feat(api): add o3 and o4-mini model IDs

Author: stainless-app[bot]

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 97
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-a555f81249cb084f463dcefa4aba069f9341fdaf3dd6ac27d7f237fc90e8f488.yml
-openapi_spec_hash: 8e590296cd1a54b9508510b0c7a2c45a
-config_hash: 5ea32de61ff42fcf5e66cff8d9e247ea
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-5633633cc38734869cf7d993f7b549bb8e4d10e0ec45381ec2cd91507cd8eb8f.yml
+openapi_spec_hash: c855121b2b2324b99499c9244c21d24d
+config_hash: d20837393b73efdb19cd08e04c1cc9a1

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

@@ -159,7 +159,9 @@ def create(
               Determinism is not guaranteed, and you should refer to the `system_fingerprint`
               response parameter to monitor changes in the backend.
 
-          stop: Up to 4 sequences where the API will stop generating further tokens. The
+          stop: Not supported with latest reasoning models `o3` and `o4-mini`.
+
+              Up to 4 sequences where the API will stop generating further tokens. The
               returned text will not contain the stop sequence.
 
           stream: Whether to stream back partial progress. If set, tokens will be sent as
@@ -319,7 +321,9 @@ def create(
               Determinism is not guaranteed, and you should refer to the `system_fingerprint`
               response parameter to monitor changes in the backend.
 
-          stop: Up to 4 sequences where the API will stop generating further tokens. The
+          stop: Not supported with latest reasoning models `o3` and `o4-mini`.
+
+              Up to 4 sequences where the API will stop generating further tokens. The
               returned text will not contain the stop sequence.
 
           stream_options: Options for streaming response. Only set this when you set `stream: true`.
@@ -472,7 +476,9 @@ def create(
               Determinism is not guaranteed, and you should refer to the `system_fingerprint`
               response parameter to monitor changes in the backend.
 
-          stop: Up to 4 sequences where the API will stop generating further tokens. The
+          stop: Not supported with latest reasoning models `o3` and `o4-mini`.
+
+              Up to 4 sequences where the API will stop generating further tokens. The
               returned text will not contain the stop sequence.
 
           stream_options: Options for streaming response. Only set this when you set `stream: true`.
@@ -703,7 +709,9 @@ async def create(
               Determinism is not guaranteed, and you should refer to the `system_fingerprint`
               response parameter to monitor changes in the backend.
 
-          stop: Up to 4 sequences where the API will stop generating further tokens. The
+          stop: Not supported with latest reasoning models `o3` and `o4-mini`.
+
+              Up to 4 sequences where the API will stop generating further tokens. The
               returned text will not contain the stop sequence.
 
           stream: Whether to stream back partial progress. If set, tokens will be sent as
@@ -863,7 +871,9 @@ async def create(
               Determinism is not guaranteed, and you should refer to the `system_fingerprint`
               response parameter to monitor changes in the backend.
 
-          stop: Up to 4 sequences where the API will stop generating further tokens. The
+          stop: Not supported with latest reasoning models `o3` and `o4-mini`.
+
+              Up to 4 sequences where the API will stop generating further tokens. The
               returned text will not contain the stop sequence.
 
           stream_options: Options for streaming response. Only set this when you set `stream: true`.
@@ -1016,7 +1026,9 @@ async def create(
               Determinism is not guaranteed, and you should refer to the `system_fingerprint`
               response parameter to monitor changes in the backend.
 
-          stop: Up to 4 sequences where the API will stop generating further tokens. The
+          stop: Not supported with latest reasoning models `o3` and `o4-mini`.
+
+              Up to 4 sequences where the API will stop generating further tokens. The
               returned text will not contain the stop sequence.
 
           stream_options: Options for streaming response. Only set this when you set `stream: true`.

src/openai/resources/completions.py

@@ -59,8 +59,26 @@ class ChatCompletion(BaseModel):
     object: Literal["chat.completion"]
     """The object type, which is always `chat.completion`."""
 
-    service_tier: Optional[Literal["scale", "default"]] = None
-    """The service tier used for processing the request."""
+    service_tier: Optional[Literal["auto", "default", "flex"]] = None
+    """Specifies the latency tier to use for processing the request.
+
+    This parameter is relevant for customers subscribed to the scale tier service:
+
+    - If set to 'auto', and the Project is Scale tier enabled, the system will
+      utilize scale tier credits until they are exhausted.
+    - If set to 'auto', and the Project is not Scale tier enabled, the request will
+      be processed using the default service tier with a lower uptime SLA and no
+      latency guarentee.
+    - If set to 'default', the request will be processed using the default service
+      tier with a lower uptime SLA and no latency guarentee.
+    - If set to 'flex', the request will be processed with the Flex Processing
+      service tier.
+      [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+    - When not set, the default behavior is 'auto'.
+
+    When this parameter is set, the response body will include the `service_tier`
+    utilized.
+    """
 
     system_fingerprint: Optional[str] = None
     """This fingerprint represents the backend configuration that the model runs with.

src/openai/resources/responses/responses.py

@@ -9,7 +9,7 @@
 
 
 class ChatCompletionAudioParam(TypedDict, total=False):
-    format: Required[Literal["wav", "mp3", "flac", "opus", "pcm16"]]
+    format: Required[Literal["wav", "aac", "mp3", "flac", "opus", "pcm16"]]
     """Specifies the output audio format.
 
     Must be one of `wav`, `mp3`, `flac`, `opus`, or `pcm16`.
@@ -22,6 +22,6 @@ class ChatCompletionAudioParam(TypedDict, total=False):
     ]
     """The voice the model uses to respond.
 
-    Supported voices are `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, and
-    `shimmer`.
+    Supported voices are `alloy`, `ash`, `ballad`, `coral`, `echo`, `fable`, `nova`,
+    `onyx`, `sage`, and `shimmer`.
     """

src/openai/types/chat/chat_completion.py

@@ -128,8 +128,26 @@ class ChatCompletionChunk(BaseModel):
     object: Literal["chat.completion.chunk"]
     """The object type, which is always `chat.completion.chunk`."""
 
-    service_tier: Optional[Literal["scale", "default"]] = None
-    """The service tier used for processing the request."""
+    service_tier: Optional[Literal["auto", "default", "flex"]] = None
+    """Specifies the latency tier to use for processing the request.
+
+    This parameter is relevant for customers subscribed to the scale tier service:
+
+    - If set to 'auto', and the Project is Scale tier enabled, the system will
+      utilize scale tier credits until they are exhausted.
+    - If set to 'auto', and the Project is not Scale tier enabled, the request will
+      be processed using the default service tier with a lower uptime SLA and no
+      latency guarentee.
+    - If set to 'default', the request will be processed using the default service
+      tier with a lower uptime SLA and no latency guarentee.
+    - If set to 'flex', the request will be processed with the Flex Processing
+      service tier.
+      [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+    - When not set, the default behavior is 'auto'.
+
+    When this parameter is set, the response body will include the `service_tier`
+    utilized.
+    """
 
     system_fingerprint: Optional[str] = None
     """

src/openai/types/chat/chat_completion_audio_param.py

@@ -45,7 +45,7 @@ class CompletionCreateParamsBase(TypedDict, total=False):
     """
 
     model: Required[Union[str, ChatModel]]
-    """Model ID used to generate the response, like `gpt-4o` or `o1`.
+    """Model ID used to generate the response, like `gpt-4o` or `o3`.
 
     OpenAI offers a wide range of models with different capabilities, performance
     characteristics, and price points. Refer to the
@@ -123,7 +123,7 @@ class CompletionCreateParamsBase(TypedDict, total=False):
 
     This value is now deprecated in favor of `max_completion_tokens`, and is not
     compatible with
-    [o1 series models](https://platform.openai.com/docs/guides/reasoning).
+    [o-series models](https://platform.openai.com/docs/guides/reasoning).
     """
 
     metadata: Optional[Metadata]
@@ -208,7 +208,7 @@ class CompletionCreateParamsBase(TypedDict, total=False):
     in the backend.
     """
 
-    service_tier: Optional[Literal["auto", "default"]]
+    service_tier: Optional[Literal["auto", "default", "flex"]]
     """Specifies the latency tier to use for processing the request.
 
     This parameter is relevant for customers subscribed to the scale tier service:
@@ -220,16 +220,20 @@ class CompletionCreateParamsBase(TypedDict, total=False):
       latency guarentee.
     - If set to 'default', the request will be processed using the default service
       tier with a lower uptime SLA and no latency guarentee.
+    - If set to 'flex', the request will be processed with the Flex Processing
+      service tier.
+      [Learn more](https://platform.openai.com/docs/guides/flex-processing).
     - When not set, the default behavior is 'auto'.
 
     When this parameter is set, the response body will include the `service_tier`
     utilized.
     """
 
     stop: Union[Optional[str], List[str], None]
-    """Up to 4 sequences where the API will stop generating further tokens.
+    """Not supported with latest reasoning models `o3` and `o4-mini`.
 
-    The returned text will not contain the stop sequence.
+    Up to 4 sequences where the API will stop generating further tokens. The
+    returned text will not contain the stop sequence.
     """
 
     store: Optional[bool]

src/openai/types/chat/chat_completion_chunk.py

@@ -120,9 +120,10 @@ class CompletionCreateParamsBase(TypedDict, total=False):
     """
 
     stop: Union[Optional[str], List[str], None]
-    """Up to 4 sequences where the API will stop generating further tokens.
+    """Not supported with latest reasoning models `o3` and `o4-mini`.
 
-    The returned text will not contain the stop sequence.
+    Up to 4 sequences where the API will stop generating further tokens. The
+    returned text will not contain the stop sequence.
     """
 
     stream_options: Optional[ChatCompletionStreamOptionsParam]

src/openai/types/chat/completion_create_params.py

@@ -62,7 +62,7 @@ class Response(BaseModel):
     """
 
     model: ResponsesModel
-    """Model ID used to generate the response, like `gpt-4o` or `o1`.
+    """Model ID used to generate the response, like `gpt-4o` or `o3`.
 
     OpenAI offers a wide range of models with different capabilities, performance
     characteristics, and price points. Refer to the
@@ -149,6 +149,27 @@ class Response(BaseModel):
     [reasoning models](https://platform.openai.com/docs/guides/reasoning).
     """
 
+    service_tier: Optional[Literal["auto", "default", "flex"]] = None
+    """Specifies the latency tier to use for processing the request.
+
+    This parameter is relevant for customers subscribed to the scale tier service:
+
+    - If set to 'auto', and the Project is Scale tier enabled, the system will
+      utilize scale tier credits until they are exhausted.
+    - If set to 'auto', and the Project is not Scale tier enabled, the request will
+      be processed using the default service tier with a lower uptime SLA and no
+      latency guarentee.
+    - If set to 'default', the request will be processed using the default service
+      tier with a lower uptime SLA and no latency guarentee.
+    - If set to 'flex', the request will be processed with the Flex Processing
+      service tier.
+      [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+    - When not set, the default behavior is 'auto'.
+
+    When this parameter is set, the response body will include the `service_tier`
+    utilized.
+    """
+
     status: Optional[ResponseStatus] = None
     """The status of the response generation.
 

src/openai/types/completion_create_params.py

@@ -38,7 +38,7 @@ class ResponseCreateParamsBase(TypedDict, total=False):
     """
 
     model: Required[ResponsesModel]
-    """Model ID used to generate the response, like `gpt-4o` or `o1`.
+    """Model ID used to generate the response, like `gpt-4o` or `o3`.
 
     OpenAI offers a wide range of models with different capabilities, performance
     characteristics, and price points. Refer to the
@@ -102,6 +102,27 @@ class ResponseCreateParamsBase(TypedDict, total=False):
     [reasoning models](https://platform.openai.com/docs/guides/reasoning).
     """
 
+    service_tier: Optional[Literal["auto", "default", "flex"]]
+    """Specifies the latency tier to use for processing the request.
+
+    This parameter is relevant for customers subscribed to the scale tier service:
+
+    - If set to 'auto', and the Project is Scale tier enabled, the system will
+      utilize scale tier credits until they are exhausted.
+    - If set to 'auto', and the Project is not Scale tier enabled, the request will
+      be processed using the default service tier with a lower uptime SLA and no
+      latency guarentee.
+    - If set to 'default', the request will be processed using the default service
+      tier with a lower uptime SLA and no latency guarentee.
+    - If set to 'flex', the request will be processed with the Flex Processing
+      service tier.
+      [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+    - When not set, the default behavior is 'auto'.
+
+    When this parameter is set, the response body will include the `service_tier`
+    utilized.
+    """
+
     store: Optional[bool]
     """Whether to store the generated model response for later retrieval via API."""
 

src/openai/types/responses/response.py

@@ -11,6 +11,10 @@
     "gpt-4.1-2025-04-14",
     "gpt-4.1-mini-2025-04-14",
     "gpt-4.1-nano-2025-04-14",
+    "o4-mini",
+    "o4-mini-2025-04-16",
+    "o3",
+    "o3-2025-04-16",
     "o3-mini",
     "o3-mini-2025-01-31",
     "o1",

src/openai/types/responses/response_create_params.py

@@ -19,10 +19,17 @@ class Reasoning(BaseModel):
     result in faster responses and fewer tokens used on reasoning in a response.
     """
 
-    generate_summary: Optional[Literal["concise", "detailed"]] = None
-    """**computer_use_preview only**
+    generate_summary: Optional[Literal["auto", "concise", "detailed"]] = None
+    """**Deprecated:** use `summary` instead.
 
     A summary of the reasoning performed by the model. This can be useful for
-    debugging and understanding the model's reasoning process. One of `concise` or
-    `detailed`.
+    debugging and understanding the model's reasoning process. One of `auto`,
+    `concise`, or `detailed`.
+    """
+
+    summary: Optional[Literal["auto", "concise", "detailed"]] = None
+    """A summary of the reasoning performed by the model.
+
+    This can be useful for debugging and understanding the model's reasoning
+    process. One of `auto`, `concise`, or `detailed`.
     """

src/openai/types/shared/chat_model.py

@@ -13,6 +13,10 @@
     "gpt-4.1-2025-04-14",
     "gpt-4.1-mini-2025-04-14",
     "gpt-4.1-nano-2025-04-14",
+    "o4-mini",
+    "o4-mini-2025-04-16",
+    "o3",
+    "o3-2025-04-16",
     "o3-mini",
     "o3-mini-2025-01-31",
     "o1",

src/openai/types/shared/reasoning.py

@@ -20,10 +20,17 @@ class Reasoning(TypedDict, total=False):
     result in faster responses and fewer tokens used on reasoning in a response.
     """
 
-    generate_summary: Optional[Literal["concise", "detailed"]]
-    """**computer_use_preview only**
+    generate_summary: Optional[Literal["auto", "concise", "detailed"]]
+    """**Deprecated:** use `summary` instead.
 
     A summary of the reasoning performed by the model. This can be useful for
-    debugging and understanding the model's reasoning process. One of `concise` or
-    `detailed`.
+    debugging and understanding the model's reasoning process. One of `auto`,
+    `concise`, or `detailed`.
+    """
+
+    summary: Optional[Literal["auto", "concise", "detailed"]]
+    """A summary of the reasoning performed by the model.
+
+    This can be useful for debugging and understanding the model's reasoning
+    process. One of `auto`, `concise`, or `detailed`.
     """