scale-gp-beta 0.1.0a2__py3-none-any.whl

scale_gp/resources/chat/completions.py

@@ -0,0 +1,1054 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Any, Dict, List, Union, Iterable, cast
+from typing_extensions import Literal, overload
+
+import httpx
+
+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_raw_response_wrapper,
+    to_streamed_response_wrapper,
+    async_to_raw_response_wrapper,
+    async_to_streamed_response_wrapper,
+)
+from ..._streaming import Stream, AsyncStream
+from ...types.chat import completion_create_params
+from ..._base_client import make_request_options
+from ...types.chat.chat_completion_chunk import ChatCompletionChunk
+from ...types.chat.completion_create_response import CompletionCreateResponse
+
+__all__ = ["CompletionsResource", "AsyncCompletionsResource"]
+
+
+class CompletionsResource(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> CompletionsResourceWithRawResponse:
+        """
+        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/scaleapi/sgp-python-beta#accessing-raw-response-data-eg-headers
+        """
+        return CompletionsResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> CompletionsResourceWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/scaleapi/sgp-python-beta#with_streaming_response
+        """
+        return CompletionsResourceWithStreamingResponse(self)
+
+    @overload
+    def create(
+        self,
+        *,
+        messages: Iterable[Dict[str, object]],
+        model: str,
+        audio: Dict[str, object] | NotGiven = NOT_GIVEN,
+        frequency_penalty: float | NotGiven = NOT_GIVEN,
+        function_call: Dict[str, object] | NotGiven = NOT_GIVEN,
+        functions: Iterable[Dict[str, object]] | NotGiven = NOT_GIVEN,
+        logit_bias: Dict[str, int] | NotGiven = NOT_GIVEN,
+        logprobs: bool | NotGiven = NOT_GIVEN,
+        max_completion_tokens: int | NotGiven = NOT_GIVEN,
+        max_tokens: int | NotGiven = NOT_GIVEN,
+        metadata: Dict[str, str] | NotGiven = NOT_GIVEN,
+        modalities: List[str] | NotGiven = NOT_GIVEN,
+        n: int | NotGiven = NOT_GIVEN,
+        parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        prediction: Dict[str, object] | NotGiven = NOT_GIVEN,
+        presence_penalty: float | NotGiven = NOT_GIVEN,
+        reasoning_effort: str | NotGiven = NOT_GIVEN,
+        response_format: Dict[str, object] | NotGiven = NOT_GIVEN,
+        seed: int | NotGiven = NOT_GIVEN,
+        stop: Union[str, List[str]] | NotGiven = NOT_GIVEN,
+        store: bool | NotGiven = NOT_GIVEN,
+        stream: Literal[False] | NotGiven = NOT_GIVEN,
+        stream_options: Dict[str, object] | NotGiven = NOT_GIVEN,
+        temperature: float | NotGiven = NOT_GIVEN,
+        tool_choice: Union[str, Dict[str, object]] | NotGiven = NOT_GIVEN,
+        tools: Iterable[Dict[str, object]] | NotGiven = NOT_GIVEN,
+        top_k: int | NotGiven = NOT_GIVEN,
+        top_logprobs: int | NotGiven = NOT_GIVEN,
+        top_p: float | 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,
+    ) -> CompletionCreateResponse:
+        """
+        Chat Completions
+
+        Args:
+          messages: openai standard message format
+
+          model: model specified as `model_vendor/model`, for example `openai/gpt-4o`
+
+          audio: Parameters for audio output. Required when audio output is requested with
+              modalities: ['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.
+
+          function_call: Deprecated in favor of tool_choice. Controls which function is called by the
+              model.
+
+          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. Maps
+              tokens to bias values from -100 to 100.
+
+          logprobs: Whether to return log probabilities of the output tokens or not.
+
+          max_completion_tokens: An upper bound for the number of tokens that can be generated, including visible
+              output tokens and reasoning tokens.
+
+          max_tokens: Deprecated in favor of max_completion_tokens. The maximum number of tokens to
+              generate.
+
+          metadata: Developer-defined tags and values used for filtering completions in the
+              dashboard.
+
+          modalities: Output types that you would like the model to generate for this request.
+
+          n: How many chat completion choices to generate for each input message.
+
+          parallel_tool_calls: Whether to enable parallel function calling during tool use.
+
+          prediction: Static predicted output content, such as the content of a text file being
+              regenerated.
+
+          presence_penalty: Number between -2.0 and 2.0. Positive values penalize tokens based on whether
+              they appear in the text so far.
+
+          reasoning_effort: For o1 models only. Constrains effort on reasoning. Values: low, medium, high.
+
+          response_format: An object specifying the format that the model must output.
+
+          seed: If specified, system will attempt to sample deterministically for repeated
+              requests with same seed.
+
+          stop: Up to 4 sequences where the API will stop generating further tokens.
+
+          store: Whether to store the output for use in model distillation or evals products.
+
+          stream: If true, partial message deltas will be sent as server-sent events.
+
+          stream_options: Options for streaming response. Only set this when stream is true.
+
+          temperature: What sampling temperature to use. Higher values make output more random, lower
+              more focused.
+
+          tool_choice: Controls which tool is called by the model. Values: none, auto, required, or
+              specific tool.
+
+          tools: A list of tools the model may call. Currently, only functions are supported. Max
+              128 functions.
+
+          top_k: Only sample from the top K options for each subsequent token
+
+          top_logprobs: Number of most likely tokens to return at each position, with associated log
+              probability.
+
+          top_p: Alternative to temperature. Only tokens comprising top_p probability mass are
+              considered.
+
+          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[Dict[str, object]],
+        model: str,
+        stream: Literal[True],
+        audio: Dict[str, object] | NotGiven = NOT_GIVEN,
+        frequency_penalty: float | NotGiven = NOT_GIVEN,
+        function_call: Dict[str, object] | NotGiven = NOT_GIVEN,
+        functions: Iterable[Dict[str, object]] | NotGiven = NOT_GIVEN,
+        logit_bias: Dict[str, int] | NotGiven = NOT_GIVEN,
+        logprobs: bool | NotGiven = NOT_GIVEN,
+        max_completion_tokens: int | NotGiven = NOT_GIVEN,
+        max_tokens: int | NotGiven = NOT_GIVEN,
+        metadata: Dict[str, str] | NotGiven = NOT_GIVEN,
+        modalities: List[str] | NotGiven = NOT_GIVEN,
+        n: int | NotGiven = NOT_GIVEN,
+        parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        prediction: Dict[str, object] | NotGiven = NOT_GIVEN,
+        presence_penalty: float | NotGiven = NOT_GIVEN,
+        reasoning_effort: str | NotGiven = NOT_GIVEN,
+        response_format: Dict[str, object] | NotGiven = NOT_GIVEN,
+        seed: int | NotGiven = NOT_GIVEN,
+        stop: Union[str, List[str]] | NotGiven = NOT_GIVEN,
+        store: bool | NotGiven = NOT_GIVEN,
+        stream_options: Dict[str, object] | NotGiven = NOT_GIVEN,
+        temperature: float | NotGiven = NOT_GIVEN,
+        tool_choice: Union[str, Dict[str, object]] | NotGiven = NOT_GIVEN,
+        tools: Iterable[Dict[str, object]] | NotGiven = NOT_GIVEN,
+        top_k: int | NotGiven = NOT_GIVEN,
+        top_logprobs: int | NotGiven = NOT_GIVEN,
+        top_p: float | 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]:
+        """
+        Chat Completions
+
+        Args:
+          messages: openai standard message format
+
+          model: model specified as `model_vendor/model`, for example `openai/gpt-4o`
+
+          stream: If true, partial message deltas will be sent as server-sent events.
+
+          audio: Parameters for audio output. Required when audio output is requested with
+              modalities: ['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.
+
+          function_call: Deprecated in favor of tool_choice. Controls which function is called by the
+              model.
+
+          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. Maps
+              tokens to bias values from -100 to 100.
+
+          logprobs: Whether to return log probabilities of the output tokens or not.
+
+          max_completion_tokens: An upper bound for the number of tokens that can be generated, including visible
+              output tokens and reasoning tokens.
+
+          max_tokens: Deprecated in favor of max_completion_tokens. The maximum number of tokens to
+              generate.
+
+          metadata: Developer-defined tags and values used for filtering completions in the
+              dashboard.
+
+          modalities: Output types that you would like the model to generate for this request.
+
+          n: How many chat completion choices to generate for each input message.
+
+          parallel_tool_calls: Whether to enable parallel function calling during tool use.
+
+          prediction: Static predicted output content, such as the content of a text file being
+              regenerated.
+
+          presence_penalty: Number between -2.0 and 2.0. Positive values penalize tokens based on whether
+              they appear in the text so far.
+
+          reasoning_effort: For o1 models only. Constrains effort on reasoning. Values: low, medium, high.
+
+          response_format: An object specifying the format that the model must output.
+
+          seed: If specified, system will attempt to sample deterministically for repeated
+              requests with same seed.
+
+          stop: Up to 4 sequences where the API will stop generating further tokens.
+
+          store: Whether to store the output for use in model distillation or evals products.
+
+          stream_options: Options for streaming response. Only set this when stream is true.
+
+          temperature: What sampling temperature to use. Higher values make output more random, lower
+              more focused.
+
+          tool_choice: Controls which tool is called by the model. Values: none, auto, required, or
+              specific tool.
+
+          tools: A list of tools the model may call. Currently, only functions are supported. Max
+              128 functions.
+
+          top_k: Only sample from the top K options for each subsequent token
+
+          top_logprobs: Number of most likely tokens to return at each position, with associated log
+              probability.
+
+          top_p: Alternative to temperature. Only tokens comprising top_p probability mass are
+              considered.
+
+          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[Dict[str, object]],
+        model: str,
+        stream: bool,
+        audio: Dict[str, object] | NotGiven = NOT_GIVEN,
+        frequency_penalty: float | NotGiven = NOT_GIVEN,
+        function_call: Dict[str, object] | NotGiven = NOT_GIVEN,
+        functions: Iterable[Dict[str, object]] | NotGiven = NOT_GIVEN,
+        logit_bias: Dict[str, int] | NotGiven = NOT_GIVEN,
+        logprobs: bool | NotGiven = NOT_GIVEN,
+        max_completion_tokens: int | NotGiven = NOT_GIVEN,
+        max_tokens: int | NotGiven = NOT_GIVEN,
+        metadata: Dict[str, str] | NotGiven = NOT_GIVEN,
+        modalities: List[str] | NotGiven = NOT_GIVEN,
+        n: int | NotGiven = NOT_GIVEN,
+        parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        prediction: Dict[str, object] | NotGiven = NOT_GIVEN,
+        presence_penalty: float | NotGiven = NOT_GIVEN,
+        reasoning_effort: str | NotGiven = NOT_GIVEN,
+        response_format: Dict[str, object] | NotGiven = NOT_GIVEN,
+        seed: int | NotGiven = NOT_GIVEN,
+        stop: Union[str, List[str]] | NotGiven = NOT_GIVEN,
+        store: bool | NotGiven = NOT_GIVEN,
+        stream_options: Dict[str, object] | NotGiven = NOT_GIVEN,
+        temperature: float | NotGiven = NOT_GIVEN,
+        tool_choice: Union[str, Dict[str, object]] | NotGiven = NOT_GIVEN,
+        tools: Iterable[Dict[str, object]] | NotGiven = NOT_GIVEN,
+        top_k: int | NotGiven = NOT_GIVEN,
+        top_logprobs: int | NotGiven = NOT_GIVEN,
+        top_p: float | 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,
+    ) -> CompletionCreateResponse | Stream[ChatCompletionChunk]:
+        """
+        Chat Completions
+
+        Args:
+          messages: openai standard message format
+
+          model: model specified as `model_vendor/model`, for example `openai/gpt-4o`
+
+          stream: If true, partial message deltas will be sent as server-sent events.
+
+          audio: Parameters for audio output. Required when audio output is requested with
+              modalities: ['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.
+
+          function_call: Deprecated in favor of tool_choice. Controls which function is called by the
+              model.
+
+          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. Maps
+              tokens to bias values from -100 to 100.
+
+          logprobs: Whether to return log probabilities of the output tokens or not.
+
+          max_completion_tokens: An upper bound for the number of tokens that can be generated, including visible
+              output tokens and reasoning tokens.
+
+          max_tokens: Deprecated in favor of max_completion_tokens. The maximum number of tokens to
+              generate.
+
+          metadata: Developer-defined tags and values used for filtering completions in the
+              dashboard.
+
+          modalities: Output types that you would like the model to generate for this request.
+
+          n: How many chat completion choices to generate for each input message.
+
+          parallel_tool_calls: Whether to enable parallel function calling during tool use.
+
+          prediction: Static predicted output content, such as the content of a text file being
+              regenerated.
+
+          presence_penalty: Number between -2.0 and 2.0. Positive values penalize tokens based on whether
+              they appear in the text so far.
+
+          reasoning_effort: For o1 models only. Constrains effort on reasoning. Values: low, medium, high.
+
+          response_format: An object specifying the format that the model must output.
+
+          seed: If specified, system will attempt to sample deterministically for repeated
+              requests with same seed.
+
+          stop: Up to 4 sequences where the API will stop generating further tokens.
+
+          store: Whether to store the output for use in model distillation or evals products.
+
+          stream_options: Options for streaming response. Only set this when stream is true.
+
+          temperature: What sampling temperature to use. Higher values make output more random, lower
+              more focused.
+
+          tool_choice: Controls which tool is called by the model. Values: none, auto, required, or
+              specific tool.
+
+          tools: A list of tools the model may call. Currently, only functions are supported. Max
+              128 functions.
+
+          top_k: Only sample from the top K options for each subsequent token
+
+          top_logprobs: Number of most likely tokens to return at each position, with associated log
+              probability.
+
+          top_p: Alternative to temperature. Only tokens comprising top_p probability mass are
+              considered.
+
+          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[Dict[str, object]],
+        model: str,
+        audio: Dict[str, object] | NotGiven = NOT_GIVEN,
+        frequency_penalty: float | NotGiven = NOT_GIVEN,
+        function_call: Dict[str, object] | NotGiven = NOT_GIVEN,
+        functions: Iterable[Dict[str, object]] | NotGiven = NOT_GIVEN,
+        logit_bias: Dict[str, int] | NotGiven = NOT_GIVEN,
+        logprobs: bool | NotGiven = NOT_GIVEN,
+        max_completion_tokens: int | NotGiven = NOT_GIVEN,
+        max_tokens: int | NotGiven = NOT_GIVEN,
+        metadata: Dict[str, str] | NotGiven = NOT_GIVEN,
+        modalities: List[str] | NotGiven = NOT_GIVEN,
+        n: int | NotGiven = NOT_GIVEN,
+        parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        prediction: Dict[str, object] | NotGiven = NOT_GIVEN,
+        presence_penalty: float | NotGiven = NOT_GIVEN,
+        reasoning_effort: str | NotGiven = NOT_GIVEN,
+        response_format: Dict[str, object] | NotGiven = NOT_GIVEN,
+        seed: int | NotGiven = NOT_GIVEN,
+        stop: Union[str, List[str]] | NotGiven = NOT_GIVEN,
+        store: bool | NotGiven = NOT_GIVEN,
+        stream: Literal[False] | Literal[True] | NotGiven = NOT_GIVEN,
+        stream_options: Dict[str, object] | NotGiven = NOT_GIVEN,
+        temperature: float | NotGiven = NOT_GIVEN,
+        tool_choice: Union[str, Dict[str, object]] | NotGiven = NOT_GIVEN,
+        tools: Iterable[Dict[str, object]] | NotGiven = NOT_GIVEN,
+        top_k: int | NotGiven = NOT_GIVEN,
+        top_logprobs: int | NotGiven = NOT_GIVEN,
+        top_p: float | 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,
+    ) -> CompletionCreateResponse | Stream[ChatCompletionChunk]:
+        return cast(
+            CompletionCreateResponse,
+            self._post(
+                "/v5/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,
+                        "stop": stop,
+                        "store": store,
+                        "stream": stream,
+                        "stream_options": stream_options,
+                        "temperature": temperature,
+                        "tool_choice": tool_choice,
+                        "tools": tools,
+                        "top_k": top_k,
+                        "top_logprobs": top_logprobs,
+                        "top_p": top_p,
+                    },
+                    completion_create_params.CompletionCreateParams,
+                ),
+                options=make_request_options(
+                    extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+                ),
+                cast_to=cast(
+                    Any, CompletionCreateResponse
+                ),  # Union types cannot be passed in as arguments in the type system
+                stream=stream or False,
+                stream_cls=Stream[ChatCompletionChunk],
+            ),
+        )
+
+
+class AsyncCompletionsResource(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncCompletionsResourceWithRawResponse:
+        """
+        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/scaleapi/sgp-python-beta#accessing-raw-response-data-eg-headers
+        """
+        return AsyncCompletionsResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncCompletionsResourceWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/scaleapi/sgp-python-beta#with_streaming_response
+        """
+        return AsyncCompletionsResourceWithStreamingResponse(self)
+
+    @overload
+    async def create(
+        self,
+        *,
+        messages: Iterable[Dict[str, object]],
+        model: str,
+        audio: Dict[str, object] | NotGiven = NOT_GIVEN,
+        frequency_penalty: float | NotGiven = NOT_GIVEN,
+        function_call: Dict[str, object] | NotGiven = NOT_GIVEN,
+        functions: Iterable[Dict[str, object]] | NotGiven = NOT_GIVEN,
+        logit_bias: Dict[str, int] | NotGiven = NOT_GIVEN,
+        logprobs: bool | NotGiven = NOT_GIVEN,
+        max_completion_tokens: int | NotGiven = NOT_GIVEN,
+        max_tokens: int | NotGiven = NOT_GIVEN,
+        metadata: Dict[str, str] | NotGiven = NOT_GIVEN,
+        modalities: List[str] | NotGiven = NOT_GIVEN,
+        n: int | NotGiven = NOT_GIVEN,
+        parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        prediction: Dict[str, object] | NotGiven = NOT_GIVEN,
+        presence_penalty: float | NotGiven = NOT_GIVEN,
+        reasoning_effort: str | NotGiven = NOT_GIVEN,
+        response_format: Dict[str, object] | NotGiven = NOT_GIVEN,
+        seed: int | NotGiven = NOT_GIVEN,
+        stop: Union[str, List[str]] | NotGiven = NOT_GIVEN,
+        store: bool | NotGiven = NOT_GIVEN,
+        stream: Literal[False] | NotGiven = NOT_GIVEN,
+        stream_options: Dict[str, object] | NotGiven = NOT_GIVEN,
+        temperature: float | NotGiven = NOT_GIVEN,
+        tool_choice: Union[str, Dict[str, object]] | NotGiven = NOT_GIVEN,
+        tools: Iterable[Dict[str, object]] | NotGiven = NOT_GIVEN,
+        top_k: int | NotGiven = NOT_GIVEN,
+        top_logprobs: int | NotGiven = NOT_GIVEN,
+        top_p: float | 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,
+    ) -> CompletionCreateResponse:
+        """
+        Chat Completions
+
+        Args:
+          messages: openai standard message format
+
+          model: model specified as `model_vendor/model`, for example `openai/gpt-4o`
+
+          audio: Parameters for audio output. Required when audio output is requested with
+              modalities: ['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.
+
+          function_call: Deprecated in favor of tool_choice. Controls which function is called by the
+              model.
+
+          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. Maps
+              tokens to bias values from -100 to 100.
+
+          logprobs: Whether to return log probabilities of the output tokens or not.
+
+          max_completion_tokens: An upper bound for the number of tokens that can be generated, including visible
+              output tokens and reasoning tokens.
+
+          max_tokens: Deprecated in favor of max_completion_tokens. The maximum number of tokens to
+              generate.
+
+          metadata: Developer-defined tags and values used for filtering completions in the
+              dashboard.
+
+          modalities: Output types that you would like the model to generate for this request.
+
+          n: How many chat completion choices to generate for each input message.
+
+          parallel_tool_calls: Whether to enable parallel function calling during tool use.
+
+          prediction: Static predicted output content, such as the content of a text file being
+              regenerated.
+
+          presence_penalty: Number between -2.0 and 2.0. Positive values penalize tokens based on whether
+              they appear in the text so far.
+
+          reasoning_effort: For o1 models only. Constrains effort on reasoning. Values: low, medium, high.
+
+          response_format: An object specifying the format that the model must output.
+
+          seed: If specified, system will attempt to sample deterministically for repeated
+              requests with same seed.
+
+          stop: Up to 4 sequences where the API will stop generating further tokens.
+
+          store: Whether to store the output for use in model distillation or evals products.
+
+          stream: If true, partial message deltas will be sent as server-sent events.
+
+          stream_options: Options for streaming response. Only set this when stream is true.
+
+          temperature: What sampling temperature to use. Higher values make output more random, lower
+              more focused.
+
+          tool_choice: Controls which tool is called by the model. Values: none, auto, required, or
+              specific tool.
+
+          tools: A list of tools the model may call. Currently, only functions are supported. Max
+              128 functions.
+
+          top_k: Only sample from the top K options for each subsequent token
+
+          top_logprobs: Number of most likely tokens to return at each position, with associated log
+              probability.
+
+          top_p: Alternative to temperature. Only tokens comprising top_p probability mass are
+              considered.
+
+          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[Dict[str, object]],
+        model: str,
+        stream: Literal[True],
+        audio: Dict[str, object] | NotGiven = NOT_GIVEN,
+        frequency_penalty: float | NotGiven = NOT_GIVEN,
+        function_call: Dict[str, object] | NotGiven = NOT_GIVEN,
+        functions: Iterable[Dict[str, object]] | NotGiven = NOT_GIVEN,
+        logit_bias: Dict[str, int] | NotGiven = NOT_GIVEN,
+        logprobs: bool | NotGiven = NOT_GIVEN,
+        max_completion_tokens: int | NotGiven = NOT_GIVEN,
+        max_tokens: int | NotGiven = NOT_GIVEN,
+        metadata: Dict[str, str] | NotGiven = NOT_GIVEN,
+        modalities: List[str] | NotGiven = NOT_GIVEN,
+        n: int | NotGiven = NOT_GIVEN,
+        parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        prediction: Dict[str, object] | NotGiven = NOT_GIVEN,
+        presence_penalty: float | NotGiven = NOT_GIVEN,
+        reasoning_effort: str | NotGiven = NOT_GIVEN,
+        response_format: Dict[str, object] | NotGiven = NOT_GIVEN,
+        seed: int | NotGiven = NOT_GIVEN,
+        stop: Union[str, List[str]] | NotGiven = NOT_GIVEN,
+        store: bool | NotGiven = NOT_GIVEN,
+        stream_options: Dict[str, object] | NotGiven = NOT_GIVEN,
+        temperature: float | NotGiven = NOT_GIVEN,
+        tool_choice: Union[str, Dict[str, object]] | NotGiven = NOT_GIVEN,
+        tools: Iterable[Dict[str, object]] | NotGiven = NOT_GIVEN,
+        top_k: int | NotGiven = NOT_GIVEN,
+        top_logprobs: int | NotGiven = NOT_GIVEN,
+        top_p: float | 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]:
+        """
+        Chat Completions
+
+        Args:
+          messages: openai standard message format
+
+          model: model specified as `model_vendor/model`, for example `openai/gpt-4o`
+
+          stream: If true, partial message deltas will be sent as server-sent events.
+
+          audio: Parameters for audio output. Required when audio output is requested with
+              modalities: ['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.
+
+          function_call: Deprecated in favor of tool_choice. Controls which function is called by the
+              model.
+
+          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. Maps
+              tokens to bias values from -100 to 100.
+
+          logprobs: Whether to return log probabilities of the output tokens or not.
+
+          max_completion_tokens: An upper bound for the number of tokens that can be generated, including visible
+              output tokens and reasoning tokens.
+
+          max_tokens: Deprecated in favor of max_completion_tokens. The maximum number of tokens to
+              generate.
+
+          metadata: Developer-defined tags and values used for filtering completions in the
+              dashboard.
+
+          modalities: Output types that you would like the model to generate for this request.
+
+          n: How many chat completion choices to generate for each input message.
+
+          parallel_tool_calls: Whether to enable parallel function calling during tool use.
+
+          prediction: Static predicted output content, such as the content of a text file being
+              regenerated.
+
+          presence_penalty: Number between -2.0 and 2.0. Positive values penalize tokens based on whether
+              they appear in the text so far.
+
+          reasoning_effort: For o1 models only. Constrains effort on reasoning. Values: low, medium, high.
+
+          response_format: An object specifying the format that the model must output.
+
+          seed: If specified, system will attempt to sample deterministically for repeated
+              requests with same seed.
+
+          stop: Up to 4 sequences where the API will stop generating further tokens.
+
+          store: Whether to store the output for use in model distillation or evals products.
+
+          stream_options: Options for streaming response. Only set this when stream is true.
+
+          temperature: What sampling temperature to use. Higher values make output more random, lower
+              more focused.
+
+          tool_choice: Controls which tool is called by the model. Values: none, auto, required, or
+              specific tool.
+
+          tools: A list of tools the model may call. Currently, only functions are supported. Max
+              128 functions.
+
+          top_k: Only sample from the top K options for each subsequent token
+
+          top_logprobs: Number of most likely tokens to return at each position, with associated log
+              probability.
+
+          top_p: Alternative to temperature. Only tokens comprising top_p probability mass are
+              considered.
+
+          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[Dict[str, object]],
+        model: str,
+        stream: bool,
+        audio: Dict[str, object] | NotGiven = NOT_GIVEN,
+        frequency_penalty: float | NotGiven = NOT_GIVEN,
+        function_call: Dict[str, object] | NotGiven = NOT_GIVEN,
+        functions: Iterable[Dict[str, object]] | NotGiven = NOT_GIVEN,
+        logit_bias: Dict[str, int] | NotGiven = NOT_GIVEN,
+        logprobs: bool | NotGiven = NOT_GIVEN,
+        max_completion_tokens: int | NotGiven = NOT_GIVEN,
+        max_tokens: int | NotGiven = NOT_GIVEN,
+        metadata: Dict[str, str] | NotGiven = NOT_GIVEN,
+        modalities: List[str] | NotGiven = NOT_GIVEN,
+        n: int | NotGiven = NOT_GIVEN,
+        parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        prediction: Dict[str, object] | NotGiven = NOT_GIVEN,
+        presence_penalty: float | NotGiven = NOT_GIVEN,
+        reasoning_effort: str | NotGiven = NOT_GIVEN,
+        response_format: Dict[str, object] | NotGiven = NOT_GIVEN,
+        seed: int | NotGiven = NOT_GIVEN,
+        stop: Union[str, List[str]] | NotGiven = NOT_GIVEN,
+        store: bool | NotGiven = NOT_GIVEN,
+        stream_options: Dict[str, object] | NotGiven = NOT_GIVEN,
+        temperature: float | NotGiven = NOT_GIVEN,
+        tool_choice: Union[str, Dict[str, object]] | NotGiven = NOT_GIVEN,
+        tools: Iterable[Dict[str, object]] | NotGiven = NOT_GIVEN,
+        top_k: int | NotGiven = NOT_GIVEN,
+        top_logprobs: int | NotGiven = NOT_GIVEN,
+        top_p: float | 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,
+    ) -> CompletionCreateResponse | AsyncStream[ChatCompletionChunk]:
+        """
+        Chat Completions
+
+        Args:
+          messages: openai standard message format
+
+          model: model specified as `model_vendor/model`, for example `openai/gpt-4o`
+
+          stream: If true, partial message deltas will be sent as server-sent events.
+
+          audio: Parameters for audio output. Required when audio output is requested with
+              modalities: ['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.
+
+          function_call: Deprecated in favor of tool_choice. Controls which function is called by the
+              model.
+
+          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. Maps
+              tokens to bias values from -100 to 100.
+
+          logprobs: Whether to return log probabilities of the output tokens or not.
+
+          max_completion_tokens: An upper bound for the number of tokens that can be generated, including visible
+              output tokens and reasoning tokens.
+
+          max_tokens: Deprecated in favor of max_completion_tokens. The maximum number of tokens to
+              generate.
+
+          metadata: Developer-defined tags and values used for filtering completions in the
+              dashboard.
+
+          modalities: Output types that you would like the model to generate for this request.
+
+          n: How many chat completion choices to generate for each input message.
+
+          parallel_tool_calls: Whether to enable parallel function calling during tool use.
+
+          prediction: Static predicted output content, such as the content of a text file being
+              regenerated.
+
+          presence_penalty: Number between -2.0 and 2.0. Positive values penalize tokens based on whether
+              they appear in the text so far.
+
+          reasoning_effort: For o1 models only. Constrains effort on reasoning. Values: low, medium, high.
+
+          response_format: An object specifying the format that the model must output.
+
+          seed: If specified, system will attempt to sample deterministically for repeated
+              requests with same seed.
+
+          stop: Up to 4 sequences where the API will stop generating further tokens.
+
+          store: Whether to store the output for use in model distillation or evals products.
+
+          stream_options: Options for streaming response. Only set this when stream is true.
+
+          temperature: What sampling temperature to use. Higher values make output more random, lower
+              more focused.
+
+          tool_choice: Controls which tool is called by the model. Values: none, auto, required, or
+              specific tool.
+
+          tools: A list of tools the model may call. Currently, only functions are supported. Max
+              128 functions.
+
+          top_k: Only sample from the top K options for each subsequent token
+
+          top_logprobs: Number of most likely tokens to return at each position, with associated log
+              probability.
+
+          top_p: Alternative to temperature. Only tokens comprising top_p probability mass are
+              considered.
+
+          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[Dict[str, object]],
+        model: str,
+        audio: Dict[str, object] | NotGiven = NOT_GIVEN,
+        frequency_penalty: float | NotGiven = NOT_GIVEN,
+        function_call: Dict[str, object] | NotGiven = NOT_GIVEN,
+        functions: Iterable[Dict[str, object]] | NotGiven = NOT_GIVEN,
+        logit_bias: Dict[str, int] | NotGiven = NOT_GIVEN,
+        logprobs: bool | NotGiven = NOT_GIVEN,
+        max_completion_tokens: int | NotGiven = NOT_GIVEN,
+        max_tokens: int | NotGiven = NOT_GIVEN,
+        metadata: Dict[str, str] | NotGiven = NOT_GIVEN,
+        modalities: List[str] | NotGiven = NOT_GIVEN,
+        n: int | NotGiven = NOT_GIVEN,
+        parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        prediction: Dict[str, object] | NotGiven = NOT_GIVEN,
+        presence_penalty: float | NotGiven = NOT_GIVEN,
+        reasoning_effort: str | NotGiven = NOT_GIVEN,
+        response_format: Dict[str, object] | NotGiven = NOT_GIVEN,
+        seed: int | NotGiven = NOT_GIVEN,
+        stop: Union[str, List[str]] | NotGiven = NOT_GIVEN,
+        store: bool | NotGiven = NOT_GIVEN,
+        stream: Literal[False] | Literal[True] | NotGiven = NOT_GIVEN,
+        stream_options: Dict[str, object] | NotGiven = NOT_GIVEN,
+        temperature: float | NotGiven = NOT_GIVEN,
+        tool_choice: Union[str, Dict[str, object]] | NotGiven = NOT_GIVEN,
+        tools: Iterable[Dict[str, object]] | NotGiven = NOT_GIVEN,
+        top_k: int | NotGiven = NOT_GIVEN,
+        top_logprobs: int | NotGiven = NOT_GIVEN,
+        top_p: float | 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,
+    ) -> CompletionCreateResponse | AsyncStream[ChatCompletionChunk]:
+        return cast(
+            CompletionCreateResponse,
+            await self._post(
+                "/v5/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,
+                        "stop": stop,
+                        "store": store,
+                        "stream": stream,
+                        "stream_options": stream_options,
+                        "temperature": temperature,
+                        "tool_choice": tool_choice,
+                        "tools": tools,
+                        "top_k": top_k,
+                        "top_logprobs": top_logprobs,
+                        "top_p": top_p,
+                    },
+                    completion_create_params.CompletionCreateParams,
+                ),
+                options=make_request_options(
+                    extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+                ),
+                cast_to=cast(
+                    Any, CompletionCreateResponse
+                ),  # Union types cannot be passed in as arguments in the type system
+                stream=stream or False,
+                stream_cls=AsyncStream[ChatCompletionChunk],
+            ),
+        )
+
+
+class CompletionsResourceWithRawResponse:
+    def __init__(self, completions: CompletionsResource) -> None:
+        self._completions = completions
+
+        self.create = to_raw_response_wrapper(
+            completions.create,
+        )
+
+
+class AsyncCompletionsResourceWithRawResponse:
+    def __init__(self, completions: AsyncCompletionsResource) -> None:
+        self._completions = completions
+
+        self.create = async_to_raw_response_wrapper(
+            completions.create,
+        )
+
+
+class CompletionsResourceWithStreamingResponse:
+    def __init__(self, completions: CompletionsResource) -> None:
+        self._completions = completions
+
+        self.create = to_streamed_response_wrapper(
+            completions.create,
+        )
+
+
+class AsyncCompletionsResourceWithStreamingResponse:
+    def __init__(self, completions: AsyncCompletionsResource) -> None:
+        self._completions = completions
+
+        self.create = async_to_streamed_response_wrapper(
+            completions.create,
+        )