# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. from __future__ import annotations import inspect from typing import Dict, List, Union, Iterable, Optional from typing_extensions import Literal, overload import httpx import pydantic from ... import _legacy_response from ..._types import NOT_GIVEN, Body, Query, Headers, NotGiven 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 ...types.chat import ( ChatCompletionAudioParam, ChatCompletionReasoningEffort, completion_create_params, ) from ..._base_client import make_request_options from ...types.chat_model import ChatModel from ...types.chat.chat_completion import ChatCompletion from ...types.chat.chat_completion_chunk import ChatCompletionChunk from ...types.chat.chat_completion_modality import ChatCompletionModality from ...types.chat.chat_completion_tool_param import ChatCompletionToolParam from ...types.chat.chat_completion_audio_param import ChatCompletionAudioParam from ...types.chat.chat_completion_message_param import ChatCompletionMessageParam from ...types.chat.chat_completion_reasoning_effort import ChatCompletionReasoningEffort 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 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, *, messages: Iterable[ChatCompletionMessageParam], model: Union[str, ChatModel], audio: Optional[ChatCompletionAudioParam] | NotGiven = NOT_GIVEN, frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN, function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN, functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN, logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN, logprobs: Optional[bool] | NotGiven = NOT_GIVEN, max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN, max_tokens: Optional[int] | NotGiven = NOT_GIVEN, metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN, modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN, n: Optional[int] | NotGiven = NOT_GIVEN, parallel_tool_calls: bool | NotGiven = NOT_GIVEN, prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN, presence_penalty: Optional[float] | NotGiven = NOT_GIVEN, reasoning_effort: ChatCompletionReasoningEffort | NotGiven = NOT_GIVEN, response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN, seed: Optional[int] | NotGiven = NOT_GIVEN, service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN, stop: Union[Optional[str], List[str]] | NotGiven = NOT_GIVEN, store: Optional[bool] | NotGiven = NOT_GIVEN, stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN, stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN, temperature: Optional[float] | NotGiven = NOT_GIVEN, tool_choice: ChatCompletionToolChoiceOptionParam | NotGiven = NOT_GIVEN, tools: Iterable[ChatCompletionToolParam] | NotGiven = NOT_GIVEN, top_logprobs: Optional[int] | NotGiven = NOT_GIVEN, top_p: Optional[float] | NotGiven = NOT_GIVEN, user: str | NotGiven = NOT_GIVEN, # 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: """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: ID of the model to use. See the [model endpoint compatibility](https://platform.openai.com/docs/models#model-endpoint-compatibility) table for details on which models work with the Chat API. 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 [o1 series models](https://platform.openai.com/docs/guides/reasoning). metadata: Developer-defined tags and values used for filtering completions in the [dashboard](https://platform.openai.com/chat-completions). modalities: Output types that you would like the model to generate for this request. 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. reasoning_effort: **o1 models only** Constrains effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently supported values are `low`, `medium`, and `high`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. 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 JSON mode, which ensures the message the model generates is valid JSON. **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. 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 latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service: - If set to 'auto', and the Project is Scale tier enabled, the system will utilize scale tier credits until they are exhausted. - If set to 'auto', and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. - If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. - When not set, the default behavior is 'auto'. stop: Up to 4 sequences where the API will stop generating further tokens. store: Whether or not to store the output of this chat completion request for use in our [model distillation](https://platform.openai.com/docs/guides/distillation) or [evals](https://platform.openai.com/docs/guides/evals) products. stream: If set, partial message deltas will be sent, like in ChatGPT. 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`. 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. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported. 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: 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, *, messages: Iterable[ChatCompletionMessageParam], model: Union[str, ChatModel], stream: Literal[True], audio: Optional[ChatCompletionAudioParam] | NotGiven = NOT_GIVEN, frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN, function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN, functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN, logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN, logprobs: Optional[bool] | NotGiven = NOT_GIVEN, max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN, max_tokens: Optional[int] | NotGiven = NOT_GIVEN, metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN, modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN, n: Optional[int] | NotGiven = NOT_GIVEN, parallel_tool_calls: bool | NotGiven = NOT_GIVEN, prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN, presence_penalty: Optional[float] | NotGiven = NOT_GIVEN, reasoning_effort: ChatCompletionReasoningEffort | NotGiven = NOT_GIVEN, response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN, seed: Optional[int] | NotGiven = NOT_GIVEN, service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN, stop: Union[Optional[str], List[str]] | NotGiven = NOT_GIVEN, store: Optional[bool] | NotGiven = NOT_GIVEN, stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN, temperature: Optional[float] | NotGiven = NOT_GIVEN, tool_choice: ChatCompletionToolChoiceOptionParam | NotGiven = NOT_GIVEN, tools: Iterable[ChatCompletionToolParam] | NotGiven = NOT_GIVEN, top_logprobs: Optional[int] | NotGiven = NOT_GIVEN, top_p: Optional[float] | NotGiven = NOT_GIVEN, user: str | NotGiven = NOT_GIVEN, # 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]: """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: ID of the model to use. See the [model endpoint compatibility](https://platform.openai.com/docs/models#model-endpoint-compatibility) table for details on which models work with the Chat API. stream: If set, partial message deltas will be sent, like in ChatGPT. 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). 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 [o1 series models](https://platform.openai.com/docs/guides/reasoning). metadata: Developer-defined tags and values used for filtering completions in the [dashboard](https://platform.openai.com/chat-completions). modalities: Output types that you would like the model to generate for this request. 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. reasoning_effort: **o1 models only** Constrains effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently supported values are `low`, `medium`, and `high`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. 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 JSON mode, which ensures the message the model generates is valid JSON. **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. 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 latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service: - If set to 'auto', and the Project is Scale tier enabled, the system will utilize scale tier credits until they are exhausted. - If set to 'auto', and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. - If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. - When not set, the default behavior is 'auto'. stop: Up to 4 sequences where the API will stop generating further tokens. store: Whether or not to store the output of this chat completion request for use in our [model distillation](https://platform.openai.com/docs/guides/distillation) or [evals](https://platform.openai.com/docs/guides/evals) products. 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. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported. 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: 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, *, messages: Iterable[ChatCompletionMessageParam], model: Union[str, ChatModel], stream: bool, audio: Optional[ChatCompletionAudioParam] | NotGiven = NOT_GIVEN, frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN, function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN, functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN, logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN, logprobs: Optional[bool] | NotGiven = NOT_GIVEN, max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN, max_tokens: Optional[int] | NotGiven = NOT_GIVEN, metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN, modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN, n: Optional[int] | NotGiven = NOT_GIVEN, parallel_tool_calls: bool | NotGiven = NOT_GIVEN, prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN, presence_penalty: Optional[float] | NotGiven = NOT_GIVEN, reasoning_effort: ChatCompletionReasoningEffort | NotGiven = NOT_GIVEN, response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN, seed: Optional[int] | NotGiven = NOT_GIVEN, service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN, stop: Union[Optional[str], List[str]] | NotGiven = NOT_GIVEN, store: Optional[bool] | NotGiven = NOT_GIVEN, stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN, temperature: Optional[float] | NotGiven = NOT_GIVEN, tool_choice: ChatCompletionToolChoiceOptionParam | NotGiven = NOT_GIVEN, tools: Iterable[ChatCompletionToolParam] | NotGiven = NOT_GIVEN, top_logprobs: Optional[int] | NotGiven = NOT_GIVEN, top_p: Optional[float] | NotGiven = NOT_GIVEN, user: str | NotGiven = NOT_GIVEN, # 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]: """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: ID of the model to use. See the [model endpoint compatibility](https://platform.openai.com/docs/models#model-endpoint-compatibility) table for details on which models work with the Chat API. stream: If set, partial message deltas will be sent, like in ChatGPT. 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). 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 [o1 series models](https://platform.openai.com/docs/guides/reasoning). metadata: Developer-defined tags and values used for filtering completions in the [dashboard](https://platform.openai.com/chat-completions). modalities: Output types that you would like the model to generate for this request. 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. reasoning_effort: **o1 models only** Constrains effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently supported values are `low`, `medium`, and `high`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. 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 JSON mode, which ensures the message the model generates is valid JSON. **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. 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 latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service: - If set to 'auto', and the Project is Scale tier enabled, the system will utilize scale tier credits until they are exhausted. - If set to 'auto', and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. - If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. - When not set, the default behavior is 'auto'. stop: Up to 4 sequences where the API will stop generating further tokens. store: Whether or not to store the output of this chat completion request for use in our [model distillation](https://platform.openai.com/docs/guides/distillation) or [evals](https://platform.openai.com/docs/guides/evals) products. 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. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported. 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: 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(["messages", "model"], ["messages", "model", "stream"]) def create( self, *, messages: Iterable[ChatCompletionMessageParam], model: Union[str, ChatModel], audio: Optional[ChatCompletionAudioParam] | NotGiven = NOT_GIVEN, frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN, function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN, functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN, logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN, logprobs: Optional[bool] | NotGiven = NOT_GIVEN, max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN, max_tokens: Optional[int] | NotGiven = NOT_GIVEN, metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN, modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN, n: Optional[int] | NotGiven = NOT_GIVEN, parallel_tool_calls: bool | NotGiven = NOT_GIVEN, prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN, presence_penalty: Optional[float] | NotGiven = NOT_GIVEN, reasoning_effort: ChatCompletionReasoningEffort | NotGiven = NOT_GIVEN, response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN, seed: Optional[int] | NotGiven = NOT_GIVEN, service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN, stop: Union[Optional[str], List[str]] | NotGiven = NOT_GIVEN, store: Optional[bool] | NotGiven = NOT_GIVEN, stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN, stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN, temperature: Optional[float] | NotGiven = NOT_GIVEN, tool_choice: ChatCompletionToolChoiceOptionParam | NotGiven = NOT_GIVEN, tools: Iterable[ChatCompletionToolParam] | NotGiven = NOT_GIVEN, top_logprobs: Optional[int] | NotGiven = NOT_GIVEN, top_p: Optional[float] | NotGiven = NOT_GIVEN, user: str | NotGiven = NOT_GIVEN, # 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, "reasoning_effort": reasoning_effort, "response_format": response_format, "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, }, completion_create_params.CompletionCreateParams, ), 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], ) 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, *, messages: Iterable[ChatCompletionMessageParam], model: Union[str, ChatModel], audio: Optional[ChatCompletionAudioParam] | NotGiven = NOT_GIVEN, frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN, function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN, functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN, logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN, logprobs: Optional[bool] | NotGiven = NOT_GIVEN, max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN, max_tokens: Optional[int] | NotGiven = NOT_GIVEN, metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN, modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN, n: Optional[int] | NotGiven = NOT_GIVEN, parallel_tool_calls: bool | NotGiven = NOT_GIVEN, prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN, presence_penalty: Optional[float] | NotGiven = NOT_GIVEN, reasoning_effort: ChatCompletionReasoningEffort | NotGiven = NOT_GIVEN, response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN, seed: Optional[int] | NotGiven = NOT_GIVEN, service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN, stop: Union[Optional[str], List[str]] | NotGiven = NOT_GIVEN, store: Optional[bool] | NotGiven = NOT_GIVEN, stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN, stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN, temperature: Optional[float] | NotGiven = NOT_GIVEN, tool_choice: ChatCompletionToolChoiceOptionParam | NotGiven = NOT_GIVEN, tools: Iterable[ChatCompletionToolParam] | NotGiven = NOT_GIVEN, top_logprobs: Optional[int] | NotGiven = NOT_GIVEN, top_p: Optional[float] | NotGiven = NOT_GIVEN, user: str | NotGiven = NOT_GIVEN, # 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: """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: ID of the model to use. See the [model endpoint compatibility](https://platform.openai.com/docs/models#model-endpoint-compatibility) table for details on which models work with the Chat API. 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 [o1 series models](https://platform.openai.com/docs/guides/reasoning). metadata: Developer-defined tags and values used for filtering completions in the [dashboard](https://platform.openai.com/chat-completions). modalities: Output types that you would like the model to generate for this request. 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. reasoning_effort: **o1 models only** Constrains effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently supported values are `low`, `medium`, and `high`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. 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 JSON mode, which ensures the message the model generates is valid JSON. **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. 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 latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service: - If set to 'auto', and the Project is Scale tier enabled, the system will utilize scale tier credits until they are exhausted. - If set to 'auto', and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. - If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. - When not set, the default behavior is 'auto'. stop: Up to 4 sequences where the API will stop generating further tokens. store: Whether or not to store the output of this chat completion request for use in our [model distillation](https://platform.openai.com/docs/guides/distillation) or [evals](https://platform.openai.com/docs/guides/evals) products. stream: If set, partial message deltas will be sent, like in ChatGPT. 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`. 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. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported. 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: 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, *, messages: Iterable[ChatCompletionMessageParam], model: Union[str, ChatModel], stream: Literal[True], audio: Optional[ChatCompletionAudioParam] | NotGiven = NOT_GIVEN, frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN, function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN, functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN, logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN, logprobs: Optional[bool] | NotGiven = NOT_GIVEN, max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN, max_tokens: Optional[int] | NotGiven = NOT_GIVEN, metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN, modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN, n: Optional[int] | NotGiven = NOT_GIVEN, parallel_tool_calls: bool | NotGiven = NOT_GIVEN, prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN, presence_penalty: Optional[float] | NotGiven = NOT_GIVEN, reasoning_effort: ChatCompletionReasoningEffort | NotGiven = NOT_GIVEN, response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN, seed: Optional[int] | NotGiven = NOT_GIVEN, service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN, stop: Union[Optional[str], List[str]] | NotGiven = NOT_GIVEN, store: Optional[bool] | NotGiven = NOT_GIVEN, stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN, temperature: Optional[float] | NotGiven = NOT_GIVEN, tool_choice: ChatCompletionToolChoiceOptionParam | NotGiven = NOT_GIVEN, tools: Iterable[ChatCompletionToolParam] | NotGiven = NOT_GIVEN, top_logprobs: Optional[int] | NotGiven = NOT_GIVEN, top_p: Optional[float] | NotGiven = NOT_GIVEN, user: str | NotGiven = NOT_GIVEN, # 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]: """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: ID of the model to use. See the [model endpoint compatibility](https://platform.openai.com/docs/models#model-endpoint-compatibility) table for details on which models work with the Chat API. stream: If set, partial message deltas will be sent, like in ChatGPT. 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). 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 [o1 series models](https://platform.openai.com/docs/guides/reasoning). metadata: Developer-defined tags and values used for filtering completions in the [dashboard](https://platform.openai.com/chat-completions). modalities: Output types that you would like the model to generate for this request. 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. reasoning_effort: **o1 models only** Constrains effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently supported values are `low`, `medium`, and `high`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. 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 JSON mode, which ensures the message the model generates is valid JSON. **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. 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 latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service: - If set to 'auto', and the Project is Scale tier enabled, the system will utilize scale tier credits until they are exhausted. - If set to 'auto', and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. - If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. - When not set, the default behavior is 'auto'. stop: Up to 4 sequences where the API will stop generating further tokens. store: Whether or not to store the output of this chat completion request for use in our [model distillation](https://platform.openai.com/docs/guides/distillation) or [evals](https://platform.openai.com/docs/guides/evals) products. 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. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported. 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: 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, *, messages: Iterable[ChatCompletionMessageParam], model: Union[str, ChatModel], stream: bool, audio: Optional[ChatCompletionAudioParam] | NotGiven = NOT_GIVEN, frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN, function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN, functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN, logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN, logprobs: Optional[bool] | NotGiven = NOT_GIVEN, max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN, max_tokens: Optional[int] | NotGiven = NOT_GIVEN, metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN, modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN, n: Optional[int] | NotGiven = NOT_GIVEN, parallel_tool_calls: bool | NotGiven = NOT_GIVEN, prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN, presence_penalty: Optional[float] | NotGiven = NOT_GIVEN, reasoning_effort: ChatCompletionReasoningEffort | NotGiven = NOT_GIVEN, response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN, seed: Optional[int] | NotGiven = NOT_GIVEN, service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN, stop: Union[Optional[str], List[str]] | NotGiven = NOT_GIVEN, store: Optional[bool] | NotGiven = NOT_GIVEN, stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN, temperature: Optional[float] | NotGiven = NOT_GIVEN, tool_choice: ChatCompletionToolChoiceOptionParam | NotGiven = NOT_GIVEN, tools: Iterable[ChatCompletionToolParam] | NotGiven = NOT_GIVEN, top_logprobs: Optional[int] | NotGiven = NOT_GIVEN, top_p: Optional[float] | NotGiven = NOT_GIVEN, user: str | NotGiven = NOT_GIVEN, # 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]: """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: ID of the model to use. See the [model endpoint compatibility](https://platform.openai.com/docs/models#model-endpoint-compatibility) table for details on which models work with the Chat API. stream: If set, partial message deltas will be sent, like in ChatGPT. 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). 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 [o1 series models](https://platform.openai.com/docs/guides/reasoning). metadata: Developer-defined tags and values used for filtering completions in the [dashboard](https://platform.openai.com/chat-completions). modalities: Output types that you would like the model to generate for this request. 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. reasoning_effort: **o1 models only** Constrains effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently supported values are `low`, `medium`, and `high`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. 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 JSON mode, which ensures the message the model generates is valid JSON. **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. 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 latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service: - If set to 'auto', and the Project is Scale tier enabled, the system will utilize scale tier credits until they are exhausted. - If set to 'auto', and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. - If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. - When not set, the default behavior is 'auto'. stop: Up to 4 sequences where the API will stop generating further tokens. store: Whether or not to store the output of this chat completion request for use in our [model distillation](https://platform.openai.com/docs/guides/distillation) or [evals](https://platform.openai.com/docs/guides/evals) products. 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. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported. 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: 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(["messages", "model"], ["messages", "model", "stream"]) async def create( self, *, messages: Iterable[ChatCompletionMessageParam], model: Union[str, ChatModel], audio: Optional[ChatCompletionAudioParam] | NotGiven = NOT_GIVEN, frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN, function_call: completion_create_params.FunctionCall | NotGiven = NOT_GIVEN, functions: Iterable[completion_create_params.Function] | NotGiven = NOT_GIVEN, logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN, logprobs: Optional[bool] | NotGiven = NOT_GIVEN, max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN, max_tokens: Optional[int] | NotGiven = NOT_GIVEN, metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN, modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN, n: Optional[int] | NotGiven = NOT_GIVEN, parallel_tool_calls: bool | NotGiven = NOT_GIVEN, prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN, presence_penalty: Optional[float] | NotGiven = NOT_GIVEN, reasoning_effort: ChatCompletionReasoningEffort | NotGiven = NOT_GIVEN, response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN, seed: Optional[int] | NotGiven = NOT_GIVEN, service_tier: Optional[Literal["auto", "default"]] | NotGiven = NOT_GIVEN, stop: Union[Optional[str], List[str]] | NotGiven = NOT_GIVEN, store: Optional[bool] | NotGiven = NOT_GIVEN, stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN, stream_options: Optional[ChatCompletionStreamOptionsParam] | NotGiven = NOT_GIVEN, temperature: Optional[float] | NotGiven = NOT_GIVEN, tool_choice: ChatCompletionToolChoiceOptionParam | NotGiven = NOT_GIVEN, tools: Iterable[ChatCompletionToolParam] | NotGiven = NOT_GIVEN, top_logprobs: Optional[int] | NotGiven = NOT_GIVEN, top_p: Optional[float] | NotGiven = NOT_GIVEN, user: str | NotGiven = NOT_GIVEN, # 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, "reasoning_effort": reasoning_effort, "response_format": response_format, "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, }, completion_create_params.CompletionCreateParams, ), 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], ) 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, ) 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 `beta.chat.completions.parse()` instead" )