Interface ResponseCreateParamsStreaming

interface ResponseCreateParamsStreaming {
    include?: null | ResponseIncludable[];
    input: string | ResponseInput;
    instructions?: null | string;
    max_output_tokens?: null | number;
    metadata?: null | Metadata;
    model: ResponsesModel;
    parallel_tool_calls?: null | boolean;
    previous_response_id?: null | string;
    reasoning?: null | Reasoning;
    store?: null | boolean;
    stream: true;
    temperature?: null | number;
    text?: ResponseTextConfig;
    tool_choice?: ToolChoiceOptions | ToolChoiceTypes | ToolChoiceFunction;
    tools?: OpenAIClient.Responses.Tool[];
    top_p?: null | number;
    truncation?: null | "auto" | "disabled";
    user?: string;
}

Hierarchy

  • ResponseCreateParamsBase
    • ResponseCreateParamsStreaming

Properties

Optionalinclude

include?: null | ResponseIncludable[]

Specify additional output data to include in the model response. Currently supported values are:

  • file_search_call.results: Include the search results of the file search tool call.
  • message.input_image.image_url: Include image urls from the input message.
  • computer_call_output.output.image_url: Include image urls from the computer call output.

input

input: string | ResponseInput

Text, image, or file inputs to the model, used to generate a response.

Learn more:

Optionalinstructions

instructions?: null | string

Inserts a system (or developer) message as the first item in the model's context.

When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.

Optionalmax_output_tokens

max_output_tokens?: null | number

An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.

Optionalmetadata

metadata?: null | Metadata

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

model

model: ResponsesModel

Model ID used to generate the response, like gpt-4o or o1. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.

Optionalparallel_tool_calls

parallel_tool_calls?: null | boolean

Whether to allow the model to run tool calls in parallel.

Optionalprevious_response_id

previous_response_id?: null | string

The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state.

Optionalreasoning

reasoning?: null | Reasoning

o-series models only

Configuration options for reasoning models.

Optionalstore

store?: null | boolean

Whether to store the generated model response for later retrieval via API.

stream

stream: true

If set to true, the model response data will be streamed to the client as it is generated using server-sent events. See the Streaming section below for more information.

Optionaltemperature

temperature?: null | number

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.

Optionaltext

text?: ResponseTextConfig

Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:

Optionaltool_choice

tool_choice?: ToolChoiceOptions | ToolChoiceTypes | ToolChoiceFunction

How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.

Optionaltools

tools?: OpenAIClient.Responses.Tool[]

An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.

The two categories of tools you can provide the model are:

  • Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
  • Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code. Learn more about function calling.

Optionaltop_p

top_p?: null | number

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.

Optionaltruncation

truncation?: null | "auto" | "disabled"

The truncation strategy to use for the model response.

  • auto: If the context of this response and previous ones exceeds the model's context window size, the model will truncate the response to fit the context window by dropping input items in the middle of the conversation.
  • disabled (default): If a model response will exceed the context window size for a model, the request will fail with a 400 error.

Optionaluser

user?: string

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

Settings

Member Visibility

On This Page

Properties
""