice: Literal["alloy", "echo", "fable", "onyx", "nova", "shimmer"],
+        voice: Literal["alloy", "ash", "coral", "echo", "fable", "onyx", "nova", "sage", "shimmer"],
         response_format: Literal["mp3", "opus", "aac", "flac", "wav", "pcm"] | NotGiven = NOT_GIVEN,
         speed: float | NotGiven = NOT_GIVEN,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
@@ -157,9 +157,9 @@ async def create(
               One of the available [TTS models](https://platform.openai.com/docs/models#tts):
               `tts-1` or `tts-1-hd`
 
-          voice: The voice to use when generating the audio. Supported voices are `alloy`,
-              `echo`, `fable`, `onyx`, `nova`, and `shimmer`. Previews of the voices are
-              available in the
+          voice: The voice to use when generating the audio. Supported voices are `alloy`, `ash`,
+              `coral`, `echo`, `fable`, `onyx`, `nova`, `sage` and `shimmer`. Previews of the
+              voices are available in the
               [Text to speech guide](https://platform.openai.com/docs/guides/text-to-speech#voice-options).
 
           response_format: The format to audio in. Supported formats are `mp3`, `opus`, `aac`, `flac`,

@@ -46,18 +46,19 @@ def with_streaming_response(self) -> SessionsWithStreamingResponse:
     def create(
         self,
         *,
+        input_audio_format: Literal["pcm16", "g711_ulaw", "g711_alaw"] | NotGiven = NOT_GIVEN,
+        input_audio_transcription: session_create_params.InputAudioTranscription | NotGiven = NOT_GIVEN,
+        instructions: str | NotGiven = NOT_GIVEN,
+        max_response_output_tokens: Union[int, Literal["inf"]] | NotGiven = NOT_GIVEN,
+        modalities: List[Literal["text", "audio"]] | NotGiven = NOT_GIVEN,
         model: Literal[
             "gpt-4o-realtime-preview",
             "gpt-4o-realtime-preview-2024-10-01",
             "gpt-4o-realtime-preview-2024-12-17",
             "gpt-4o-mini-realtime-preview",
             "gpt-4o-mini-realtime-preview-2024-12-17",
-        ],
-        input_audio_format: Literal["pcm16", "g711_ulaw", "g711_alaw"] | NotGiven = NOT_GIVEN,
-        input_audio_transcription: session_create_params.InputAudioTranscription | NotGiven = NOT_GIVEN,
-        instructions: str | NotGiven = NOT_GIVEN,
-        max_response_output_tokens: Union[int, Literal["inf"]] | NotGiven = NOT_GIVEN,
-        modalities: List[Literal["text", "audio"]] | NotGiven = NOT_GIVEN,
+        ]
+        | NotGiven = NOT_GIVEN,
         output_audio_format: Literal["pcm16", "g711_ulaw", "g711_alaw"] | NotGiven = NOT_GIVEN,
         temperature: float | NotGiven = NOT_GIVEN,
         tool_choice: str | NotGiven = NOT_GIVEN,
@@ -81,9 +82,9 @@ def create(
         the Realtime API.
 
         Args:
-          model: The Realtime model used for this session.
-
-          input_audio_format: The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.
+          input_audio_format: The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. For
+              `pcm16`, input audio must be 16-bit PCM at a 24kHz sample rate, single channel
+              (mono), and little-endian byte order.
 
           input_audio_transcription: Configuration for input audio transcription, defaults to off and can be set to
               `null` to turn off once on. Input audio transcription is not native to the
@@ -110,7 +111,10 @@ def create(
           modalities: The set of modalities the model can respond with. To disable audio, set this to
               ["text"].
 
+          model: The Realtime model used for this session.
+
           output_audio_format: The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.
+              For `pcm16`, output audio is sampled at a rate of 24kHz.
 
           temperature: Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.
 
@@ -140,12 +144,12 @@ def create(
             "/realtime/sessions",
             body=maybe_transform(
                 {
-                    "model": model,
                     "input_audio_format": input_audio_format,
                     "input_audio_transcription": input_audio_transcription,
                     "instructions": instructions,
                     "max_response_output_tokens": max_response_output_tokens,
                     "modalities": modalities,
+                    "model": model,
                     "output_audio_format": output_audio_format,
                     "temperature": temperature,
                     "tool_choice": tool_choice,
@@ -185,18 +189,19 @@ def with_streaming_response(self) -> AsyncSessionsWithStreamingResponse:
     async def create(
         self,
         *,
+        input_audio_format: Literal["pcm16", "g711_ulaw", "g711_alaw"] | NotGiven = NOT_GIVEN,
+        input_audio_transcription: session_create_params.InputAudioTranscription | NotGiven = NOT_GIVEN,
+        instructions: str | NotGiven = NOT_GIVEN,
+        max_response_output_tokens: Union[int, Literal["inf"]] | NotGiven = NOT_GIVEN,
+        modalities: List[Literal["text", "audio"]] | NotGiven = NOT_GIVEN,
         model: Literal[
             "gpt-4o-realtime-preview",
             "gpt-4o-realtime-preview-2024-10-01",
             "gpt-4o-realtime-preview-2024-12-17",
             "gpt-4o-mini-realtime-preview",
             "gpt-4o-mini-realtime-preview-2024-12-17",
-        ],
-        input_audio_format: Literal["pcm16", "g711_ulaw", "g711_alaw"] | NotGiven = NOT_GIVEN,
-        input_audio_transcription: session_create_params.InputAudioTranscription | NotGiven = NOT_GIVEN,
-        instructions: str | NotGiven = NOT_GIVEN,
-        max_response_output_tokens: Union[int, Literal["inf"]] | NotGiven = NOT_GIVEN,
-        modalities: List[Literal["text", "audio"]] | NotGiven = NOT_GIVEN,
+        ]
+        | NotGiven = NOT_GIVEN,
         output_audio_format: Literal["pcm16", "g711_ulaw", "g711_alaw"] | NotGiven = NOT_GIVEN,
         temperature: float | NotGiven = NOT_GIVEN,
         tool_choice: str | NotGiven = NOT_GIVEN,
@@ -220,9 +225,9 @@ async def create(
         the Realtime API.
 
         Args:
-          model: The Realtime model used for this session.
-
-          input_audio_format: The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.
+          input_audio_format: The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. For
+              `pcm16`, input audio must be 16-bit PCM at a 24kHz sample rate, single channel
+              (mono), and little-endian byte order.
 
           input_audio_transcription: Configuration for input audio transcription, defaults to off and can be set to
               `null` to turn off once on. Input audio transcription is not native to the
@@ -249,7 +254,10 @@ async def create(
           modalities: The set of modalities the model can respond with. To disable audio, set this to
               ["text"].
 
+          model: The Realtime model used for this session.
+
           output_audio_format: The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.
+              For `pcm16`, output audio is sampled at a rate of 24kHz.
 
           temperature: Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.
 
@@ -279,12 +287,12 @@ async def create(
             "/realtime/sessions",
             body=await async_maybe_transform(
                 {
-                    "model": model,
                     "input_audio_format": input_audio_format,
                     "input_audio_transcription": input_audio_transcription,
                     "instructions": instructions,
                     "max_response_output_tokens": max_response_output_tokens,
                     "modalities": modalities,
+                    "model": model,
                     "output_audio_format": output_audio_format,
                     "temperature": temperature,
                     "tool_choice": tool_choice,

@@ -251,9 +251,6 @@ def create(
                 tier with a lower uptime SLA and no latency guarentee.
               - When not set, the default behavior is 'auto'.
 
-              When this parameter is set, the response body will include the `service_tier`
-              utilized.
-
           stop: Up to 4 sequences where the API will stop generating further tokens.
 
           store: Whether or not to store the output of this chat completion request for use in
@@ -509,9 +506,6 @@ def create(
                 tier with a lower uptime SLA and no latency guarentee.
               - When not set, the default behavior is 'auto'.
 
-              When this parameter is set, the response body will include the `service_tier`
-              utilized.
-
           stop: Up to 4 sequences where the API will stop generating further tokens.
 
           store: Whether or not to store the output of this chat completion request for use in
@@ -760,9 +754,6 @@ def create(
                 tier with a lower uptime SLA and no latency guarentee.
               - When not set, the default behavior is 'auto'.
 
-              When this parameter is set, the response body will include the `service_tier`
-              utilized.
-
           stop: Up to 4 sequences where the API will stop generating further tokens.
 
           store: Whether or not to store the output of this chat completion request for use in
@@ -1112,9 +1103,6 @@ async def create(
                 tier with a lower uptime SLA and no latency guarentee.
               - When not set, the default behavior is 'auto'.
 
-              When this parameter is set, the response body will include the `service_tier`
-              utilized.
-
           stop: Up to 4 sequences where the API will stop generating further tokens.
 
           store: Whether or not to store the output of this chat completion request for use in
@@ -1370,9 +1358,6 @@ async def create(
                 tier with a lower uptime SLA and no latency guarentee.
               - When not set, the default behavior is 'auto'.
 
-              When this parameter is set, the response body will include the `service_tier`
-              utilized.
-
           stop: Up to 4 sequences where the API will stop generating further tokens.
 
           store: Whether or not to store the output of this chat completion request for use in
@@ -1621,9 +1606,6 @@ async def create(
                 tier with a lower uptime SLA and no latency guarentee.
               - When not set, the default behavior is 'auto'.
 
-              When this parameter is set, the response body will include the `service_tier`
-              utilized.
-
           stop: Up to 4 sequences where the API will stop generating further tokens.
 
           store: Whether or not to store the output of this chat completion request for use in

@@ -68,7 +68,8 @@ def create(
               `text-embedding-ada-002`), cannot be an empty string, and any array must be 2048
               dimensions or less.
               [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
-              for counting tokens.
+              for counting tokens. Some models may also impose a limit on total number of
+              tokens summed across inputs.
 
           model: ID of the model to use. You can use the
               [List models](https://platform.openai.com/docs/api-reference/models/list) API to
@@ -180,7 +181,8 @@ async def create(
               `text-embedding-ada-002`), cannot be an empty string, and any array must be 2048
               dimensions or less.
               [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
-              for counting tokens.
+              for counting tokens. Some models may also impose a limit on total number of
+              tokens summed across inputs.
 
           model: ID of the model to use. You can use the
               [List models](https://platform.openai.com/docs/api-reference/models/list) API to

@@ -20,11 +20,11 @@ class SpeechCreateParams(TypedDict, total=False):
     `tts-1` or `tts-1-hd`
     """
 
-    voice: Required[Literal["alloy", "echo", "fable", "onyx", "nova", "shimmer"]]
+    voice: Required[Literal["alloy", "ash", "coral", "echo", "fable", "onyx", "nova", "sage", "shimmer"]]
     """The voice to use when generating the audio.
 
-    Supported voices are `alloy`, `echo`, `fable`, `onyx`, `nova`, and `shimmer`.
-    Previews of the voices are available in the
+    Supported voices are `alloy`, `ash`, `coral`, `echo`, `fable`, `onyx`, `nova`,
+    `sage` and `shimmer`. Previews of the voices are available in the
     [Text to speech guide](https://platform.openai.com/docs/guides/text-to-speech#voice-options).
     """
 

@@ -20,9 +20,10 @@ class ConversationItemCreateEvent(BaseModel):
     """Optional client-generated ID used to identify this event."""
 
     previous_item_id: Optional[str] = None
-    """The ID of the preceding item after which the new item will be inserted.
-
-    If not set, the new item will be appended to the end of the conversation. If
-    set, it allows an item to be inserted mid-conversation. If the ID cannot be
-    found, an error will be returned and the item will not be added.
+    """
+    The ID of the preceding item after which the new item will be inserted. If not
+    set, the new item will be appended to the end of the conversation. If set to
+    `root`, the new item will be added to the beginning of the conversation. If set
+    to an existing ID, it allows an item to be inserted mid-conversation. If the ID
+    cannot be found, an error will be returned and the item will not be added.
     """