aimlapi-sdk-python 2.8.1b0__py3-none-any.whl

openai/resources/chat/completions/completions.py

@@ -0,0 +1,3143 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+import inspect
+from typing import Dict, List, Type, Union, Iterable, Optional, cast
+from functools import partial
+from typing_extensions import Literal, overload
+
+import httpx
+import pydantic
+
+from .... import _legacy_response
+from .messages import (
+    Messages,
+    AsyncMessages,
+    MessagesWithRawResponse,
+    AsyncMessagesWithRawResponse,
+    MessagesWithStreamingResponse,
+    AsyncMessagesWithStreamingResponse,
+)
+from ...._types import Body, Omit, Query, Headers, NotGiven, SequenceNotStr, omit, not_given
+from ...._utils import required_args, maybe_transform, async_maybe_transform
+from ...._compat import cached_property
+from ...._resource import SyncAPIResource, AsyncAPIResource
+from ...._response import to_streamed_response_wrapper, async_to_streamed_response_wrapper
+from ...._streaming import Stream, AsyncStream
+from ....pagination import SyncCursorPage, AsyncCursorPage
+from ....types.chat import (
+    ChatCompletionAudioParam,
+    completion_list_params,
+    completion_create_params,
+    completion_update_params,
+)
+from ...._base_client import AsyncPaginator, make_request_options
+from ....lib._parsing import (
+    ResponseFormatT,
+    validate_input_tools as _validate_input_tools,
+    parse_chat_completion as _parse_chat_completion,
+    type_to_response_format_param as _type_to_response_format,
+)
+from ....lib.streaming.chat import ChatCompletionStreamManager, AsyncChatCompletionStreamManager
+from ....types.shared.chat_model import ChatModel
+from ....types.chat.chat_completion import ChatCompletion
+from ....types.shared_params.metadata import Metadata
+from ....types.shared.reasoning_effort import ReasoningEffort
+from ....types.chat.chat_completion_chunk import ChatCompletionChunk
+from ....types.chat.parsed_chat_completion import ParsedChatCompletion
+from ....types.chat.chat_completion_deleted import ChatCompletionDeleted
+from ....types.chat.chat_completion_audio_param import ChatCompletionAudioParam
+from ....types.chat.chat_completion_message_param import ChatCompletionMessageParam
+from ....types.chat.chat_completion_tool_union_param import ChatCompletionToolUnionParam
+from ....types.chat.chat_completion_stream_options_param import ChatCompletionStreamOptionsParam
+from ....types.chat.chat_completion_prediction_content_param import ChatCompletionPredictionContentParam
+from ....types.chat.chat_completion_tool_choice_option_param import ChatCompletionToolChoiceOptionParam
+
+__all__ = ["Completions", "AsyncCompletions"]
+
+
+class Completions(SyncAPIResource):
+    @cached_property
+    def messages(self) -> Messages:
+        return Messages(self._client)
+
+    @cached_property
+    def with_raw_response(self) -> CompletionsWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/openai/openai-python#accessing-raw-response-data-eg-headers
+        """
+        return CompletionsWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> CompletionsWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/openai/openai-python#with_streaming_response
+        """
+        return CompletionsWithStreamingResponse(self)
+
+    def parse(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: Union[str, ChatModel],
+        audio: Optional[ChatCompletionAudioParam] | Omit = omit,
+        response_format: type[ResponseFormatT] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        function_call: completion_create_params.FunctionCall | Omit = omit,
+        functions: Iterable[completion_create_params.Function] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[bool] | Omit = omit,
+        max_completion_tokens: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        metadata: Optional[Metadata] | Omit = omit,
+        modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        parallel_tool_calls: bool | Omit = omit,
+        prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        prompt_cache_key: str | Omit = omit,
+        prompt_cache_retention: Optional[Literal["in-memory", "24h"]] | Omit = omit,
+        reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
+        safety_identifier: str | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        store: Optional[bool] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        tool_choice: ChatCompletionToolChoiceOptionParam | Omit = omit,
+        tools: Iterable[ChatCompletionToolUnionParam] | Omit = omit,
+        top_logprobs: Optional[int] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | Omit = omit,
+        verbosity: Optional[Literal["low", "medium", "high"]] | Omit = omit,
+        web_search_options: completion_create_params.WebSearchOptions | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ParsedChatCompletion[ResponseFormatT]:
+        """Wrapper over the `client.chat.completions.create()` method that provides richer integrations with Python specific types
+        & returns a `ParsedChatCompletion` object, which is a subclass of the standard `ChatCompletion` class.
+
+        You can pass a pydantic model to this method and it will automatically convert the model
+        into a JSON schema, send it to the API and parse the response content back into the given model.
+
+        This method will also automatically parse `function` tool calls if:
+        - You use the `openai.pydantic_function_tool()` helper method
+        - You mark your tool schema with `"strict": True`
+
+        Example usage:
+        ```py
+        from pydantic import BaseModel
+        from openai import OpenAI
+
+
+        class Step(BaseModel):
+            explanation: str
+            output: str
+
+
+        class MathResponse(BaseModel):
+            steps: List[Step]
+            final_answer: str
+
+
+        client = OpenAI()
+        completion = client.chat.completions.parse(
+            model="gpt-4o-2024-08-06",
+            messages=[
+                {"role": "system", "content": "You are a helpful math tutor."},
+                {"role": "user", "content": "solve 8x + 31 = 2"},
+            ],
+            response_format=MathResponse,
+        )
+
+        message = completion.choices[0].message
+        if message.parsed:
+            print(message.parsed.steps)
+            print("answer: ", message.parsed.final_answer)
+        ```
+        """
+        chat_completion_tools = _validate_input_tools(tools)
+
+        extra_headers = {
+            "X-Stainless-Helper-Method": "chat.completions.parse",
+            **(extra_headers or {}),
+        }
+
+        def parser(raw_completion: ChatCompletion) -> ParsedChatCompletion[ResponseFormatT]:
+            return _parse_chat_completion(
+                response_format=response_format,
+                chat_completion=raw_completion,
+                input_tools=chat_completion_tools,
+            )
+
+        return self._post(
+            "/chat/completions",
+            body=maybe_transform(
+                {
+                    "messages": messages,
+                    "model": model,
+                    "audio": audio,
+                    "frequency_penalty": frequency_penalty,
+                    "function_call": function_call,
+                    "functions": functions,
+                    "logit_bias": logit_bias,
+                    "logprobs": logprobs,
+                    "max_completion_tokens": max_completion_tokens,
+                    "max_tokens": max_tokens,
+                    "metadata": metadata,
+                    "modalities": modalities,
+                    "n": n,
+                    "parallel_tool_calls": parallel_tool_calls,
+                    "prediction": prediction,
+                    "presence_penalty": presence_penalty,
+                    "prompt_cache_key": prompt_cache_key,
+                    "prompt_cache_retention": prompt_cache_retention,
+                    "reasoning_effort": reasoning_effort,
+                    "response_format": _type_to_response_format(response_format),
+                    "safety_identifier": safety_identifier,
+                    "seed": seed,
+                    "service_tier": service_tier,
+                    "stop": stop,
+                    "store": store,
+                    "stream": False,
+                    "stream_options": stream_options,
+                    "temperature": temperature,
+                    "tool_choice": tool_choice,
+                    "tools": tools,
+                    "top_logprobs": top_logprobs,
+                    "top_p": top_p,
+                    "user": user,
+                    "verbosity": verbosity,
+                    "web_search_options": web_search_options,
+                },
+                completion_create_params.CompletionCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                post_parser=parser,
+            ),
+            # we turn the `ChatCompletion` instance into a `ParsedChatCompletion`
+            # in the `parser` function above
+            cast_to=cast(Type[ParsedChatCompletion[ResponseFormatT]], ChatCompletion),
+            stream=False,
+        )
+
+    @overload
+    def create(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: Union[str, ChatModel],
+        audio: Optional[ChatCompletionAudioParam] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        function_call: completion_create_params.FunctionCall | Omit = omit,
+        functions: Iterable[completion_create_params.Function] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[bool] | Omit = omit,
+        max_completion_tokens: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        metadata: Optional[Metadata] | Omit = omit,
+        modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        parallel_tool_calls: bool | Omit = omit,
+        prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        prompt_cache_key: str | Omit = omit,
+        prompt_cache_retention: Optional[Literal["in-memory", "24h"]] | Omit = omit,
+        reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
+        response_format: completion_create_params.ResponseFormat | Omit = omit,
+        safety_identifier: str | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        store: Optional[bool] | Omit = omit,
+        stream: Optional[Literal[False]] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        tool_choice: ChatCompletionToolChoiceOptionParam | Omit = omit,
+        tools: Iterable[ChatCompletionToolUnionParam] | Omit = omit,
+        top_logprobs: Optional[int] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | Omit = omit,
+        verbosity: Optional[Literal["low", "medium", "high"]] | Omit = omit,
+        web_search_options: completion_create_params.WebSearchOptions | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ChatCompletion:
+        """
+        **Starting a new project?** We recommend trying
+        [Responses](https://platform.openai.com/docs/api-reference/responses) to take
+        advantage of the latest OpenAI platform features. Compare
+        [Chat Completions with Responses](https://platform.openai.com/docs/guides/responses-vs-chat-completions?api-mode=responses).
+
+        ---
+
+        Creates a model response for the given chat conversation. Learn more in the
+        [text generation](https://platform.openai.com/docs/guides/text-generation),
+        [vision](https://platform.openai.com/docs/guides/vision), and
+        [audio](https://platform.openai.com/docs/guides/audio) guides.
+
+        Parameter support can differ depending on the model used to generate the
+        response, particularly for newer reasoning models. Parameters that are only
+        supported for reasoning models are noted below. For the current state of
+        unsupported parameters in reasoning models,
+        [refer to the reasoning guide](https://platform.openai.com/docs/guides/reasoning).
+
+        Args:
+          messages: A list of messages comprising the conversation so far. Depending on the
+              [model](https://platform.openai.com/docs/models) you use, different message
+              types (modalities) are supported, like
+              [text](https://platform.openai.com/docs/guides/text-generation),
+              [images](https://platform.openai.com/docs/guides/vision), and
+              [audio](https://platform.openai.com/docs/guides/audio).
+
+          model: 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
+              [model guide](https://platform.openai.com/docs/models) to browse and compare
+              available models.
+
+          audio: Parameters for audio output. Required when audio output is requested with
+              `modalities: ["audio"]`.
+              [Learn more](https://platform.openai.com/docs/guides/audio).
+
+          frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their
+              existing frequency in the text so far, decreasing the model's likelihood to
+              repeat the same line verbatim.
+
+          function_call: Deprecated in favor of `tool_choice`.
+
+              Controls which (if any) function is called by the model.
+
+              `none` means the model will not call a function and instead generates a message.
+
+              `auto` means the model can pick between generating a message or calling a
+              function.
+
+              Specifying a particular function via `{"name": "my_function"}` forces the model
+              to call that function.
+
+              `none` is the default when no functions are present. `auto` is the default if
+              functions are present.
+
+          functions: Deprecated in favor of `tools`.
+
+              A list of functions the model may generate JSON inputs for.
+
+          logit_bias: Modify the likelihood of specified tokens appearing in the completion.
+
+              Accepts a JSON object that maps tokens (specified by their token ID in the
+              tokenizer) to an associated bias value from -100 to 100. Mathematically, the
+              bias is added to the logits generated by the model prior to sampling. The exact
+              effect will vary per model, but values between -1 and 1 should decrease or
+              increase likelihood of selection; values like -100 or 100 should result in a ban
+              or exclusive selection of the relevant token.
+
+          logprobs: Whether to return log probabilities of the output tokens or not. If true,
+              returns the log probabilities of each output token returned in the `content` of
+              `message`.
+
+          max_completion_tokens: An upper bound for the number of tokens that can be generated for a completion,
+              including visible output tokens and
+              [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
+
+          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat
+              completion. This value can be used to control
+              [costs](https://openai.com/api/pricing/) for text generated via API.
+
+              This value is now deprecated in favor of `max_completion_tokens`, and is not
+              compatible with
+              [o-series models](https://platform.openai.com/docs/guides/reasoning).
+
+          metadata: Set of 16 key-value pairs that can be attached to an object. This can be useful
+              for storing additional information about the object in a structured format, and
+              querying for objects via API or the dashboard.
+
+              Keys are strings with a maximum length of 64 characters. Values are strings with
+              a maximum length of 512 characters.
+
+          modalities: Output types that you would like the model to generate. Most models are capable
+              of generating text, which is the default:
+
+              `["text"]`
+
+              The `gpt-4o-audio-preview` model can also be used to
+              [generate audio](https://platform.openai.com/docs/guides/audio). To request that
+              this model generate both text and audio responses, you can use:
+
+              `["text", "audio"]`
+
+          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.
+
+          parallel_tool_calls: Whether to enable
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
+              during tool use.
+
+          prediction: Static predicted output content, such as the content of a text file that is
+              being regenerated.
+
+          presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
+              whether they appear in the text so far, increasing the model's likelihood to
+              talk about new topics.
+
+          prompt_cache_key: Used by OpenAI to cache responses for similar requests to optimize your cache
+              hit rates. Replaces the `user` field.
+              [Learn more](https://platform.openai.com/docs/guides/prompt-caching).
+
+          prompt_cache_retention: The retention policy for the prompt cache. Set to `24h` to enable extended
+              prompt caching, which keeps cached prefixes active for longer, up to a maximum
+              of 24 hours.
+              [Learn more](https://platform.openai.com/docs/guides/prompt-caching#prompt-cache-retention).
+
+          reasoning_effort: Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
+              reasoning effort can result in faster responses and fewer tokens used on
+              reasoning in a response.
+
+              - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
+                reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
+                calls are supported for all reasoning values in gpt-5.1.
+              - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
+                support `none`.
+              - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+
+          response_format: An object specifying the format that the model must output.
+
+              Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
+              [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
+
+              Setting to `{ "type": "json_object" }` enables the older JSON mode, which
+              ensures the message the model generates is valid JSON. Using `json_schema` is
+              preferred for models that support it.
+
+          safety_identifier: A stable identifier used to help detect users of your application that may be
+              violating OpenAI's usage policies. The IDs should be a string that uniquely
+              identifies each user. We recommend hashing their username or email address, in
+              order to avoid sending us any identifying information.
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
+
+          seed: This feature is in Beta. If specified, our system will make a best effort to
+              sample deterministically, such that repeated requests with the same `seed` and
+              parameters should return the same result. Determinism is not guaranteed, and you
+              should refer to the `system_fingerprint` response parameter to monitor changes
+              in the backend.
+
+          service_tier: Specifies the processing type used for serving the request.
+
+              - If set to 'auto', then the request will be processed with the service tier
+                configured in the Project settings. Unless otherwise configured, the Project
+                will use 'default'.
+              - If set to 'default', then the request will be processed with the standard
+                pricing and performance for the selected model.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+                '[priority](https://openai.com/api-priority-processing/)', then the request
+                will be processed with the corresponding service tier.
+              - When not set, the default behavior is 'auto'.
+
+              When the `service_tier` parameter is set, the response body will include the
+              `service_tier` value based on the processing mode actually used to serve the
+              request. This response value may be different from the value set in the
+              parameter.
+
+          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.
+
+          store: Whether or not to store the output of this chat completion request for use in
+              our [model distillation](https://platform.openai.com/docs/guides/distillation)
+              or [evals](https://platform.openai.com/docs/guides/evals) products.
+
+              Supports text and image inputs. Note: image inputs over 8MB will be dropped.
+
+          stream: If set to true, the model response data will be streamed to the client as it is
+              generated using
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
+              See the
+              [Streaming section below](https://platform.openai.com/docs/api-reference/chat/streaming)
+              for more information, along with the
+              [streaming responses](https://platform.openai.com/docs/guides/streaming-responses)
+              guide for more information on how to handle the streaming events.
+
+          stream_options: Options for streaming response. Only set this when you set `stream: true`.
+
+          temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
+              make the output more random, while lower values like 0.2 will make it more
+              focused and deterministic. We generally recommend altering this or `top_p` but
+              not both.
+
+          tool_choice: Controls which (if any) tool is called by the model. `none` means the model will
+              not call any tool and instead generates a message. `auto` means the model can
+              pick between generating a message or calling one or more tools. `required` means
+              the model must call one or more tools. Specifying a particular tool via
+              `{"type": "function", "function": {"name": "my_function"}}` forces the model to
+              call that tool.
+
+              `none` is the default when no tools are present. `auto` is the default if tools
+              are present.
+
+          tools: A list of tools the model may call. You can provide either
+              [custom tools](https://platform.openai.com/docs/guides/function-calling#custom-tools)
+              or [function tools](https://platform.openai.com/docs/guides/function-calling).
+
+          top_logprobs: An integer between 0 and 20 specifying the number of most likely tokens to
+              return at each token position, each with an associated log probability.
+              `logprobs` must be set to `true` if this parameter is used.
+
+          top_p: An alternative to sampling with temperature, called nucleus sampling, where the
+              model considers the results of the tokens with top_p probability mass. So 0.1
+              means only the tokens comprising the top 10% probability mass are considered.
+
+              We generally recommend altering this or `temperature` but not both.
+
+          user: This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use
+              `prompt_cache_key` instead to maintain caching optimizations. A stable
+              identifier for your end-users. Used to boost cache hit rates by better bucketing
+              similar requests and to help OpenAI detect and prevent abuse.
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
+
+          verbosity: Constrains the verbosity of the model's response. Lower values will result in
+              more concise responses, while higher values will result in more verbose
+              responses. Currently supported values are `low`, `medium`, and `high`.
+
+          web_search_options: This tool searches the web for relevant results to use in a response. Learn more
+              about the
+              [web search tool](https://platform.openai.com/docs/guides/tools-web-search?api-mode=chat).
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        ...
+
+    @overload
+    def create(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: Union[str, ChatModel],
+        stream: Literal[True],
+        audio: Optional[ChatCompletionAudioParam] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        function_call: completion_create_params.FunctionCall | Omit = omit,
+        functions: Iterable[completion_create_params.Function] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[bool] | Omit = omit,
+        max_completion_tokens: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        metadata: Optional[Metadata] | Omit = omit,
+        modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        parallel_tool_calls: bool | Omit = omit,
+        prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        prompt_cache_key: str | Omit = omit,
+        prompt_cache_retention: Optional[Literal["in-memory", "24h"]] | Omit = omit,
+        reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
+        response_format: completion_create_params.ResponseFormat | Omit = omit,
+        safety_identifier: str | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        store: Optional[bool] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        tool_choice: ChatCompletionToolChoiceOptionParam | Omit = omit,
+        tools: Iterable[ChatCompletionToolUnionParam] | Omit = omit,
+        top_logprobs: Optional[int] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | Omit = omit,
+        verbosity: Optional[Literal["low", "medium", "high"]] | Omit = omit,
+        web_search_options: completion_create_params.WebSearchOptions | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> Stream[ChatCompletionChunk]:
+        """
+        **Starting a new project?** We recommend trying
+        [Responses](https://platform.openai.com/docs/api-reference/responses) to take
+        advantage of the latest OpenAI platform features. Compare
+        [Chat Completions with Responses](https://platform.openai.com/docs/guides/responses-vs-chat-completions?api-mode=responses).
+
+        ---
+
+        Creates a model response for the given chat conversation. Learn more in the
+        [text generation](https://platform.openai.com/docs/guides/text-generation),
+        [vision](https://platform.openai.com/docs/guides/vision), and
+        [audio](https://platform.openai.com/docs/guides/audio) guides.
+
+        Parameter support can differ depending on the model used to generate the
+        response, particularly for newer reasoning models. Parameters that are only
+        supported for reasoning models are noted below. For the current state of
+        unsupported parameters in reasoning models,
+        [refer to the reasoning guide](https://platform.openai.com/docs/guides/reasoning).
+
+        Args:
+          messages: A list of messages comprising the conversation so far. Depending on the
+              [model](https://platform.openai.com/docs/models) you use, different message
+              types (modalities) are supported, like
+              [text](https://platform.openai.com/docs/guides/text-generation),
+              [images](https://platform.openai.com/docs/guides/vision), and
+              [audio](https://platform.openai.com/docs/guides/audio).
+
+          model: 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
+              [model guide](https://platform.openai.com/docs/models) to browse and compare
+              available models.
+
+          stream: If set to true, the model response data will be streamed to the client as it is
+              generated using
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
+              See the
+              [Streaming section below](https://platform.openai.com/docs/api-reference/chat/streaming)
+              for more information, along with the
+              [streaming responses](https://platform.openai.com/docs/guides/streaming-responses)
+              guide for more information on how to handle the streaming events.
+
+          audio: Parameters for audio output. Required when audio output is requested with
+              `modalities: ["audio"]`.
+              [Learn more](https://platform.openai.com/docs/guides/audio).
+
+          frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their
+              existing frequency in the text so far, decreasing the model's likelihood to
+              repeat the same line verbatim.
+
+          function_call: Deprecated in favor of `tool_choice`.
+
+              Controls which (if any) function is called by the model.
+
+              `none` means the model will not call a function and instead generates a message.
+
+              `auto` means the model can pick between generating a message or calling a
+              function.
+
+              Specifying a particular function via `{"name": "my_function"}` forces the model
+              to call that function.
+
+              `none` is the default when no functions are present. `auto` is the default if
+              functions are present.
+
+          functions: Deprecated in favor of `tools`.
+
+              A list of functions the model may generate JSON inputs for.
+
+          logit_bias: Modify the likelihood of specified tokens appearing in the completion.
+
+              Accepts a JSON object that maps tokens (specified by their token ID in the
+              tokenizer) to an associated bias value from -100 to 100. Mathematically, the
+              bias is added to the logits generated by the model prior to sampling. The exact
+              effect will vary per model, but values between -1 and 1 should decrease or
+              increase likelihood of selection; values like -100 or 100 should result in a ban
+              or exclusive selection of the relevant token.
+
+          logprobs: Whether to return log probabilities of the output tokens or not. If true,
+              returns the log probabilities of each output token returned in the `content` of
+              `message`.
+
+          max_completion_tokens: An upper bound for the number of tokens that can be generated for a completion,
+              including visible output tokens and
+              [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
+
+          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat
+              completion. This value can be used to control
+              [costs](https://openai.com/api/pricing/) for text generated via API.
+
+              This value is now deprecated in favor of `max_completion_tokens`, and is not
+              compatible with
+              [o-series models](https://platform.openai.com/docs/guides/reasoning).
+
+          metadata: Set of 16 key-value pairs that can be attached to an object. This can be useful
+              for storing additional information about the object in a structured format, and
+              querying for objects via API or the dashboard.
+
+              Keys are strings with a maximum length of 64 characters. Values are strings with
+              a maximum length of 512 characters.
+
+          modalities: Output types that you would like the model to generate. Most models are capable
+              of generating text, which is the default:
+
+              `["text"]`
+
+              The `gpt-4o-audio-preview` model can also be used to
+              [generate audio](https://platform.openai.com/docs/guides/audio). To request that
+              this model generate both text and audio responses, you can use:
+
+              `["text", "audio"]`
+
+          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.
+
+          parallel_tool_calls: Whether to enable
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
+              during tool use.
+
+          prediction: Static predicted output content, such as the content of a text file that is
+              being regenerated.
+
+          presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
+              whether they appear in the text so far, increasing the model's likelihood to
+              talk about new topics.
+
+          prompt_cache_key: Used by OpenAI to cache responses for similar requests to optimize your cache
+              hit rates. Replaces the `user` field.
+              [Learn more](https://platform.openai.com/docs/guides/prompt-caching).
+
+          prompt_cache_retention: The retention policy for the prompt cache. Set to `24h` to enable extended
+              prompt caching, which keeps cached prefixes active for longer, up to a maximum
+              of 24 hours.
+              [Learn more](https://platform.openai.com/docs/guides/prompt-caching#prompt-cache-retention).
+
+          reasoning_effort: Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
+              reasoning effort can result in faster responses and fewer tokens used on
+              reasoning in a response.
+
+              - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
+                reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
+                calls are supported for all reasoning values in gpt-5.1.
+              - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
+                support `none`.
+              - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+
+          response_format: An object specifying the format that the model must output.
+
+              Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
+              [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
+
+              Setting to `{ "type": "json_object" }` enables the older JSON mode, which
+              ensures the message the model generates is valid JSON. Using `json_schema` is
+              preferred for models that support it.
+
+          safety_identifier: A stable identifier used to help detect users of your application that may be
+              violating OpenAI's usage policies. The IDs should be a string that uniquely
+              identifies each user. We recommend hashing their username or email address, in
+              order to avoid sending us any identifying information.
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
+
+          seed: This feature is in Beta. If specified, our system will make a best effort to
+              sample deterministically, such that repeated requests with the same `seed` and
+              parameters should return the same result. Determinism is not guaranteed, and you
+              should refer to the `system_fingerprint` response parameter to monitor changes
+              in the backend.
+
+          service_tier: Specifies the processing type used for serving the request.
+
+              - If set to 'auto', then the request will be processed with the service tier
+                configured in the Project settings. Unless otherwise configured, the Project
+                will use 'default'.
+              - If set to 'default', then the request will be processed with the standard
+                pricing and performance for the selected model.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+                '[priority](https://openai.com/api-priority-processing/)', then the request
+                will be processed with the corresponding service tier.
+              - When not set, the default behavior is 'auto'.
+
+              When the `service_tier` parameter is set, the response body will include the
+              `service_tier` value based on the processing mode actually used to serve the
+              request. This response value may be different from the value set in the
+              parameter.
+
+          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.
+
+          store: Whether or not to store the output of this chat completion request for use in
+              our [model distillation](https://platform.openai.com/docs/guides/distillation)
+              or [evals](https://platform.openai.com/docs/guides/evals) products.
+
+              Supports text and image inputs. Note: image inputs over 8MB will be dropped.
+
+          stream_options: Options for streaming response. Only set this when you set `stream: true`.
+
+          temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
+              make the output more random, while lower values like 0.2 will make it more
+              focused and deterministic. We generally recommend altering this or `top_p` but
+              not both.
+
+          tool_choice: Controls which (if any) tool is called by the model. `none` means the model will
+              not call any tool and instead generates a message. `auto` means the model can
+              pick between generating a message or calling one or more tools. `required` means
+              the model must call one or more tools. Specifying a particular tool via
+              `{"type": "function", "function": {"name": "my_function"}}` forces the model to
+              call that tool.
+
+              `none` is the default when no tools are present. `auto` is the default if tools
+              are present.
+
+          tools: A list of tools the model may call. You can provide either
+              [custom tools](https://platform.openai.com/docs/guides/function-calling#custom-tools)
+              or [function tools](https://platform.openai.com/docs/guides/function-calling).
+
+          top_logprobs: An integer between 0 and 20 specifying the number of most likely tokens to
+              return at each token position, each with an associated log probability.
+              `logprobs` must be set to `true` if this parameter is used.
+
+          top_p: An alternative to sampling with temperature, called nucleus sampling, where the
+              model considers the results of the tokens with top_p probability mass. So 0.1
+              means only the tokens comprising the top 10% probability mass are considered.
+
+              We generally recommend altering this or `temperature` but not both.
+
+          user: This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use
+              `prompt_cache_key` instead to maintain caching optimizations. A stable
+              identifier for your end-users. Used to boost cache hit rates by better bucketing
+              similar requests and to help OpenAI detect and prevent abuse.
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
+
+          verbosity: Constrains the verbosity of the model's response. Lower values will result in
+              more concise responses, while higher values will result in more verbose
+              responses. Currently supported values are `low`, `medium`, and `high`.
+
+          web_search_options: This tool searches the web for relevant results to use in a response. Learn more
+              about the
+              [web search tool](https://platform.openai.com/docs/guides/tools-web-search?api-mode=chat).
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        ...
+
+    @overload
+    def create(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: Union[str, ChatModel],
+        stream: bool,
+        audio: Optional[ChatCompletionAudioParam] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        function_call: completion_create_params.FunctionCall | Omit = omit,
+        functions: Iterable[completion_create_params.Function] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[bool] | Omit = omit,
+        max_completion_tokens: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        metadata: Optional[Metadata] | Omit = omit,
+        modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        parallel_tool_calls: bool | Omit = omit,
+        prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        prompt_cache_key: str | Omit = omit,
+        prompt_cache_retention: Optional[Literal["in-memory", "24h"]] | Omit = omit,
+        reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
+        response_format: completion_create_params.ResponseFormat | Omit = omit,
+        safety_identifier: str | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        store: Optional[bool] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        tool_choice: ChatCompletionToolChoiceOptionParam | Omit = omit,
+        tools: Iterable[ChatCompletionToolUnionParam] | Omit = omit,
+        top_logprobs: Optional[int] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | Omit = omit,
+        verbosity: Optional[Literal["low", "medium", "high"]] | Omit = omit,
+        web_search_options: completion_create_params.WebSearchOptions | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ChatCompletion | Stream[ChatCompletionChunk]:
+        """
+        **Starting a new project?** We recommend trying
+        [Responses](https://platform.openai.com/docs/api-reference/responses) to take
+        advantage of the latest OpenAI platform features. Compare
+        [Chat Completions with Responses](https://platform.openai.com/docs/guides/responses-vs-chat-completions?api-mode=responses).
+
+        ---
+
+        Creates a model response for the given chat conversation. Learn more in the
+        [text generation](https://platform.openai.com/docs/guides/text-generation),
+        [vision](https://platform.openai.com/docs/guides/vision), and
+        [audio](https://platform.openai.com/docs/guides/audio) guides.
+
+        Parameter support can differ depending on the model used to generate the
+        response, particularly for newer reasoning models. Parameters that are only
+        supported for reasoning models are noted below. For the current state of
+        unsupported parameters in reasoning models,
+        [refer to the reasoning guide](https://platform.openai.com/docs/guides/reasoning).
+
+        Args:
+          messages: A list of messages comprising the conversation so far. Depending on the
+              [model](https://platform.openai.com/docs/models) you use, different message
+              types (modalities) are supported, like
+              [text](https://platform.openai.com/docs/guides/text-generation),
+              [images](https://platform.openai.com/docs/guides/vision), and
+              [audio](https://platform.openai.com/docs/guides/audio).
+
+          model: 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
+              [model guide](https://platform.openai.com/docs/models) to browse and compare
+              available models.
+
+          stream: If set to true, the model response data will be streamed to the client as it is
+              generated using
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
+              See the
+              [Streaming section below](https://platform.openai.com/docs/api-reference/chat/streaming)
+              for more information, along with the
+              [streaming responses](https://platform.openai.com/docs/guides/streaming-responses)
+              guide for more information on how to handle the streaming events.
+
+          audio: Parameters for audio output. Required when audio output is requested with
+              `modalities: ["audio"]`.
+              [Learn more](https://platform.openai.com/docs/guides/audio).
+
+          frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their
+              existing frequency in the text so far, decreasing the model's likelihood to
+              repeat the same line verbatim.
+
+          function_call: Deprecated in favor of `tool_choice`.
+
+              Controls which (if any) function is called by the model.
+
+              `none` means the model will not call a function and instead generates a message.
+
+              `auto` means the model can pick between generating a message or calling a
+              function.
+
+              Specifying a particular function via `{"name": "my_function"}` forces the model
+              to call that function.
+
+              `none` is the default when no functions are present. `auto` is the default if
+              functions are present.
+
+          functions: Deprecated in favor of `tools`.
+
+              A list of functions the model may generate JSON inputs for.
+
+          logit_bias: Modify the likelihood of specified tokens appearing in the completion.
+
+              Accepts a JSON object that maps tokens (specified by their token ID in the
+              tokenizer) to an associated bias value from -100 to 100. Mathematically, the
+              bias is added to the logits generated by the model prior to sampling. The exact
+              effect will vary per model, but values between -1 and 1 should decrease or
+              increase likelihood of selection; values like -100 or 100 should result in a ban
+              or exclusive selection of the relevant token.
+
+          logprobs: Whether to return log probabilities of the output tokens or not. If true,
+              returns the log probabilities of each output token returned in the `content` of
+              `message`.
+
+          max_completion_tokens: An upper bound for the number of tokens that can be generated for a completion,
+              including visible output tokens and
+              [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
+
+          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat
+              completion. This value can be used to control
+              [costs](https://openai.com/api/pricing/) for text generated via API.
+
+              This value is now deprecated in favor of `max_completion_tokens`, and is not
+              compatible with
+              [o-series models](https://platform.openai.com/docs/guides/reasoning).
+
+          metadata: Set of 16 key-value pairs that can be attached to an object. This can be useful
+              for storing additional information about the object in a structured format, and
+              querying for objects via API or the dashboard.
+
+              Keys are strings with a maximum length of 64 characters. Values are strings with
+              a maximum length of 512 characters.
+
+          modalities: Output types that you would like the model to generate. Most models are capable
+              of generating text, which is the default:
+
+              `["text"]`
+
+              The `gpt-4o-audio-preview` model can also be used to
+              [generate audio](https://platform.openai.com/docs/guides/audio). To request that
+              this model generate both text and audio responses, you can use:
+
+              `["text", "audio"]`
+
+          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.
+
+          parallel_tool_calls: Whether to enable
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
+              during tool use.
+
+          prediction: Static predicted output content, such as the content of a text file that is
+              being regenerated.
+
+          presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
+              whether they appear in the text so far, increasing the model's likelihood to
+              talk about new topics.
+
+          prompt_cache_key: Used by OpenAI to cache responses for similar requests to optimize your cache
+              hit rates. Replaces the `user` field.
+              [Learn more](https://platform.openai.com/docs/guides/prompt-caching).
+
+          prompt_cache_retention: The retention policy for the prompt cache. Set to `24h` to enable extended
+              prompt caching, which keeps cached prefixes active for longer, up to a maximum
+              of 24 hours.
+              [Learn more](https://platform.openai.com/docs/guides/prompt-caching#prompt-cache-retention).
+
+          reasoning_effort: Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
+              reasoning effort can result in faster responses and fewer tokens used on
+              reasoning in a response.
+
+              - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
+                reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
+                calls are supported for all reasoning values in gpt-5.1.
+              - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
+                support `none`.
+              - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+
+          response_format: An object specifying the format that the model must output.
+
+              Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
+              [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
+
+              Setting to `{ "type": "json_object" }` enables the older JSON mode, which
+              ensures the message the model generates is valid JSON. Using `json_schema` is
+              preferred for models that support it.
+
+          safety_identifier: A stable identifier used to help detect users of your application that may be
+              violating OpenAI's usage policies. The IDs should be a string that uniquely
+              identifies each user. We recommend hashing their username or email address, in
+              order to avoid sending us any identifying information.
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
+
+          seed: This feature is in Beta. If specified, our system will make a best effort to
+              sample deterministically, such that repeated requests with the same `seed` and
+              parameters should return the same result. Determinism is not guaranteed, and you
+              should refer to the `system_fingerprint` response parameter to monitor changes
+              in the backend.
+
+          service_tier: Specifies the processing type used for serving the request.
+
+              - If set to 'auto', then the request will be processed with the service tier
+                configured in the Project settings. Unless otherwise configured, the Project
+                will use 'default'.
+              - If set to 'default', then the request will be processed with the standard
+                pricing and performance for the selected model.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+                '[priority](https://openai.com/api-priority-processing/)', then the request
+                will be processed with the corresponding service tier.
+              - When not set, the default behavior is 'auto'.
+
+              When the `service_tier` parameter is set, the response body will include the
+              `service_tier` value based on the processing mode actually used to serve the
+              request. This response value may be different from the value set in the
+              parameter.
+
+          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.
+
+          store: Whether or not to store the output of this chat completion request for use in
+              our [model distillation](https://platform.openai.com/docs/guides/distillation)
+              or [evals](https://platform.openai.com/docs/guides/evals) products.
+
+              Supports text and image inputs. Note: image inputs over 8MB will be dropped.
+
+          stream_options: Options for streaming response. Only set this when you set `stream: true`.
+
+          temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
+              make the output more random, while lower values like 0.2 will make it more
+              focused and deterministic. We generally recommend altering this or `top_p` but
+              not both.
+
+          tool_choice: Controls which (if any) tool is called by the model. `none` means the model will
+              not call any tool and instead generates a message. `auto` means the model can
+              pick between generating a message or calling one or more tools. `required` means
+              the model must call one or more tools. Specifying a particular tool via
+              `{"type": "function", "function": {"name": "my_function"}}` forces the model to
+              call that tool.
+
+              `none` is the default when no tools are present. `auto` is the default if tools
+              are present.
+
+          tools: A list of tools the model may call. You can provide either
+              [custom tools](https://platform.openai.com/docs/guides/function-calling#custom-tools)
+              or [function tools](https://platform.openai.com/docs/guides/function-calling).
+
+          top_logprobs: An integer between 0 and 20 specifying the number of most likely tokens to
+              return at each token position, each with an associated log probability.
+              `logprobs` must be set to `true` if this parameter is used.
+
+          top_p: An alternative to sampling with temperature, called nucleus sampling, where the
+              model considers the results of the tokens with top_p probability mass. So 0.1
+              means only the tokens comprising the top 10% probability mass are considered.
+
+              We generally recommend altering this or `temperature` but not both.
+
+          user: This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use
+              `prompt_cache_key` instead to maintain caching optimizations. A stable
+              identifier for your end-users. Used to boost cache hit rates by better bucketing
+              similar requests and to help OpenAI detect and prevent abuse.
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
+
+          verbosity: Constrains the verbosity of the model's response. Lower values will result in
+              more concise responses, while higher values will result in more verbose
+              responses. Currently supported values are `low`, `medium`, and `high`.
+
+          web_search_options: This tool searches the web for relevant results to use in a response. Learn more
+              about the
+              [web search tool](https://platform.openai.com/docs/guides/tools-web-search?api-mode=chat).
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        ...
+
+    @required_args(["messages", "model"], ["messages", "model", "stream"])
+    def create(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: Union[str, ChatModel],
+        audio: Optional[ChatCompletionAudioParam] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        function_call: completion_create_params.FunctionCall | Omit = omit,
+        functions: Iterable[completion_create_params.Function] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[bool] | Omit = omit,
+        max_completion_tokens: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        metadata: Optional[Metadata] | Omit = omit,
+        modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        parallel_tool_calls: bool | Omit = omit,
+        prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        prompt_cache_key: str | Omit = omit,
+        prompt_cache_retention: Optional[Literal["in-memory", "24h"]] | Omit = omit,
+        reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
+        response_format: completion_create_params.ResponseFormat | Omit = omit,
+        safety_identifier: str | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        store: Optional[bool] | Omit = omit,
+        stream: Optional[Literal[False]] | Literal[True] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        tool_choice: ChatCompletionToolChoiceOptionParam | Omit = omit,
+        tools: Iterable[ChatCompletionToolUnionParam] | Omit = omit,
+        top_logprobs: Optional[int] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | Omit = omit,
+        verbosity: Optional[Literal["low", "medium", "high"]] | Omit = omit,
+        web_search_options: completion_create_params.WebSearchOptions | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ChatCompletion | Stream[ChatCompletionChunk]:
+        validate_response_format(response_format)
+        return self._post(
+            "/chat/completions",
+            body=maybe_transform(
+                {
+                    "messages": messages,
+                    "model": model,
+                    "audio": audio,
+                    "frequency_penalty": frequency_penalty,
+                    "function_call": function_call,
+                    "functions": functions,
+                    "logit_bias": logit_bias,
+                    "logprobs": logprobs,
+                    "max_completion_tokens": max_completion_tokens,
+                    "max_tokens": max_tokens,
+                    "metadata": metadata,
+                    "modalities": modalities,
+                    "n": n,
+                    "parallel_tool_calls": parallel_tool_calls,
+                    "prediction": prediction,
+                    "presence_penalty": presence_penalty,
+                    "prompt_cache_key": prompt_cache_key,
+                    "prompt_cache_retention": prompt_cache_retention,
+                    "reasoning_effort": reasoning_effort,
+                    "response_format": response_format,
+                    "safety_identifier": safety_identifier,
+                    "seed": seed,
+                    "service_tier": service_tier,
+                    "stop": stop,
+                    "store": store,
+                    "stream": stream,
+                    "stream_options": stream_options,
+                    "temperature": temperature,
+                    "tool_choice": tool_choice,
+                    "tools": tools,
+                    "top_logprobs": top_logprobs,
+                    "top_p": top_p,
+                    "user": user,
+                    "verbosity": verbosity,
+                    "web_search_options": web_search_options,
+                },
+                completion_create_params.CompletionCreateParamsStreaming
+                if stream
+                else completion_create_params.CompletionCreateParamsNonStreaming,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ChatCompletion,
+            stream=stream or False,
+            stream_cls=Stream[ChatCompletionChunk],
+        )
+
+    def retrieve(
+        self,
+        completion_id: str,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ChatCompletion:
+        """Get a stored chat completion.
+
+        Only Chat Completions that have been created with
+        the `store` parameter set to `true` will be returned.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not completion_id:
+            raise ValueError(f"Expected a non-empty value for `completion_id` but received {completion_id!r}")
+        return self._get(
+            f"/chat/completions/{completion_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ChatCompletion,
+        )
+
+    def update(
+        self,
+        completion_id: str,
+        *,
+        metadata: Optional[Metadata],
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ChatCompletion:
+        """Modify a stored chat completion.
+
+        Only Chat Completions that have been created
+        with the `store` parameter set to `true` can be modified. Currently, the only
+        supported modification is to update the `metadata` field.
+
+        Args:
+          metadata: Set of 16 key-value pairs that can be attached to an object. This can be useful
+              for storing additional information about the object in a structured format, and
+              querying for objects via API or the dashboard.
+
+              Keys are strings with a maximum length of 64 characters. Values are strings with
+              a maximum length of 512 characters.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not completion_id:
+            raise ValueError(f"Expected a non-empty value for `completion_id` but received {completion_id!r}")
+        return self._post(
+            f"/chat/completions/{completion_id}",
+            body=maybe_transform({"metadata": metadata}, completion_update_params.CompletionUpdateParams),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ChatCompletion,
+        )
+
+    def list(
+        self,
+        *,
+        after: str | Omit = omit,
+        limit: int | Omit = omit,
+        metadata: Optional[Metadata] | Omit = omit,
+        model: str | Omit = omit,
+        order: Literal["asc", "desc"] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> SyncCursorPage[ChatCompletion]:
+        """List stored Chat Completions.
+
+        Only Chat Completions that have been stored with
+        the `store` parameter set to `true` will be returned.
+
+        Args:
+          after: Identifier for the last chat completion from the previous pagination request.
+
+          limit: Number of Chat Completions to retrieve.
+
+          metadata: Set of 16 key-value pairs that can be attached to an object. This can be useful
+              for storing additional information about the object in a structured format, and
+              querying for objects via API or the dashboard.
+
+              Keys are strings with a maximum length of 64 characters. Values are strings with
+              a maximum length of 512 characters.
+
+          model: The model used to generate the Chat Completions.
+
+          order: Sort order for Chat Completions by timestamp. Use `asc` for ascending order or
+              `desc` for descending order. Defaults to `asc`.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        return self._get_api_list(
+            "/chat/completions",
+            page=SyncCursorPage[ChatCompletion],
+            options=make_request_options(
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                query=maybe_transform(
+                    {
+                        "after": after,
+                        "limit": limit,
+                        "metadata": metadata,
+                        "model": model,
+                        "order": order,
+                    },
+                    completion_list_params.CompletionListParams,
+                ),
+            ),
+            model=ChatCompletion,
+        )
+
+    def delete(
+        self,
+        completion_id: str,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ChatCompletionDeleted:
+        """Delete a stored chat completion.
+
+        Only Chat Completions that have been created
+        with the `store` parameter set to `true` can be deleted.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not completion_id:
+            raise ValueError(f"Expected a non-empty value for `completion_id` but received {completion_id!r}")
+        return self._delete(
+            f"/chat/completions/{completion_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ChatCompletionDeleted,
+        )
+
+    def stream(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: Union[str, ChatModel],
+        audio: Optional[ChatCompletionAudioParam] | Omit = omit,
+        response_format: completion_create_params.ResponseFormat | type[ResponseFormatT] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        function_call: completion_create_params.FunctionCall | Omit = omit,
+        functions: Iterable[completion_create_params.Function] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[bool] | Omit = omit,
+        max_completion_tokens: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        metadata: Optional[Metadata] | Omit = omit,
+        modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        parallel_tool_calls: bool | Omit = omit,
+        prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        prompt_cache_key: str | Omit = omit,
+        prompt_cache_retention: Optional[Literal["in-memory", "24h"]] | Omit = omit,
+        reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
+        safety_identifier: str | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        store: Optional[bool] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        tool_choice: ChatCompletionToolChoiceOptionParam | Omit = omit,
+        tools: Iterable[ChatCompletionToolUnionParam] | Omit = omit,
+        top_logprobs: Optional[int] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | Omit = omit,
+        verbosity: Optional[Literal["low", "medium", "high"]] | Omit = omit,
+        web_search_options: completion_create_params.WebSearchOptions | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ChatCompletionStreamManager[ResponseFormatT]:
+        """Wrapper over the `client.chat.completions.create(stream=True)` method that provides a more granular event API
+        and automatic accumulation of each delta.
+
+        This also supports all of the parsing utilities that `.parse()` does.
+
+        Unlike `.create(stream=True)`, the `.stream()` method requires usage within a context manager to prevent accidental leakage of the response:
+
+        ```py
+        with client.chat.completions.stream(
+            model="gpt-4o-2024-08-06",
+            messages=[...],
+        ) as stream:
+            for event in stream:
+                if event.type == "content.delta":
+                    print(event.delta, flush=True, end="")
+        ```
+
+        When the context manager is entered, a `ChatCompletionStream` instance is returned which, like `.create(stream=True)` is an iterator. The full list of events that are yielded by the iterator are outlined in [these docs](https://github.com/openai/openai-python/blob/main/helpers.md#chat-completions-events).
+
+        When the context manager exits, the response will be closed, however the `stream` instance is still available outside
+        the context manager.
+        """
+        extra_headers = {
+            "X-Stainless-Helper-Method": "chat.completions.stream",
+            **(extra_headers or {}),
+        }
+
+        api_request: partial[Stream[ChatCompletionChunk]] = partial(
+            self.create,
+            messages=messages,
+            model=model,
+            audio=audio,
+            stream=True,
+            response_format=_type_to_response_format(response_format),
+            frequency_penalty=frequency_penalty,
+            function_call=function_call,
+            functions=functions,
+            logit_bias=logit_bias,
+            logprobs=logprobs,
+            max_completion_tokens=max_completion_tokens,
+            max_tokens=max_tokens,
+            metadata=metadata,
+            modalities=modalities,
+            n=n,
+            parallel_tool_calls=parallel_tool_calls,
+            prediction=prediction,
+            presence_penalty=presence_penalty,
+            prompt_cache_key=prompt_cache_key,
+            prompt_cache_retention=prompt_cache_retention,
+            reasoning_effort=reasoning_effort,
+            safety_identifier=safety_identifier,
+            seed=seed,
+            service_tier=service_tier,
+            store=store,
+            stop=stop,
+            stream_options=stream_options,
+            temperature=temperature,
+            tool_choice=tool_choice,
+            tools=tools,
+            top_logprobs=top_logprobs,
+            top_p=top_p,
+            user=user,
+            verbosity=verbosity,
+            web_search_options=web_search_options,
+            extra_headers=extra_headers,
+            extra_query=extra_query,
+            extra_body=extra_body,
+            timeout=timeout,
+        )
+        return ChatCompletionStreamManager(
+            api_request,
+            response_format=response_format,
+            input_tools=tools,
+        )
+
+
+class AsyncCompletions(AsyncAPIResource):
+    @cached_property
+    def messages(self) -> AsyncMessages:
+        return AsyncMessages(self._client)
+
+    @cached_property
+    def with_raw_response(self) -> AsyncCompletionsWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/openai/openai-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncCompletionsWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncCompletionsWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/openai/openai-python#with_streaming_response
+        """
+        return AsyncCompletionsWithStreamingResponse(self)
+
+    async def parse(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: Union[str, ChatModel],
+        audio: Optional[ChatCompletionAudioParam] | Omit = omit,
+        response_format: type[ResponseFormatT] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        function_call: completion_create_params.FunctionCall | Omit = omit,
+        functions: Iterable[completion_create_params.Function] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[bool] | Omit = omit,
+        max_completion_tokens: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        metadata: Optional[Metadata] | Omit = omit,
+        modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        parallel_tool_calls: bool | Omit = omit,
+        prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        prompt_cache_key: str | Omit = omit,
+        prompt_cache_retention: Optional[Literal["in-memory", "24h"]] | Omit = omit,
+        reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
+        safety_identifier: str | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        store: Optional[bool] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        tool_choice: ChatCompletionToolChoiceOptionParam | Omit = omit,
+        tools: Iterable[ChatCompletionToolUnionParam] | Omit = omit,
+        top_logprobs: Optional[int] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | Omit = omit,
+        verbosity: Optional[Literal["low", "medium", "high"]] | Omit = omit,
+        web_search_options: completion_create_params.WebSearchOptions | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ParsedChatCompletion[ResponseFormatT]:
+        """Wrapper over the `client.chat.completions.create()` method that provides richer integrations with Python specific types
+        & returns a `ParsedChatCompletion` object, which is a subclass of the standard `ChatCompletion` class.
+
+        You can pass a pydantic model to this method and it will automatically convert the model
+        into a JSON schema, send it to the API and parse the response content back into the given model.
+
+        This method will also automatically parse `function` tool calls if:
+        - You use the `openai.pydantic_function_tool()` helper method
+        - You mark your tool schema with `"strict": True`
+
+        Example usage:
+        ```py
+        from pydantic import BaseModel
+        from openai import AsyncOpenAI
+
+
+        class Step(BaseModel):
+            explanation: str
+            output: str
+
+
+        class MathResponse(BaseModel):
+            steps: List[Step]
+            final_answer: str
+
+
+        client = AsyncOpenAI()
+        completion = await client.chat.completions.parse(
+            model="gpt-4o-2024-08-06",
+            messages=[
+                {"role": "system", "content": "You are a helpful math tutor."},
+                {"role": "user", "content": "solve 8x + 31 = 2"},
+            ],
+            response_format=MathResponse,
+        )
+
+        message = completion.choices[0].message
+        if message.parsed:
+            print(message.parsed.steps)
+            print("answer: ", message.parsed.final_answer)
+        ```
+        """
+        _validate_input_tools(tools)
+
+        extra_headers = {
+            "X-Stainless-Helper-Method": "chat.completions.parse",
+            **(extra_headers or {}),
+        }
+
+        def parser(raw_completion: ChatCompletion) -> ParsedChatCompletion[ResponseFormatT]:
+            return _parse_chat_completion(
+                response_format=response_format,
+                chat_completion=raw_completion,
+                input_tools=tools,
+            )
+
+        return await self._post(
+            "/chat/completions",
+            body=await async_maybe_transform(
+                {
+                    "messages": messages,
+                    "model": model,
+                    "audio": audio,
+                    "frequency_penalty": frequency_penalty,
+                    "function_call": function_call,
+                    "functions": functions,
+                    "logit_bias": logit_bias,
+                    "logprobs": logprobs,
+                    "max_completion_tokens": max_completion_tokens,
+                    "max_tokens": max_tokens,
+                    "metadata": metadata,
+                    "modalities": modalities,
+                    "n": n,
+                    "parallel_tool_calls": parallel_tool_calls,
+                    "prediction": prediction,
+                    "presence_penalty": presence_penalty,
+                    "prompt_cache_key": prompt_cache_key,
+                    "prompt_cache_retention": prompt_cache_retention,
+                    "reasoning_effort": reasoning_effort,
+                    "response_format": _type_to_response_format(response_format),
+                    "safety_identifier": safety_identifier,
+                    "seed": seed,
+                    "service_tier": service_tier,
+                    "store": store,
+                    "stop": stop,
+                    "stream": False,
+                    "stream_options": stream_options,
+                    "temperature": temperature,
+                    "tool_choice": tool_choice,
+                    "tools": tools,
+                    "top_logprobs": top_logprobs,
+                    "top_p": top_p,
+                    "user": user,
+                    "verbosity": verbosity,
+                    "web_search_options": web_search_options,
+                },
+                completion_create_params.CompletionCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                post_parser=parser,
+            ),
+            # we turn the `ChatCompletion` instance into a `ParsedChatCompletion`
+            # in the `parser` function above
+            cast_to=cast(Type[ParsedChatCompletion[ResponseFormatT]], ChatCompletion),
+            stream=False,
+        )
+
+    @overload
+    async def create(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: Union[str, ChatModel],
+        audio: Optional[ChatCompletionAudioParam] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        function_call: completion_create_params.FunctionCall | Omit = omit,
+        functions: Iterable[completion_create_params.Function] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[bool] | Omit = omit,
+        max_completion_tokens: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        metadata: Optional[Metadata] | Omit = omit,
+        modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        parallel_tool_calls: bool | Omit = omit,
+        prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        prompt_cache_key: str | Omit = omit,
+        prompt_cache_retention: Optional[Literal["in-memory", "24h"]] | Omit = omit,
+        reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
+        response_format: completion_create_params.ResponseFormat | Omit = omit,
+        safety_identifier: str | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        store: Optional[bool] | Omit = omit,
+        stream: Optional[Literal[False]] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        tool_choice: ChatCompletionToolChoiceOptionParam | Omit = omit,
+        tools: Iterable[ChatCompletionToolUnionParam] | Omit = omit,
+        top_logprobs: Optional[int] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | Omit = omit,
+        verbosity: Optional[Literal["low", "medium", "high"]] | Omit = omit,
+        web_search_options: completion_create_params.WebSearchOptions | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ChatCompletion:
+        """
+        **Starting a new project?** We recommend trying
+        [Responses](https://platform.openai.com/docs/api-reference/responses) to take
+        advantage of the latest OpenAI platform features. Compare
+        [Chat Completions with Responses](https://platform.openai.com/docs/guides/responses-vs-chat-completions?api-mode=responses).
+
+        ---
+
+        Creates a model response for the given chat conversation. Learn more in the
+        [text generation](https://platform.openai.com/docs/guides/text-generation),
+        [vision](https://platform.openai.com/docs/guides/vision), and
+        [audio](https://platform.openai.com/docs/guides/audio) guides.
+
+        Parameter support can differ depending on the model used to generate the
+        response, particularly for newer reasoning models. Parameters that are only
+        supported for reasoning models are noted below. For the current state of
+        unsupported parameters in reasoning models,
+        [refer to the reasoning guide](https://platform.openai.com/docs/guides/reasoning).
+
+        Args:
+          messages: A list of messages comprising the conversation so far. Depending on the
+              [model](https://platform.openai.com/docs/models) you use, different message
+              types (modalities) are supported, like
+              [text](https://platform.openai.com/docs/guides/text-generation),
+              [images](https://platform.openai.com/docs/guides/vision), and
+              [audio](https://platform.openai.com/docs/guides/audio).
+
+          model: 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
+              [model guide](https://platform.openai.com/docs/models) to browse and compare
+              available models.
+
+          audio: Parameters for audio output. Required when audio output is requested with
+              `modalities: ["audio"]`.
+              [Learn more](https://platform.openai.com/docs/guides/audio).
+
+          frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their
+              existing frequency in the text so far, decreasing the model's likelihood to
+              repeat the same line verbatim.
+
+          function_call: Deprecated in favor of `tool_choice`.
+
+              Controls which (if any) function is called by the model.
+
+              `none` means the model will not call a function and instead generates a message.
+
+              `auto` means the model can pick between generating a message or calling a
+              function.
+
+              Specifying a particular function via `{"name": "my_function"}` forces the model
+              to call that function.
+
+              `none` is the default when no functions are present. `auto` is the default if
+              functions are present.
+
+          functions: Deprecated in favor of `tools`.
+
+              A list of functions the model may generate JSON inputs for.
+
+          logit_bias: Modify the likelihood of specified tokens appearing in the completion.
+
+              Accepts a JSON object that maps tokens (specified by their token ID in the
+              tokenizer) to an associated bias value from -100 to 100. Mathematically, the
+              bias is added to the logits generated by the model prior to sampling. The exact
+              effect will vary per model, but values between -1 and 1 should decrease or
+              increase likelihood of selection; values like -100 or 100 should result in a ban
+              or exclusive selection of the relevant token.
+
+          logprobs: Whether to return log probabilities of the output tokens or not. If true,
+              returns the log probabilities of each output token returned in the `content` of
+              `message`.
+
+          max_completion_tokens: An upper bound for the number of tokens that can be generated for a completion,
+              including visible output tokens and
+              [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
+
+          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat
+              completion. This value can be used to control
+              [costs](https://openai.com/api/pricing/) for text generated via API.
+
+              This value is now deprecated in favor of `max_completion_tokens`, and is not
+              compatible with
+              [o-series models](https://platform.openai.com/docs/guides/reasoning).
+
+          metadata: Set of 16 key-value pairs that can be attached to an object. This can be useful
+              for storing additional information about the object in a structured format, and
+              querying for objects via API or the dashboard.
+
+              Keys are strings with a maximum length of 64 characters. Values are strings with
+              a maximum length of 512 characters.
+
+          modalities: Output types that you would like the model to generate. Most models are capable
+              of generating text, which is the default:
+
+              `["text"]`
+
+              The `gpt-4o-audio-preview` model can also be used to
+              [generate audio](https://platform.openai.com/docs/guides/audio). To request that
+              this model generate both text and audio responses, you can use:
+
+              `["text", "audio"]`
+
+          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.
+
+          parallel_tool_calls: Whether to enable
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
+              during tool use.
+
+          prediction: Static predicted output content, such as the content of a text file that is
+              being regenerated.
+
+          presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
+              whether they appear in the text so far, increasing the model's likelihood to
+              talk about new topics.
+
+          prompt_cache_key: Used by OpenAI to cache responses for similar requests to optimize your cache
+              hit rates. Replaces the `user` field.
+              [Learn more](https://platform.openai.com/docs/guides/prompt-caching).
+
+          prompt_cache_retention: The retention policy for the prompt cache. Set to `24h` to enable extended
+              prompt caching, which keeps cached prefixes active for longer, up to a maximum
+              of 24 hours.
+              [Learn more](https://platform.openai.com/docs/guides/prompt-caching#prompt-cache-retention).
+
+          reasoning_effort: Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
+              reasoning effort can result in faster responses and fewer tokens used on
+              reasoning in a response.
+
+              - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
+                reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
+                calls are supported for all reasoning values in gpt-5.1.
+              - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
+                support `none`.
+              - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+
+          response_format: An object specifying the format that the model must output.
+
+              Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
+              [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
+
+              Setting to `{ "type": "json_object" }` enables the older JSON mode, which
+              ensures the message the model generates is valid JSON. Using `json_schema` is
+              preferred for models that support it.
+
+          safety_identifier: A stable identifier used to help detect users of your application that may be
+              violating OpenAI's usage policies. The IDs should be a string that uniquely
+              identifies each user. We recommend hashing their username or email address, in
+              order to avoid sending us any identifying information.
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
+
+          seed: This feature is in Beta. If specified, our system will make a best effort to
+              sample deterministically, such that repeated requests with the same `seed` and
+              parameters should return the same result. Determinism is not guaranteed, and you
+              should refer to the `system_fingerprint` response parameter to monitor changes
+              in the backend.
+
+          service_tier: Specifies the processing type used for serving the request.
+
+              - If set to 'auto', then the request will be processed with the service tier
+                configured in the Project settings. Unless otherwise configured, the Project
+                will use 'default'.
+              - If set to 'default', then the request will be processed with the standard
+                pricing and performance for the selected model.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+                '[priority](https://openai.com/api-priority-processing/)', then the request
+                will be processed with the corresponding service tier.
+              - When not set, the default behavior is 'auto'.
+
+              When the `service_tier` parameter is set, the response body will include the
+              `service_tier` value based on the processing mode actually used to serve the
+              request. This response value may be different from the value set in the
+              parameter.
+
+          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.
+
+          store: Whether or not to store the output of this chat completion request for use in
+              our [model distillation](https://platform.openai.com/docs/guides/distillation)
+              or [evals](https://platform.openai.com/docs/guides/evals) products.
+
+              Supports text and image inputs. Note: image inputs over 8MB will be dropped.
+
+          stream: If set to true, the model response data will be streamed to the client as it is
+              generated using
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
+              See the
+              [Streaming section below](https://platform.openai.com/docs/api-reference/chat/streaming)
+              for more information, along with the
+              [streaming responses](https://platform.openai.com/docs/guides/streaming-responses)
+              guide for more information on how to handle the streaming events.
+
+          stream_options: Options for streaming response. Only set this when you set `stream: true`.
+
+          temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
+              make the output more random, while lower values like 0.2 will make it more
+              focused and deterministic. We generally recommend altering this or `top_p` but
+              not both.
+
+          tool_choice: Controls which (if any) tool is called by the model. `none` means the model will
+              not call any tool and instead generates a message. `auto` means the model can
+              pick between generating a message or calling one or more tools. `required` means
+              the model must call one or more tools. Specifying a particular tool via
+              `{"type": "function", "function": {"name": "my_function"}}` forces the model to
+              call that tool.
+
+              `none` is the default when no tools are present. `auto` is the default if tools
+              are present.
+
+          tools: A list of tools the model may call. You can provide either
+              [custom tools](https://platform.openai.com/docs/guides/function-calling#custom-tools)
+              or [function tools](https://platform.openai.com/docs/guides/function-calling).
+
+          top_logprobs: An integer between 0 and 20 specifying the number of most likely tokens to
+              return at each token position, each with an associated log probability.
+              `logprobs` must be set to `true` if this parameter is used.
+
+          top_p: An alternative to sampling with temperature, called nucleus sampling, where the
+              model considers the results of the tokens with top_p probability mass. So 0.1
+              means only the tokens comprising the top 10% probability mass are considered.
+
+              We generally recommend altering this or `temperature` but not both.
+
+          user: This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use
+              `prompt_cache_key` instead to maintain caching optimizations. A stable
+              identifier for your end-users. Used to boost cache hit rates by better bucketing
+              similar requests and to help OpenAI detect and prevent abuse.
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
+
+          verbosity: Constrains the verbosity of the model's response. Lower values will result in
+              more concise responses, while higher values will result in more verbose
+              responses. Currently supported values are `low`, `medium`, and `high`.
+
+          web_search_options: This tool searches the web for relevant results to use in a response. Learn more
+              about the
+              [web search tool](https://platform.openai.com/docs/guides/tools-web-search?api-mode=chat).
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        ...
+
+    @overload
+    async def create(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: Union[str, ChatModel],
+        stream: Literal[True],
+        audio: Optional[ChatCompletionAudioParam] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        function_call: completion_create_params.FunctionCall | Omit = omit,
+        functions: Iterable[completion_create_params.Function] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[bool] | Omit = omit,
+        max_completion_tokens: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        metadata: Optional[Metadata] | Omit = omit,
+        modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        parallel_tool_calls: bool | Omit = omit,
+        prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        prompt_cache_key: str | Omit = omit,
+        prompt_cache_retention: Optional[Literal["in-memory", "24h"]] | Omit = omit,
+        reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
+        response_format: completion_create_params.ResponseFormat | Omit = omit,
+        safety_identifier: str | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        store: Optional[bool] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        tool_choice: ChatCompletionToolChoiceOptionParam | Omit = omit,
+        tools: Iterable[ChatCompletionToolUnionParam] | Omit = omit,
+        top_logprobs: Optional[int] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | Omit = omit,
+        verbosity: Optional[Literal["low", "medium", "high"]] | Omit = omit,
+        web_search_options: completion_create_params.WebSearchOptions | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> AsyncStream[ChatCompletionChunk]:
+        """
+        **Starting a new project?** We recommend trying
+        [Responses](https://platform.openai.com/docs/api-reference/responses) to take
+        advantage of the latest OpenAI platform features. Compare
+        [Chat Completions with Responses](https://platform.openai.com/docs/guides/responses-vs-chat-completions?api-mode=responses).
+
+        ---
+
+        Creates a model response for the given chat conversation. Learn more in the
+        [text generation](https://platform.openai.com/docs/guides/text-generation),
+        [vision](https://platform.openai.com/docs/guides/vision), and
+        [audio](https://platform.openai.com/docs/guides/audio) guides.
+
+        Parameter support can differ depending on the model used to generate the
+        response, particularly for newer reasoning models. Parameters that are only
+        supported for reasoning models are noted below. For the current state of
+        unsupported parameters in reasoning models,
+        [refer to the reasoning guide](https://platform.openai.com/docs/guides/reasoning).
+
+        Args:
+          messages: A list of messages comprising the conversation so far. Depending on the
+              [model](https://platform.openai.com/docs/models) you use, different message
+              types (modalities) are supported, like
+              [text](https://platform.openai.com/docs/guides/text-generation),
+              [images](https://platform.openai.com/docs/guides/vision), and
+              [audio](https://platform.openai.com/docs/guides/audio).
+
+          model: 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
+              [model guide](https://platform.openai.com/docs/models) to browse and compare
+              available models.
+
+          stream: If set to true, the model response data will be streamed to the client as it is
+              generated using
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
+              See the
+              [Streaming section below](https://platform.openai.com/docs/api-reference/chat/streaming)
+              for more information, along with the
+              [streaming responses](https://platform.openai.com/docs/guides/streaming-responses)
+              guide for more information on how to handle the streaming events.
+
+          audio: Parameters for audio output. Required when audio output is requested with
+              `modalities: ["audio"]`.
+              [Learn more](https://platform.openai.com/docs/guides/audio).
+
+          frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their
+              existing frequency in the text so far, decreasing the model's likelihood to
+              repeat the same line verbatim.
+
+          function_call: Deprecated in favor of `tool_choice`.
+
+              Controls which (if any) function is called by the model.
+
+              `none` means the model will not call a function and instead generates a message.
+
+              `auto` means the model can pick between generating a message or calling a
+              function.
+
+              Specifying a particular function via `{"name": "my_function"}` forces the model
+              to call that function.
+
+              `none` is the default when no functions are present. `auto` is the default if
+              functions are present.
+
+          functions: Deprecated in favor of `tools`.
+
+              A list of functions the model may generate JSON inputs for.
+
+          logit_bias: Modify the likelihood of specified tokens appearing in the completion.
+
+              Accepts a JSON object that maps tokens (specified by their token ID in the
+              tokenizer) to an associated bias value from -100 to 100. Mathematically, the
+              bias is added to the logits generated by the model prior to sampling. The exact
+              effect will vary per model, but values between -1 and 1 should decrease or
+              increase likelihood of selection; values like -100 or 100 should result in a ban
+              or exclusive selection of the relevant token.
+
+          logprobs: Whether to return log probabilities of the output tokens or not. If true,
+              returns the log probabilities of each output token returned in the `content` of
+              `message`.
+
+          max_completion_tokens: An upper bound for the number of tokens that can be generated for a completion,
+              including visible output tokens and
+              [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
+
+          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat
+              completion. This value can be used to control
+              [costs](https://openai.com/api/pricing/) for text generated via API.
+
+              This value is now deprecated in favor of `max_completion_tokens`, and is not
+              compatible with
+              [o-series models](https://platform.openai.com/docs/guides/reasoning).
+
+          metadata: Set of 16 key-value pairs that can be attached to an object. This can be useful
+              for storing additional information about the object in a structured format, and
+              querying for objects via API or the dashboard.
+
+              Keys are strings with a maximum length of 64 characters. Values are strings with
+              a maximum length of 512 characters.
+
+          modalities: Output types that you would like the model to generate. Most models are capable
+              of generating text, which is the default:
+
+              `["text"]`
+
+              The `gpt-4o-audio-preview` model can also be used to
+              [generate audio](https://platform.openai.com/docs/guides/audio). To request that
+              this model generate both text and audio responses, you can use:
+
+              `["text", "audio"]`
+
+          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.
+
+          parallel_tool_calls: Whether to enable
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
+              during tool use.
+
+          prediction: Static predicted output content, such as the content of a text file that is
+              being regenerated.
+
+          presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
+              whether they appear in the text so far, increasing the model's likelihood to
+              talk about new topics.
+
+          prompt_cache_key: Used by OpenAI to cache responses for similar requests to optimize your cache
+              hit rates. Replaces the `user` field.
+              [Learn more](https://platform.openai.com/docs/guides/prompt-caching).
+
+          prompt_cache_retention: The retention policy for the prompt cache. Set to `24h` to enable extended
+              prompt caching, which keeps cached prefixes active for longer, up to a maximum
+              of 24 hours.
+              [Learn more](https://platform.openai.com/docs/guides/prompt-caching#prompt-cache-retention).
+
+          reasoning_effort: Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
+              reasoning effort can result in faster responses and fewer tokens used on
+              reasoning in a response.
+
+              - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
+                reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
+                calls are supported for all reasoning values in gpt-5.1.
+              - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
+                support `none`.
+              - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+
+          response_format: An object specifying the format that the model must output.
+
+              Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
+              [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
+
+              Setting to `{ "type": "json_object" }` enables the older JSON mode, which
+              ensures the message the model generates is valid JSON. Using `json_schema` is
+              preferred for models that support it.
+
+          safety_identifier: A stable identifier used to help detect users of your application that may be
+              violating OpenAI's usage policies. The IDs should be a string that uniquely
+              identifies each user. We recommend hashing their username or email address, in
+              order to avoid sending us any identifying information.
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
+
+          seed: This feature is in Beta. If specified, our system will make a best effort to
+              sample deterministically, such that repeated requests with the same `seed` and
+              parameters should return the same result. Determinism is not guaranteed, and you
+              should refer to the `system_fingerprint` response parameter to monitor changes
+              in the backend.
+
+          service_tier: Specifies the processing type used for serving the request.
+
+              - If set to 'auto', then the request will be processed with the service tier
+                configured in the Project settings. Unless otherwise configured, the Project
+                will use 'default'.
+              - If set to 'default', then the request will be processed with the standard
+                pricing and performance for the selected model.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+                '[priority](https://openai.com/api-priority-processing/)', then the request
+                will be processed with the corresponding service tier.
+              - When not set, the default behavior is 'auto'.
+
+              When the `service_tier` parameter is set, the response body will include the
+              `service_tier` value based on the processing mode actually used to serve the
+              request. This response value may be different from the value set in the
+              parameter.
+
+          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.
+
+          store: Whether or not to store the output of this chat completion request for use in
+              our [model distillation](https://platform.openai.com/docs/guides/distillation)
+              or [evals](https://platform.openai.com/docs/guides/evals) products.
+
+              Supports text and image inputs. Note: image inputs over 8MB will be dropped.
+
+          stream_options: Options for streaming response. Only set this when you set `stream: true`.
+
+          temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
+              make the output more random, while lower values like 0.2 will make it more
+              focused and deterministic. We generally recommend altering this or `top_p` but
+              not both.
+
+          tool_choice: Controls which (if any) tool is called by the model. `none` means the model will
+              not call any tool and instead generates a message. `auto` means the model can
+              pick between generating a message or calling one or more tools. `required` means
+              the model must call one or more tools. Specifying a particular tool via
+              `{"type": "function", "function": {"name": "my_function"}}` forces the model to
+              call that tool.
+
+              `none` is the default when no tools are present. `auto` is the default if tools
+              are present.
+
+          tools: A list of tools the model may call. You can provide either
+              [custom tools](https://platform.openai.com/docs/guides/function-calling#custom-tools)
+              or [function tools](https://platform.openai.com/docs/guides/function-calling).
+
+          top_logprobs: An integer between 0 and 20 specifying the number of most likely tokens to
+              return at each token position, each with an associated log probability.
+              `logprobs` must be set to `true` if this parameter is used.
+
+          top_p: An alternative to sampling with temperature, called nucleus sampling, where the
+              model considers the results of the tokens with top_p probability mass. So 0.1
+              means only the tokens comprising the top 10% probability mass are considered.
+
+              We generally recommend altering this or `temperature` but not both.
+
+          user: This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use
+              `prompt_cache_key` instead to maintain caching optimizations. A stable
+              identifier for your end-users. Used to boost cache hit rates by better bucketing
+              similar requests and to help OpenAI detect and prevent abuse.
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
+
+          verbosity: Constrains the verbosity of the model's response. Lower values will result in
+              more concise responses, while higher values will result in more verbose
+              responses. Currently supported values are `low`, `medium`, and `high`.
+
+          web_search_options: This tool searches the web for relevant results to use in a response. Learn more
+              about the
+              [web search tool](https://platform.openai.com/docs/guides/tools-web-search?api-mode=chat).
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        ...
+
+    @overload
+    async def create(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: Union[str, ChatModel],
+        stream: bool,
+        audio: Optional[ChatCompletionAudioParam] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        function_call: completion_create_params.FunctionCall | Omit = omit,
+        functions: Iterable[completion_create_params.Function] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[bool] | Omit = omit,
+        max_completion_tokens: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        metadata: Optional[Metadata] | Omit = omit,
+        modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        parallel_tool_calls: bool | Omit = omit,
+        prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        prompt_cache_key: str | Omit = omit,
+        prompt_cache_retention: Optional[Literal["in-memory", "24h"]] | Omit = omit,
+        reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
+        response_format: completion_create_params.ResponseFormat | Omit = omit,
+        safety_identifier: str | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        store: Optional[bool] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        tool_choice: ChatCompletionToolChoiceOptionParam | Omit = omit,
+        tools: Iterable[ChatCompletionToolUnionParam] | Omit = omit,
+        top_logprobs: Optional[int] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | Omit = omit,
+        verbosity: Optional[Literal["low", "medium", "high"]] | Omit = omit,
+        web_search_options: completion_create_params.WebSearchOptions | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ChatCompletion | AsyncStream[ChatCompletionChunk]:
+        """
+        **Starting a new project?** We recommend trying
+        [Responses](https://platform.openai.com/docs/api-reference/responses) to take
+        advantage of the latest OpenAI platform features. Compare
+        [Chat Completions with Responses](https://platform.openai.com/docs/guides/responses-vs-chat-completions?api-mode=responses).
+
+        ---
+
+        Creates a model response for the given chat conversation. Learn more in the
+        [text generation](https://platform.openai.com/docs/guides/text-generation),
+        [vision](https://platform.openai.com/docs/guides/vision), and
+        [audio](https://platform.openai.com/docs/guides/audio) guides.
+
+        Parameter support can differ depending on the model used to generate the
+        response, particularly for newer reasoning models. Parameters that are only
+        supported for reasoning models are noted below. For the current state of
+        unsupported parameters in reasoning models,
+        [refer to the reasoning guide](https://platform.openai.com/docs/guides/reasoning).
+
+        Args:
+          messages: A list of messages comprising the conversation so far. Depending on the
+              [model](https://platform.openai.com/docs/models) you use, different message
+              types (modalities) are supported, like
+              [text](https://platform.openai.com/docs/guides/text-generation),
+              [images](https://platform.openai.com/docs/guides/vision), and
+              [audio](https://platform.openai.com/docs/guides/audio).
+
+          model: 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
+              [model guide](https://platform.openai.com/docs/models) to browse and compare
+              available models.
+
+          stream: If set to true, the model response data will be streamed to the client as it is
+              generated using
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
+              See the
+              [Streaming section below](https://platform.openai.com/docs/api-reference/chat/streaming)
+              for more information, along with the
+              [streaming responses](https://platform.openai.com/docs/guides/streaming-responses)
+              guide for more information on how to handle the streaming events.
+
+          audio: Parameters for audio output. Required when audio output is requested with
+              `modalities: ["audio"]`.
+              [Learn more](https://platform.openai.com/docs/guides/audio).
+
+          frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their
+              existing frequency in the text so far, decreasing the model's likelihood to
+              repeat the same line verbatim.
+
+          function_call: Deprecated in favor of `tool_choice`.
+
+              Controls which (if any) function is called by the model.
+
+              `none` means the model will not call a function and instead generates a message.
+
+              `auto` means the model can pick between generating a message or calling a
+              function.
+
+              Specifying a particular function via `{"name": "my_function"}` forces the model
+              to call that function.
+
+              `none` is the default when no functions are present. `auto` is the default if
+              functions are present.
+
+          functions: Deprecated in favor of `tools`.
+
+              A list of functions the model may generate JSON inputs for.
+
+          logit_bias: Modify the likelihood of specified tokens appearing in the completion.
+
+              Accepts a JSON object that maps tokens (specified by their token ID in the
+              tokenizer) to an associated bias value from -100 to 100. Mathematically, the
+              bias is added to the logits generated by the model prior to sampling. The exact
+              effect will vary per model, but values between -1 and 1 should decrease or
+              increase likelihood of selection; values like -100 or 100 should result in a ban
+              or exclusive selection of the relevant token.
+
+          logprobs: Whether to return log probabilities of the output tokens or not. If true,
+              returns the log probabilities of each output token returned in the `content` of
+              `message`.
+
+          max_completion_tokens: An upper bound for the number of tokens that can be generated for a completion,
+              including visible output tokens and
+              [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
+
+          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the chat
+              completion. This value can be used to control
+              [costs](https://openai.com/api/pricing/) for text generated via API.
+
+              This value is now deprecated in favor of `max_completion_tokens`, and is not
+              compatible with
+              [o-series models](https://platform.openai.com/docs/guides/reasoning).
+
+          metadata: Set of 16 key-value pairs that can be attached to an object. This can be useful
+              for storing additional information about the object in a structured format, and
+              querying for objects via API or the dashboard.
+
+              Keys are strings with a maximum length of 64 characters. Values are strings with
+              a maximum length of 512 characters.
+
+          modalities: Output types that you would like the model to generate. Most models are capable
+              of generating text, which is the default:
+
+              `["text"]`
+
+              The `gpt-4o-audio-preview` model can also be used to
+              [generate audio](https://platform.openai.com/docs/guides/audio). To request that
+              this model generate both text and audio responses, you can use:
+
+              `["text", "audio"]`
+
+          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.
+
+          parallel_tool_calls: Whether to enable
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
+              during tool use.
+
+          prediction: Static predicted output content, such as the content of a text file that is
+              being regenerated.
+
+          presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
+              whether they appear in the text so far, increasing the model's likelihood to
+              talk about new topics.
+
+          prompt_cache_key: Used by OpenAI to cache responses for similar requests to optimize your cache
+              hit rates. Replaces the `user` field.
+              [Learn more](https://platform.openai.com/docs/guides/prompt-caching).
+
+          prompt_cache_retention: The retention policy for the prompt cache. Set to `24h` to enable extended
+              prompt caching, which keeps cached prefixes active for longer, up to a maximum
+              of 24 hours.
+              [Learn more](https://platform.openai.com/docs/guides/prompt-caching#prompt-cache-retention).
+
+          reasoning_effort: Constrains effort on reasoning for
+              [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
+              reasoning effort can result in faster responses and fewer tokens used on
+              reasoning in a response.
+
+              - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
+                reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
+                calls are supported for all reasoning values in gpt-5.1.
+              - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
+                support `none`.
+              - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+
+          response_format: An object specifying the format that the model must output.
+
+              Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
+              Outputs which ensures the model will match your supplied JSON schema. Learn more
+              in the
+              [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
+
+              Setting to `{ "type": "json_object" }` enables the older JSON mode, which
+              ensures the message the model generates is valid JSON. Using `json_schema` is
+              preferred for models that support it.
+
+          safety_identifier: A stable identifier used to help detect users of your application that may be
+              violating OpenAI's usage policies. The IDs should be a string that uniquely
+              identifies each user. We recommend hashing their username or email address, in
+              order to avoid sending us any identifying information.
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
+
+          seed: This feature is in Beta. If specified, our system will make a best effort to
+              sample deterministically, such that repeated requests with the same `seed` and
+              parameters should return the same result. Determinism is not guaranteed, and you
+              should refer to the `system_fingerprint` response parameter to monitor changes
+              in the backend.
+
+          service_tier: Specifies the processing type used for serving the request.
+
+              - If set to 'auto', then the request will be processed with the service tier
+                configured in the Project settings. Unless otherwise configured, the Project
+                will use 'default'.
+              - If set to 'default', then the request will be processed with the standard
+                pricing and performance for the selected model.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+                '[priority](https://openai.com/api-priority-processing/)', then the request
+                will be processed with the corresponding service tier.
+              - When not set, the default behavior is 'auto'.
+
+              When the `service_tier` parameter is set, the response body will include the
+              `service_tier` value based on the processing mode actually used to serve the
+              request. This response value may be different from the value set in the
+              parameter.
+
+          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.
+
+          store: Whether or not to store the output of this chat completion request for use in
+              our [model distillation](https://platform.openai.com/docs/guides/distillation)
+              or [evals](https://platform.openai.com/docs/guides/evals) products.
+
+              Supports text and image inputs. Note: image inputs over 8MB will be dropped.
+
+          stream_options: Options for streaming response. Only set this when you set `stream: true`.
+
+          temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
+              make the output more random, while lower values like 0.2 will make it more
+              focused and deterministic. We generally recommend altering this or `top_p` but
+              not both.
+
+          tool_choice: Controls which (if any) tool is called by the model. `none` means the model will
+              not call any tool and instead generates a message. `auto` means the model can
+              pick between generating a message or calling one or more tools. `required` means
+              the model must call one or more tools. Specifying a particular tool via
+              `{"type": "function", "function": {"name": "my_function"}}` forces the model to
+              call that tool.
+
+              `none` is the default when no tools are present. `auto` is the default if tools
+              are present.
+
+          tools: A list of tools the model may call. You can provide either
+              [custom tools](https://platform.openai.com/docs/guides/function-calling#custom-tools)
+              or [function tools](https://platform.openai.com/docs/guides/function-calling).
+
+          top_logprobs: An integer between 0 and 20 specifying the number of most likely tokens to
+              return at each token position, each with an associated log probability.
+              `logprobs` must be set to `true` if this parameter is used.
+
+          top_p: An alternative to sampling with temperature, called nucleus sampling, where the
+              model considers the results of the tokens with top_p probability mass. So 0.1
+              means only the tokens comprising the top 10% probability mass are considered.
+
+              We generally recommend altering this or `temperature` but not both.
+
+          user: This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use
+              `prompt_cache_key` instead to maintain caching optimizations. A stable
+              identifier for your end-users. Used to boost cache hit rates by better bucketing
+              similar requests and to help OpenAI detect and prevent abuse.
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
+
+          verbosity: Constrains the verbosity of the model's response. Lower values will result in
+              more concise responses, while higher values will result in more verbose
+              responses. Currently supported values are `low`, `medium`, and `high`.
+
+          web_search_options: This tool searches the web for relevant results to use in a response. Learn more
+              about the
+              [web search tool](https://platform.openai.com/docs/guides/tools-web-search?api-mode=chat).
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        ...
+
+    @required_args(["messages", "model"], ["messages", "model", "stream"])
+    async def create(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: Union[str, ChatModel],
+        audio: Optional[ChatCompletionAudioParam] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        function_call: completion_create_params.FunctionCall | Omit = omit,
+        functions: Iterable[completion_create_params.Function] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[bool] | Omit = omit,
+        max_completion_tokens: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        metadata: Optional[Metadata] | Omit = omit,
+        modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        parallel_tool_calls: bool | Omit = omit,
+        prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        prompt_cache_key: str | Omit = omit,
+        prompt_cache_retention: Optional[Literal["in-memory", "24h"]] | Omit = omit,
+        reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
+        response_format: completion_create_params.ResponseFormat | Omit = omit,
+        safety_identifier: str | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        store: Optional[bool] | Omit = omit,
+        stream: Optional[Literal[False]] | Literal[True] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        tool_choice: ChatCompletionToolChoiceOptionParam | Omit = omit,
+        tools: Iterable[ChatCompletionToolUnionParam] | Omit = omit,
+        top_logprobs: Optional[int] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | Omit = omit,
+        verbosity: Optional[Literal["low", "medium", "high"]] | Omit = omit,
+        web_search_options: completion_create_params.WebSearchOptions | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ChatCompletion | AsyncStream[ChatCompletionChunk]:
+        validate_response_format(response_format)
+        return await self._post(
+            "/chat/completions",
+            body=await async_maybe_transform(
+                {
+                    "messages": messages,
+                    "model": model,
+                    "audio": audio,
+                    "frequency_penalty": frequency_penalty,
+                    "function_call": function_call,
+                    "functions": functions,
+                    "logit_bias": logit_bias,
+                    "logprobs": logprobs,
+                    "max_completion_tokens": max_completion_tokens,
+                    "max_tokens": max_tokens,
+                    "metadata": metadata,
+                    "modalities": modalities,
+                    "n": n,
+                    "parallel_tool_calls": parallel_tool_calls,
+                    "prediction": prediction,
+                    "presence_penalty": presence_penalty,
+                    "prompt_cache_key": prompt_cache_key,
+                    "prompt_cache_retention": prompt_cache_retention,
+                    "reasoning_effort": reasoning_effort,
+                    "response_format": response_format,
+                    "safety_identifier": safety_identifier,
+                    "seed": seed,
+                    "service_tier": service_tier,
+                    "stop": stop,
+                    "store": store,
+                    "stream": stream,
+                    "stream_options": stream_options,
+                    "temperature": temperature,
+                    "tool_choice": tool_choice,
+                    "tools": tools,
+                    "top_logprobs": top_logprobs,
+                    "top_p": top_p,
+                    "user": user,
+                    "verbosity": verbosity,
+                    "web_search_options": web_search_options,
+                },
+                completion_create_params.CompletionCreateParamsStreaming
+                if stream
+                else completion_create_params.CompletionCreateParamsNonStreaming,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ChatCompletion,
+            stream=stream or False,
+            stream_cls=AsyncStream[ChatCompletionChunk],
+        )
+
+    async def retrieve(
+        self,
+        completion_id: str,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ChatCompletion:
+        """Get a stored chat completion.
+
+        Only Chat Completions that have been created with
+        the `store` parameter set to `true` will be returned.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not completion_id:
+            raise ValueError(f"Expected a non-empty value for `completion_id` but received {completion_id!r}")
+        return await self._get(
+            f"/chat/completions/{completion_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ChatCompletion,
+        )
+
+    async def update(
+        self,
+        completion_id: str,
+        *,
+        metadata: Optional[Metadata],
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ChatCompletion:
+        """Modify a stored chat completion.
+
+        Only Chat Completions that have been created
+        with the `store` parameter set to `true` can be modified. Currently, the only
+        supported modification is to update the `metadata` field.
+
+        Args:
+          metadata: Set of 16 key-value pairs that can be attached to an object. This can be useful
+              for storing additional information about the object in a structured format, and
+              querying for objects via API or the dashboard.
+
+              Keys are strings with a maximum length of 64 characters. Values are strings with
+              a maximum length of 512 characters.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not completion_id:
+            raise ValueError(f"Expected a non-empty value for `completion_id` but received {completion_id!r}")
+        return await self._post(
+            f"/chat/completions/{completion_id}",
+            body=await async_maybe_transform({"metadata": metadata}, completion_update_params.CompletionUpdateParams),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ChatCompletion,
+        )
+
+    def list(
+        self,
+        *,
+        after: str | Omit = omit,
+        limit: int | Omit = omit,
+        metadata: Optional[Metadata] | Omit = omit,
+        model: str | Omit = omit,
+        order: Literal["asc", "desc"] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> AsyncPaginator[ChatCompletion, AsyncCursorPage[ChatCompletion]]:
+        """List stored Chat Completions.
+
+        Only Chat Completions that have been stored with
+        the `store` parameter set to `true` will be returned.
+
+        Args:
+          after: Identifier for the last chat completion from the previous pagination request.
+
+          limit: Number of Chat Completions to retrieve.
+
+          metadata: Set of 16 key-value pairs that can be attached to an object. This can be useful
+              for storing additional information about the object in a structured format, and
+              querying for objects via API or the dashboard.
+
+              Keys are strings with a maximum length of 64 characters. Values are strings with
+              a maximum length of 512 characters.
+
+          model: The model used to generate the Chat Completions.
+
+          order: Sort order for Chat Completions by timestamp. Use `asc` for ascending order or
+              `desc` for descending order. Defaults to `asc`.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        return self._get_api_list(
+            "/chat/completions",
+            page=AsyncCursorPage[ChatCompletion],
+            options=make_request_options(
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                query=maybe_transform(
+                    {
+                        "after": after,
+                        "limit": limit,
+                        "metadata": metadata,
+                        "model": model,
+                        "order": order,
+                    },
+                    completion_list_params.CompletionListParams,
+                ),
+            ),
+            model=ChatCompletion,
+        )
+
+    async def delete(
+        self,
+        completion_id: str,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ChatCompletionDeleted:
+        """Delete a stored chat completion.
+
+        Only Chat Completions that have been created
+        with the `store` parameter set to `true` can be deleted.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not completion_id:
+            raise ValueError(f"Expected a non-empty value for `completion_id` but received {completion_id!r}")
+        return await self._delete(
+            f"/chat/completions/{completion_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ChatCompletionDeleted,
+        )
+
+    def stream(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: Union[str, ChatModel],
+        audio: Optional[ChatCompletionAudioParam] | Omit = omit,
+        response_format: completion_create_params.ResponseFormat | type[ResponseFormatT] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        function_call: completion_create_params.FunctionCall | Omit = omit,
+        functions: Iterable[completion_create_params.Function] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[bool] | Omit = omit,
+        max_completion_tokens: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        metadata: Optional[Metadata] | Omit = omit,
+        modalities: Optional[List[Literal["text", "audio"]]] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        parallel_tool_calls: bool | Omit = omit,
+        prediction: Optional[ChatCompletionPredictionContentParam] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        prompt_cache_key: str | Omit = omit,
+        prompt_cache_retention: Optional[Literal["in-memory", "24h"]] | Omit = omit,
+        reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
+        safety_identifier: str | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        store: Optional[bool] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        tool_choice: ChatCompletionToolChoiceOptionParam | Omit = omit,
+        tools: Iterable[ChatCompletionToolUnionParam] | Omit = omit,
+        top_logprobs: Optional[int] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | Omit = omit,
+        verbosity: Optional[Literal["low", "medium", "high"]] | Omit = omit,
+        web_search_options: completion_create_params.WebSearchOptions | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> AsyncChatCompletionStreamManager[ResponseFormatT]:
+        """Wrapper over the `client.chat.completions.create(stream=True)` method that provides a more granular event API
+        and automatic accumulation of each delta.
+
+        This also supports all of the parsing utilities that `.parse()` does.
+
+        Unlike `.create(stream=True)`, the `.stream()` method requires usage within a context manager to prevent accidental leakage of the response:
+
+        ```py
+        async with client.chat.completions.stream(
+            model="gpt-4o-2024-08-06",
+            messages=[...],
+        ) as stream:
+            async for event in stream:
+                if event.type == "content.delta":
+                    print(event.delta, flush=True, end="")
+        ```
+
+        When the context manager is entered, an `AsyncChatCompletionStream` instance is returned which, like `.create(stream=True)` is an async iterator. The full list of events that are yielded by the iterator are outlined in [these docs](https://github.com/openai/openai-python/blob/main/helpers.md#chat-completions-events).
+
+        When the context manager exits, the response will be closed, however the `stream` instance is still available outside
+        the context manager.
+        """
+        _validate_input_tools(tools)
+
+        extra_headers = {
+            "X-Stainless-Helper-Method": "chat.completions.stream",
+            **(extra_headers or {}),
+        }
+
+        api_request = self.create(
+            messages=messages,
+            model=model,
+            audio=audio,
+            stream=True,
+            response_format=_type_to_response_format(response_format),
+            frequency_penalty=frequency_penalty,
+            function_call=function_call,
+            functions=functions,
+            logit_bias=logit_bias,
+            logprobs=logprobs,
+            max_completion_tokens=max_completion_tokens,
+            max_tokens=max_tokens,
+            metadata=metadata,
+            modalities=modalities,
+            n=n,
+            parallel_tool_calls=parallel_tool_calls,
+            prediction=prediction,
+            presence_penalty=presence_penalty,
+            prompt_cache_key=prompt_cache_key,
+            prompt_cache_retention=prompt_cache_retention,
+            reasoning_effort=reasoning_effort,
+            safety_identifier=safety_identifier,
+            seed=seed,
+            service_tier=service_tier,
+            stop=stop,
+            store=store,
+            stream_options=stream_options,
+            temperature=temperature,
+            tool_choice=tool_choice,
+            tools=tools,
+            top_logprobs=top_logprobs,
+            top_p=top_p,
+            user=user,
+            verbosity=verbosity,
+            web_search_options=web_search_options,
+            extra_headers=extra_headers,
+            extra_query=extra_query,
+            extra_body=extra_body,
+            timeout=timeout,
+        )
+        return AsyncChatCompletionStreamManager(
+            api_request,
+            response_format=response_format,
+            input_tools=tools,
+        )
+
+
+class CompletionsWithRawResponse:
+    def __init__(self, completions: Completions) -> None:
+        self._completions = completions
+
+        self.parse = _legacy_response.to_raw_response_wrapper(
+            completions.parse,
+        )
+        self.create = _legacy_response.to_raw_response_wrapper(
+            completions.create,
+        )
+        self.retrieve = _legacy_response.to_raw_response_wrapper(
+            completions.retrieve,
+        )
+        self.update = _legacy_response.to_raw_response_wrapper(
+            completions.update,
+        )
+        self.list = _legacy_response.to_raw_response_wrapper(
+            completions.list,
+        )
+        self.delete = _legacy_response.to_raw_response_wrapper(
+            completions.delete,
+        )
+
+    @cached_property
+    def messages(self) -> MessagesWithRawResponse:
+        return MessagesWithRawResponse(self._completions.messages)
+
+
+class AsyncCompletionsWithRawResponse:
+    def __init__(self, completions: AsyncCompletions) -> None:
+        self._completions = completions
+
+        self.parse = _legacy_response.async_to_raw_response_wrapper(
+            completions.parse,
+        )
+        self.create = _legacy_response.async_to_raw_response_wrapper(
+            completions.create,
+        )
+        self.retrieve = _legacy_response.async_to_raw_response_wrapper(
+            completions.retrieve,
+        )
+        self.update = _legacy_response.async_to_raw_response_wrapper(
+            completions.update,
+        )
+        self.list = _legacy_response.async_to_raw_response_wrapper(
+            completions.list,
+        )
+        self.delete = _legacy_response.async_to_raw_response_wrapper(
+            completions.delete,
+        )
+
+    @cached_property
+    def messages(self) -> AsyncMessagesWithRawResponse:
+        return AsyncMessagesWithRawResponse(self._completions.messages)
+
+
+class CompletionsWithStreamingResponse:
+    def __init__(self, completions: Completions) -> None:
+        self._completions = completions
+
+        self.parse = to_streamed_response_wrapper(
+            completions.parse,
+        )
+        self.create = to_streamed_response_wrapper(
+            completions.create,
+        )
+        self.retrieve = to_streamed_response_wrapper(
+            completions.retrieve,
+        )
+        self.update = to_streamed_response_wrapper(
+            completions.update,
+        )
+        self.list = to_streamed_response_wrapper(
+            completions.list,
+        )
+        self.delete = to_streamed_response_wrapper(
+            completions.delete,
+        )
+
+    @cached_property
+    def messages(self) -> MessagesWithStreamingResponse:
+        return MessagesWithStreamingResponse(self._completions.messages)
+
+
+class AsyncCompletionsWithStreamingResponse:
+    def __init__(self, completions: AsyncCompletions) -> None:
+        self._completions = completions
+
+        self.parse = async_to_streamed_response_wrapper(
+            completions.parse,
+        )
+        self.create = async_to_streamed_response_wrapper(
+            completions.create,
+        )
+        self.retrieve = async_to_streamed_response_wrapper(
+            completions.retrieve,
+        )
+        self.update = async_to_streamed_response_wrapper(
+            completions.update,
+        )
+        self.list = async_to_streamed_response_wrapper(
+            completions.list,
+        )
+        self.delete = async_to_streamed_response_wrapper(
+            completions.delete,
+        )
+
+    @cached_property
+    def messages(self) -> AsyncMessagesWithStreamingResponse:
+        return AsyncMessagesWithStreamingResponse(self._completions.messages)
+
+
+def validate_response_format(response_format: object) -> None:
+    if inspect.isclass(response_format) and issubclass(response_format, pydantic.BaseModel):
+        raise TypeError(
+            "You tried to pass a `BaseModel` class to `chat.completions.create()`; You must use `chat.completions.parse()` instead"
+        )