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

openai/resources/completions.py

@@ -0,0 +1,1160 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, Union, Iterable, Optional
+from typing_extensions import Literal, overload
+
+import httpx
+
+from .. import _legacy_response
+from ..types import completion_create_params
+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 .._base_client import (
+    make_request_options,
+)
+from ..types.completion import Completion
+from ..types.chat.chat_completion_stream_options_param import ChatCompletionStreamOptionsParam
+
+__all__ = ["Completions", "AsyncCompletions"]
+
+
+class Completions(SyncAPIResource):
+    @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)
+
+    @overload
+    def create(
+        self,
+        *,
+        model: Union[str, Literal["gpt-3.5-turbo-instruct", "davinci-002", "babbage-002"]],
+        prompt: Union[str, SequenceNotStr[str], Iterable[int], Iterable[Iterable[int]], None],
+        best_of: Optional[int] | Omit = omit,
+        echo: Optional[bool] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        stream: Optional[Literal[False]] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        suffix: Optional[str] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | 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,
+    ) -> Completion:
+        """
+        Creates a completion for the provided prompt and parameters.
+
+        Args:
+          model: ID of the model to use. You can use the
+              [List models](https://platform.openai.com/docs/api-reference/models/list) API to
+              see all of your available models, or see our
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
+
+          prompt: The prompt(s) to generate completions for, encoded as a string, array of
+              strings, array of tokens, or array of token arrays.
+
+              Note that <|endoftext|> is the document separator that the model sees during
+              training, so if a prompt is not specified the model will generate as if from the
+              beginning of a new document.
+
+          best_of: Generates `best_of` completions server-side and returns the "best" (the one with
+              the highest log probability per token). Results cannot be streamed.
+
+              When used with `n`, `best_of` controls the number of candidate completions and
+              `n` specifies how many to return – `best_of` must be greater than `n`.
+
+              **Note:** Because this parameter generates many completions, it can quickly
+              consume your token quota. Use carefully and ensure that you have reasonable
+              settings for `max_tokens` and `stop`.
+
+          echo: Echo back the prompt in addition to the completion
+
+          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.
+
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
+
+          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 GPT
+              tokenizer) to an associated bias value from -100 to 100. You can use this
+              [tokenizer tool](/tokenizer?view=bpe) to convert text to token IDs.
+              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.
+
+              As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token
+              from being generated.
+
+          logprobs: Include the log probabilities on the `logprobs` most likely output tokens, as
+              well the chosen tokens. For example, if `logprobs` is 5, the API will return a
+              list of the 5 most likely tokens. The API will always return the `logprob` of
+              the sampled token, so there may be up to `logprobs+1` elements in the response.
+
+              The maximum value for `logprobs` is 5.
+
+          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the
+              completion.
+
+              The token count of your prompt plus `max_tokens` cannot exceed the model's
+              context length.
+              [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
+              for counting tokens.
+
+          n: How many completions to generate for each prompt.
+
+              **Note:** Because this parameter generates many completions, it can quickly
+              consume your token quota. Use carefully and ensure that you have reasonable
+              settings for `max_tokens` and `stop`.
+
+          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.
+
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
+
+          seed: 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.
+
+          stop: Not supported with latest reasoning models `o3` and `o4-mini`.
+
+              Up to 4 sequences where the API will stop generating further tokens. The
+              returned text will not contain the stop sequence.
+
+          stream: Whether to stream back partial progress. If set, tokens will be sent as
+              data-only
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
+              as they become available, with the stream terminated by a `data: [DONE]`
+              message.
+              [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
+
+          stream_options: Options for streaming response. Only set this when you set `stream: true`.
+
+          suffix: The suffix that comes after a completion of inserted text.
+
+              This parameter is only supported for `gpt-3.5-turbo-instruct`.
+
+          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.
+
+          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: A unique identifier representing your end-user, which can help OpenAI to monitor
+              and detect abuse.
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
+
+          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,
+        *,
+        model: Union[str, Literal["gpt-3.5-turbo-instruct", "davinci-002", "babbage-002"]],
+        prompt: Union[str, SequenceNotStr[str], Iterable[int], Iterable[Iterable[int]], None],
+        stream: Literal[True],
+        best_of: Optional[int] | Omit = omit,
+        echo: Optional[bool] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        suffix: Optional[str] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | 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[Completion]:
+        """
+        Creates a completion for the provided prompt and parameters.
+
+        Args:
+          model: ID of the model to use. You can use the
+              [List models](https://platform.openai.com/docs/api-reference/models/list) API to
+              see all of your available models, or see our
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
+
+          prompt: The prompt(s) to generate completions for, encoded as a string, array of
+              strings, array of tokens, or array of token arrays.
+
+              Note that <|endoftext|> is the document separator that the model sees during
+              training, so if a prompt is not specified the model will generate as if from the
+              beginning of a new document.
+
+          stream: Whether to stream back partial progress. If set, tokens will be sent as
+              data-only
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
+              as they become available, with the stream terminated by a `data: [DONE]`
+              message.
+              [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
+
+          best_of: Generates `best_of` completions server-side and returns the "best" (the one with
+              the highest log probability per token). Results cannot be streamed.
+
+              When used with `n`, `best_of` controls the number of candidate completions and
+              `n` specifies how many to return – `best_of` must be greater than `n`.
+
+              **Note:** Because this parameter generates many completions, it can quickly
+              consume your token quota. Use carefully and ensure that you have reasonable
+              settings for `max_tokens` and `stop`.
+
+          echo: Echo back the prompt in addition to the completion
+
+          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.
+
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
+
+          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 GPT
+              tokenizer) to an associated bias value from -100 to 100. You can use this
+              [tokenizer tool](/tokenizer?view=bpe) to convert text to token IDs.
+              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.
+
+              As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token
+              from being generated.
+
+          logprobs: Include the log probabilities on the `logprobs` most likely output tokens, as
+              well the chosen tokens. For example, if `logprobs` is 5, the API will return a
+              list of the 5 most likely tokens. The API will always return the `logprob` of
+              the sampled token, so there may be up to `logprobs+1` elements in the response.
+
+              The maximum value for `logprobs` is 5.
+
+          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the
+              completion.
+
+              The token count of your prompt plus `max_tokens` cannot exceed the model's
+              context length.
+              [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
+              for counting tokens.
+
+          n: How many completions to generate for each prompt.
+
+              **Note:** Because this parameter generates many completions, it can quickly
+              consume your token quota. Use carefully and ensure that you have reasonable
+              settings for `max_tokens` and `stop`.
+
+          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.
+
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
+
+          seed: 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.
+
+          stop: Not supported with latest reasoning models `o3` and `o4-mini`.
+
+              Up to 4 sequences where the API will stop generating further tokens. The
+              returned text will not contain the stop sequence.
+
+          stream_options: Options for streaming response. Only set this when you set `stream: true`.
+
+          suffix: The suffix that comes after a completion of inserted text.
+
+              This parameter is only supported for `gpt-3.5-turbo-instruct`.
+
+          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.
+
+          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: A unique identifier representing your end-user, which can help OpenAI to monitor
+              and detect abuse.
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
+
+          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,
+        *,
+        model: Union[str, Literal["gpt-3.5-turbo-instruct", "davinci-002", "babbage-002"]],
+        prompt: Union[str, SequenceNotStr[str], Iterable[int], Iterable[Iterable[int]], None],
+        stream: bool,
+        best_of: Optional[int] | Omit = omit,
+        echo: Optional[bool] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        suffix: Optional[str] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | 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,
+    ) -> Completion | Stream[Completion]:
+        """
+        Creates a completion for the provided prompt and parameters.
+
+        Args:
+          model: ID of the model to use. You can use the
+              [List models](https://platform.openai.com/docs/api-reference/models/list) API to
+              see all of your available models, or see our
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
+
+          prompt: The prompt(s) to generate completions for, encoded as a string, array of
+              strings, array of tokens, or array of token arrays.
+
+              Note that <|endoftext|> is the document separator that the model sees during
+              training, so if a prompt is not specified the model will generate as if from the
+              beginning of a new document.
+
+          stream: Whether to stream back partial progress. If set, tokens will be sent as
+              data-only
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
+              as they become available, with the stream terminated by a `data: [DONE]`
+              message.
+              [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
+
+          best_of: Generates `best_of` completions server-side and returns the "best" (the one with
+              the highest log probability per token). Results cannot be streamed.
+
+              When used with `n`, `best_of` controls the number of candidate completions and
+              `n` specifies how many to return – `best_of` must be greater than `n`.
+
+              **Note:** Because this parameter generates many completions, it can quickly
+              consume your token quota. Use carefully and ensure that you have reasonable
+              settings for `max_tokens` and `stop`.
+
+          echo: Echo back the prompt in addition to the completion
+
+          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.
+
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
+
+          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 GPT
+              tokenizer) to an associated bias value from -100 to 100. You can use this
+              [tokenizer tool](/tokenizer?view=bpe) to convert text to token IDs.
+              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.
+
+              As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token
+              from being generated.
+
+          logprobs: Include the log probabilities on the `logprobs` most likely output tokens, as
+              well the chosen tokens. For example, if `logprobs` is 5, the API will return a
+              list of the 5 most likely tokens. The API will always return the `logprob` of
+              the sampled token, so there may be up to `logprobs+1` elements in the response.
+
+              The maximum value for `logprobs` is 5.
+
+          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the
+              completion.
+
+              The token count of your prompt plus `max_tokens` cannot exceed the model's
+              context length.
+              [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
+              for counting tokens.
+
+          n: How many completions to generate for each prompt.
+
+              **Note:** Because this parameter generates many completions, it can quickly
+              consume your token quota. Use carefully and ensure that you have reasonable
+              settings for `max_tokens` and `stop`.
+
+          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.
+
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
+
+          seed: 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.
+
+          stop: Not supported with latest reasoning models `o3` and `o4-mini`.
+
+              Up to 4 sequences where the API will stop generating further tokens. The
+              returned text will not contain the stop sequence.
+
+          stream_options: Options for streaming response. Only set this when you set `stream: true`.
+
+          suffix: The suffix that comes after a completion of inserted text.
+
+              This parameter is only supported for `gpt-3.5-turbo-instruct`.
+
+          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.
+
+          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: A unique identifier representing your end-user, which can help OpenAI to monitor
+              and detect abuse.
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
+
+          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(["model", "prompt"], ["model", "prompt", "stream"])
+    def create(
+        self,
+        *,
+        model: Union[str, Literal["gpt-3.5-turbo-instruct", "davinci-002", "babbage-002"]],
+        prompt: Union[str, SequenceNotStr[str], Iterable[int], Iterable[Iterable[int]], None],
+        best_of: Optional[int] | Omit = omit,
+        echo: Optional[bool] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        stream: Optional[Literal[False]] | Literal[True] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        suffix: Optional[str] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | 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,
+    ) -> Completion | Stream[Completion]:
+        return self._post(
+            "/completions",
+            body=maybe_transform(
+                {
+                    "model": model,
+                    "prompt": prompt,
+                    "best_of": best_of,
+                    "echo": echo,
+                    "frequency_penalty": frequency_penalty,
+                    "logit_bias": logit_bias,
+                    "logprobs": logprobs,
+                    "max_tokens": max_tokens,
+                    "n": n,
+                    "presence_penalty": presence_penalty,
+                    "seed": seed,
+                    "stop": stop,
+                    "stream": stream,
+                    "stream_options": stream_options,
+                    "suffix": suffix,
+                    "temperature": temperature,
+                    "top_p": top_p,
+                    "user": user,
+                },
+                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=Completion,
+            stream=stream or False,
+            stream_cls=Stream[Completion],
+        )
+
+
+class AsyncCompletions(AsyncAPIResource):
+    @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)
+
+    @overload
+    async def create(
+        self,
+        *,
+        model: Union[str, Literal["gpt-3.5-turbo-instruct", "davinci-002", "babbage-002"]],
+        prompt: Union[str, SequenceNotStr[str], Iterable[int], Iterable[Iterable[int]], None],
+        best_of: Optional[int] | Omit = omit,
+        echo: Optional[bool] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        stream: Optional[Literal[False]] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        suffix: Optional[str] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | 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,
+    ) -> Completion:
+        """
+        Creates a completion for the provided prompt and parameters.
+
+        Args:
+          model: ID of the model to use. You can use the
+              [List models](https://platform.openai.com/docs/api-reference/models/list) API to
+              see all of your available models, or see our
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
+
+          prompt: The prompt(s) to generate completions for, encoded as a string, array of
+              strings, array of tokens, or array of token arrays.
+
+              Note that <|endoftext|> is the document separator that the model sees during
+              training, so if a prompt is not specified the model will generate as if from the
+              beginning of a new document.
+
+          best_of: Generates `best_of` completions server-side and returns the "best" (the one with
+              the highest log probability per token). Results cannot be streamed.
+
+              When used with `n`, `best_of` controls the number of candidate completions and
+              `n` specifies how many to return – `best_of` must be greater than `n`.
+
+              **Note:** Because this parameter generates many completions, it can quickly
+              consume your token quota. Use carefully and ensure that you have reasonable
+              settings for `max_tokens` and `stop`.
+
+          echo: Echo back the prompt in addition to the completion
+
+          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.
+
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
+
+          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 GPT
+              tokenizer) to an associated bias value from -100 to 100. You can use this
+              [tokenizer tool](/tokenizer?view=bpe) to convert text to token IDs.
+              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.
+
+              As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token
+              from being generated.
+
+          logprobs: Include the log probabilities on the `logprobs` most likely output tokens, as
+              well the chosen tokens. For example, if `logprobs` is 5, the API will return a
+              list of the 5 most likely tokens. The API will always return the `logprob` of
+              the sampled token, so there may be up to `logprobs+1` elements in the response.
+
+              The maximum value for `logprobs` is 5.
+
+          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the
+              completion.
+
+              The token count of your prompt plus `max_tokens` cannot exceed the model's
+              context length.
+              [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
+              for counting tokens.
+
+          n: How many completions to generate for each prompt.
+
+              **Note:** Because this parameter generates many completions, it can quickly
+              consume your token quota. Use carefully and ensure that you have reasonable
+              settings for `max_tokens` and `stop`.
+
+          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.
+
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
+
+          seed: 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.
+
+          stop: Not supported with latest reasoning models `o3` and `o4-mini`.
+
+              Up to 4 sequences where the API will stop generating further tokens. The
+              returned text will not contain the stop sequence.
+
+          stream: Whether to stream back partial progress. If set, tokens will be sent as
+              data-only
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
+              as they become available, with the stream terminated by a `data: [DONE]`
+              message.
+              [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
+
+          stream_options: Options for streaming response. Only set this when you set `stream: true`.
+
+          suffix: The suffix that comes after a completion of inserted text.
+
+              This parameter is only supported for `gpt-3.5-turbo-instruct`.
+
+          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.
+
+          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: A unique identifier representing your end-user, which can help OpenAI to monitor
+              and detect abuse.
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
+
+          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,
+        *,
+        model: Union[str, Literal["gpt-3.5-turbo-instruct", "davinci-002", "babbage-002"]],
+        prompt: Union[str, SequenceNotStr[str], Iterable[int], Iterable[Iterable[int]], None],
+        stream: Literal[True],
+        best_of: Optional[int] | Omit = omit,
+        echo: Optional[bool] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        suffix: Optional[str] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | 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[Completion]:
+        """
+        Creates a completion for the provided prompt and parameters.
+
+        Args:
+          model: ID of the model to use. You can use the
+              [List models](https://platform.openai.com/docs/api-reference/models/list) API to
+              see all of your available models, or see our
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
+
+          prompt: The prompt(s) to generate completions for, encoded as a string, array of
+              strings, array of tokens, or array of token arrays.
+
+              Note that <|endoftext|> is the document separator that the model sees during
+              training, so if a prompt is not specified the model will generate as if from the
+              beginning of a new document.
+
+          stream: Whether to stream back partial progress. If set, tokens will be sent as
+              data-only
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
+              as they become available, with the stream terminated by a `data: [DONE]`
+              message.
+              [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
+
+          best_of: Generates `best_of` completions server-side and returns the "best" (the one with
+              the highest log probability per token). Results cannot be streamed.
+
+              When used with `n`, `best_of` controls the number of candidate completions and
+              `n` specifies how many to return – `best_of` must be greater than `n`.
+
+              **Note:** Because this parameter generates many completions, it can quickly
+              consume your token quota. Use carefully and ensure that you have reasonable
+              settings for `max_tokens` and `stop`.
+
+          echo: Echo back the prompt in addition to the completion
+
+          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.
+
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
+
+          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 GPT
+              tokenizer) to an associated bias value from -100 to 100. You can use this
+              [tokenizer tool](/tokenizer?view=bpe) to convert text to token IDs.
+              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.
+
+              As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token
+              from being generated.
+
+          logprobs: Include the log probabilities on the `logprobs` most likely output tokens, as
+              well the chosen tokens. For example, if `logprobs` is 5, the API will return a
+              list of the 5 most likely tokens. The API will always return the `logprob` of
+              the sampled token, so there may be up to `logprobs+1` elements in the response.
+
+              The maximum value for `logprobs` is 5.
+
+          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the
+              completion.
+
+              The token count of your prompt plus `max_tokens` cannot exceed the model's
+              context length.
+              [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
+              for counting tokens.
+
+          n: How many completions to generate for each prompt.
+
+              **Note:** Because this parameter generates many completions, it can quickly
+              consume your token quota. Use carefully and ensure that you have reasonable
+              settings for `max_tokens` and `stop`.
+
+          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.
+
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
+
+          seed: 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.
+
+          stop: Not supported with latest reasoning models `o3` and `o4-mini`.
+
+              Up to 4 sequences where the API will stop generating further tokens. The
+              returned text will not contain the stop sequence.
+
+          stream_options: Options for streaming response. Only set this when you set `stream: true`.
+
+          suffix: The suffix that comes after a completion of inserted text.
+
+              This parameter is only supported for `gpt-3.5-turbo-instruct`.
+
+          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.
+
+          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: A unique identifier representing your end-user, which can help OpenAI to monitor
+              and detect abuse.
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
+
+          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,
+        *,
+        model: Union[str, Literal["gpt-3.5-turbo-instruct", "davinci-002", "babbage-002"]],
+        prompt: Union[str, SequenceNotStr[str], Iterable[int], Iterable[Iterable[int]], None],
+        stream: bool,
+        best_of: Optional[int] | Omit = omit,
+        echo: Optional[bool] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        suffix: Optional[str] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | 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,
+    ) -> Completion | AsyncStream[Completion]:
+        """
+        Creates a completion for the provided prompt and parameters.
+
+        Args:
+          model: ID of the model to use. You can use the
+              [List models](https://platform.openai.com/docs/api-reference/models/list) API to
+              see all of your available models, or see our
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
+
+          prompt: The prompt(s) to generate completions for, encoded as a string, array of
+              strings, array of tokens, or array of token arrays.
+
+              Note that <|endoftext|> is the document separator that the model sees during
+              training, so if a prompt is not specified the model will generate as if from the
+              beginning of a new document.
+
+          stream: Whether to stream back partial progress. If set, tokens will be sent as
+              data-only
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
+              as they become available, with the stream terminated by a `data: [DONE]`
+              message.
+              [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
+
+          best_of: Generates `best_of` completions server-side and returns the "best" (the one with
+              the highest log probability per token). Results cannot be streamed.
+
+              When used with `n`, `best_of` controls the number of candidate completions and
+              `n` specifies how many to return – `best_of` must be greater than `n`.
+
+              **Note:** Because this parameter generates many completions, it can quickly
+              consume your token quota. Use carefully and ensure that you have reasonable
+              settings for `max_tokens` and `stop`.
+
+          echo: Echo back the prompt in addition to the completion
+
+          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.
+
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
+
+          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 GPT
+              tokenizer) to an associated bias value from -100 to 100. You can use this
+              [tokenizer tool](/tokenizer?view=bpe) to convert text to token IDs.
+              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.
+
+              As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token
+              from being generated.
+
+          logprobs: Include the log probabilities on the `logprobs` most likely output tokens, as
+              well the chosen tokens. For example, if `logprobs` is 5, the API will return a
+              list of the 5 most likely tokens. The API will always return the `logprob` of
+              the sampled token, so there may be up to `logprobs+1` elements in the response.
+
+              The maximum value for `logprobs` is 5.
+
+          max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the
+              completion.
+
+              The token count of your prompt plus `max_tokens` cannot exceed the model's
+              context length.
+              [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
+              for counting tokens.
+
+          n: How many completions to generate for each prompt.
+
+              **Note:** Because this parameter generates many completions, it can quickly
+              consume your token quota. Use carefully and ensure that you have reasonable
+              settings for `max_tokens` and `stop`.
+
+          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.
+
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
+
+          seed: 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.
+
+          stop: Not supported with latest reasoning models `o3` and `o4-mini`.
+
+              Up to 4 sequences where the API will stop generating further tokens. The
+              returned text will not contain the stop sequence.
+
+          stream_options: Options for streaming response. Only set this when you set `stream: true`.
+
+          suffix: The suffix that comes after a completion of inserted text.
+
+              This parameter is only supported for `gpt-3.5-turbo-instruct`.
+
+          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.
+
+          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: A unique identifier representing your end-user, which can help OpenAI to monitor
+              and detect abuse.
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
+
+          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(["model", "prompt"], ["model", "prompt", "stream"])
+    async def create(
+        self,
+        *,
+        model: Union[str, Literal["gpt-3.5-turbo-instruct", "davinci-002", "babbage-002"]],
+        prompt: Union[str, SequenceNotStr[str], Iterable[int], Iterable[Iterable[int]], None],
+        best_of: Optional[int] | Omit = omit,
+        echo: Optional[bool] | Omit = omit,
+        frequency_penalty: Optional[float] | Omit = omit,
+        logit_bias: Optional[Dict[str, int]] | Omit = omit,
+        logprobs: Optional[int] | Omit = omit,
+        max_tokens: Optional[int] | Omit = omit,
+        n: Optional[int] | Omit = omit,
+        presence_penalty: Optional[float] | Omit = omit,
+        seed: Optional[int] | Omit = omit,
+        stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
+        stream: Optional[Literal[False]] | Literal[True] | Omit = omit,
+        stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
+        suffix: Optional[str] | Omit = omit,
+        temperature: Optional[float] | Omit = omit,
+        top_p: Optional[float] | Omit = omit,
+        user: str | 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,
+    ) -> Completion | AsyncStream[Completion]:
+        return await self._post(
+            "/completions",
+            body=await async_maybe_transform(
+                {
+                    "model": model,
+                    "prompt": prompt,
+                    "best_of": best_of,
+                    "echo": echo,
+                    "frequency_penalty": frequency_penalty,
+                    "logit_bias": logit_bias,
+                    "logprobs": logprobs,
+                    "max_tokens": max_tokens,
+                    "n": n,
+                    "presence_penalty": presence_penalty,
+                    "seed": seed,
+                    "stop": stop,
+                    "stream": stream,
+                    "stream_options": stream_options,
+                    "suffix": suffix,
+                    "temperature": temperature,
+                    "top_p": top_p,
+                    "user": user,
+                },
+                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=Completion,
+            stream=stream or False,
+            stream_cls=AsyncStream[Completion],
+        )
+
+
+class CompletionsWithRawResponse:
+    def __init__(self, completions: Completions) -> None:
+        self._completions = completions
+
+        self.create = _legacy_response.to_raw_response_wrapper(
+            completions.create,
+        )
+
+
+class AsyncCompletionsWithRawResponse:
+    def __init__(self, completions: AsyncCompletions) -> None:
+        self._completions = completions
+
+        self.create = _legacy_response.async_to_raw_response_wrapper(
+            completions.create,
+        )
+
+
+class CompletionsWithStreamingResponse:
+    def __init__(self, completions: Completions) -> None:
+        self._completions = completions
+
+        self.create = to_streamed_response_wrapper(
+            completions.create,
+        )
+
+
+class AsyncCompletionsWithStreamingResponse:
+    def __init__(self, completions: AsyncCompletions) -> None:
+        self._completions = completions
+
+        self.create = async_to_streamed_response_wrapper(
+            completions.create,
+        )