Create a model response | Sample

31 body fields

Model response request containing input and generation, tool, caching, streaming, and conversation configuration.

metadataobjectoptional

Key-value metadata associated with the response.

top_logprobsintegeroptional

An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.

temperaturenumberoptional

Sampling temperature configuration for controlling output randomness.

Default:1

top_pnumberoptional

Nucleus sampling configuration.

Default:1

userstringdeprecatedoptional

This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers).

safety_identifierstringoptional

Safety identifier configuration for the request.

prompt_cache_keystringoptional

Key used to group requests for prompt caching.

prompt_cache_retentionstringdeprecatedoptional

Prompt cache retention configuration.

Allowed:in_memory24h

prompt_cache_optionsobjectoptional

Options for prompt caching. Supported for `gpt-5.6` and later models. By default, OpenAI automatically chooses one implicit cache breakpoint. You can add explicit breakpoints to content blocks with `prompt_cache_breakpoint`. Each request can write up to four breakpoints. For cache matching, OpenAI considers up to the latest 80 breakpoints in the conversation, without a content-block lookback limit. Set `mode` to `explicit` to disable the implicit breakpoint. The `ttl` defaults to `30m`, which is currently the only supported value. See the [prompt caching guide](https://developers.openai.com/api/docs/guides/prompt-caching) for current details.

previous_response_idstringoptional

Identifier of a previous response to continue from, or `null`.

modelstringoptional

Model ID used to generate the response, like `gpt-6-astra`. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the [model guide](https://developers.openai.com/api/docs/models) to browse and compare available models.

backgroundbooleanoptional

Whether to process the response in the background, or `null`.

Default:false

max_tool_callsintegeroptional

Maximum number of tool calls allowed, or `null`.

textobjectoptional

Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - [Text inputs and outputs](https://developers.openai.com/api/docs/guides/text) - [Structured Outputs](https://developers.openai.com/api/docs/guides/structured-outputs)

toolsarray<Function>optional

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. We support the following categories of tools: - **Built-in tools**: Tools that are provided by OpenAI that extend the model's capabilities, like [web search](https://developers.openai.com/api/docs/guides/tools-web-search) or [file search](https://developers.openai.com/api/docs/guides/tools-file-search). Learn more about [built-in tools](https://developers.openai.com/api/docs/guides/tools). - **MCP Tools**: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about [MCP Tools](https://developers.openai.com/api/docs/guides/tools-connectors-mcp). - **Function calls (custom tools)**: Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about [function calling](https://developers.openai.com/api/docs/guides/function-calling). You can also use custom tools to call your own code.

tool_choicestringoptional

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.

Allowed:noneautorequired

promptobjectoptional

Prompt configuration or `null`.

service_tierstringoptional

Service tier configuration for the request, or `null`.

Allowed:autodefaultflexscalepriorityfastultrafastDefault:auto

truncationstringdeprecatedoptional

Deprecated truncation configuration, or `null`.

Allowed:autodisabledDefault:disabled

reasoningobjectoptional

Reasoning configuration, or `null`.

inputstringoptional

Text, image, or file inputs to the model, used to generate a response. Learn more: - [Text inputs and outputs](https://developers.openai.com/api/docs/guides/text) - [Image inputs](https://developers.openai.com/api/docs/guides/images-vision) - [File inputs](https://developers.openai.com/api/docs/guides/file-inputs) - [Conversation state](https://developers.openai.com/api/docs/guides/conversation-state) - [Function calling](https://developers.openai.com/api/docs/guides/function-calling)

includearray<string>optional

Additional output fields to include, or `null`.

parallel_tool_callsbooleanoptional

Whether the model may make tool calls in parallel, or `null`.

Default:true

storebooleanoptional

Whether to store the response, or `null`.

Default:true

instructionsstringoptional

Instructions that guide the model's response, or `null`.

moderationobjectoptional

Moderation configuration, or `null`.

streambooleanoptional

Whether to return server-sent streaming events, or `null`.

Default:false

stream_optionsobjectoptional

Options controlling streamed output, or `null`.

Default:null

conversationstring | objectoptional

Conversation configuration associated with the response, or `null`.

Default:null

context_managementarray<object>optional

Context management configuration, or `null`.

max_output_tokensintegeroptional

Maximum number of output tokens, or `null`.

3 status codes

200Returns the created response object, or a stream of server-sent events when streaming is enabled. The response includes its identifier, status, model, output, tool configuration, and usage details.

metadataobjectrequired

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.

top_logprobsintegeroptional

temperaturenumberrequired

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.

Default:1

top_pnumberrequired

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.

Default:1

userstringdeprecatedoptional

safety_identifierstringoptional

A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers).

prompt_cache_keystringoptional

Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](https://developers.openai.com/api/docs/guides/prompt-caching).

prompt_cache_retentionstringdeprecatedoptional

Deprecated. Use `prompt_cache_options.ttl` instead. The retention policy for the prompt cache. Set to `24h` to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. [Learn more](https://developers.openai.com/api/docs/guides/prompt-caching#prompt-cache-retention). This field expresses a maximum retention policy, while `prompt_cache_options.ttl` expresses a minimum cache lifetime. The two fields are independent and do not interact. For `gpt-5.5`, `gpt-5.5-pro`, and future models, only `24h` is supported. For older models that support both `in_memory` and `24h`, the default depends on your organization's data retention policy: - Organizations without ZDR enabled default to `24h`. - Organizations with ZDR enabled default to `in_memory` when `prompt_cache_retention` is not specified.

Allowed:in_memory24h

previous_response_idstringoptional

The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](https://developers.openai.com/api/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`.

modelstringrequired

backgroundbooleanoptional

Whether to run the model response in the background. [Learn more](https://developers.openai.com/api/docs/guides/background).

Default:false

max_tool_callsintegeroptional

The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.

textobjectoptional

toolsarray<Function>required

tool_choicestringrequired

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.

Allowed:noneautorequired

promptobjectoptional

Reference to a prompt template and its variables. [Learn more](https://developers.openai.com/api/docs/guides/text?api-mode=responses#version-prompts-in-code).

service_tierstringoptional

Specifies the processing type used for serving the request. - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'. - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model. - If set to '[flex](https://developers.openai.com/api/docs/guides/flex-processing)', then the request will be processed with the Flex Processing service tier. - To opt-in to [Fast mode](https://developers.openai.com/api/docs/guides/fast-mode) at the request level, include the `service_tier=fast` or `service_tier=priority` parameter for Responses or Chat Completions. The response will show `service_tier=priority` regardless of if you specify `service_tier=fast` or `priority` in your request. - If set to 'ultrafast', then the request will be processed with the access-controlled Ultrafast Processing service tier. This tier is currently available for `gpt-5.6-sol`; a response served through it will show `service_tier=ultrafast`. - When not set, the default behavior is 'auto'. When the `service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.

Allowed:autodefaultflexscalepriorityfastultrafastDefault:auto

truncationstringoptional

The truncation strategy to use for the model response. - `auto`: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. - `disabled` (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.

Allowed:autodisabledDefault:disabled

idstringrequired

Unique identifier for this Response.

objectstringrequired

The object type of this resource - always set to `response`.

Allowed:response

statusstringoptional

The status of the response generation. One of `completed`, `failed`, `in_progress`, `cancelled`, `queued`, or `incomplete`.

Allowed:completedfailedin_progresscancelledqueuedincomplete

created_atnumberrequired

Unix timestamp (in seconds) of when this Response was created.

completed_atnumberoptional

Unix timestamp (in seconds) of when this Response was completed. Only present when the status is `completed`.

errorobjectrequired

An error object returned when the model fails to generate a Response.

incomplete_detailsobjectrequired

Details about why the response is incomplete.

outputarray<OutputMessage>required

An array of content items generated by the model. - The length and order of items in the `output` array is dependent on the model's response. - Rather than accessing the first item in the `output` array and assuming it's an `assistant` message with the content generated by the model, you might consider using the `output_text` property where supported in SDKs.

reasoningobjectoptional

Configuration options for [reasoning models](https://developers.openai.com/api/docs/guides/reasoning).

instructionsstring | arrayrequired

A system (or developer) message inserted into 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.

output_textstringoptional

SDK-only convenience property that contains the aggregated text output from all `output_text` items in the `output` array, if any are present. Supported in the Python and JavaScript SDKs.

usageobjectoptional

Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.

prompt_cache_optionsobjectoptional

The prompt-caching options that were applied to the response. Supported for `gpt-5.6` and later models.

prompt_cache_diagnosticsobjectoptional

Prompt cache diagnostics requested for this response.

moderationobjectoptional

Moderation results for the response input and output, if moderated completions were requested.

parallel_tool_callsbooleanrequired

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

Default:true

conversationobjectoptional

The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.

Default:null

max_output_tokensintegeroptional

An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](https://developers.openai.com/api/docs/guides/reasoning).

429Returned when the request exceeds the rate limit; reduce the request rate and increase it gradually.

One documented failure

slow_down
Your request rate increased too quickly. Please reduce the request rate and gradually increase it again.
Traffic increased too quickly

errorobjectrequired

503Returned when the requested model is temporarily overloaded; retry after a brief delay.

One documented failure

server_is_overloaded
The model is temporarily overloaded. Please retry your request after a brief delay.
The requested model is temporarily overloaded

errorobjectrequired

Error handling

A 429 is returned when the request exceeds the rate limit; reduce the request rate and increase it gradually. A 503 is returned when the requested model is temporarily overloaded; retry after a brief delay. Use valid input, model, tools, and output configuration values, and use max_output_tokens only with a supported token limit.

import { Client } from "acme-sdk";

const client = new Client({
  baseUrl: "https://api.acme.com",
  auth: { bearer: process.env.API_TOKEN },
  retry: {
    maxAttempts: 3,
    retryOn: [
      408,
      425,
      429,
      500,
      502,
      503,
      504,
    ],
    backoffMs: 500,
    maxBackoffMs: 8000,
  },
  timeoutMs: 30000,
});

const result = await client.responses.create({
  metadata: "example",
  topLogprobs: 20,
  temperature: "example",
  topP: "example",
  user: "octocat",
});

{
  "id": "resp_67ccd3a9da748190baa7f1570fe91ac604becb25c45c1d41",
  "object": "response",
  "created_at": 1741476777,
  "status": "completed",
  "completed_at": 1741476778,
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "model": "gpt-6-astra",
  "output": [
    {
      "type": "message",
      "id": "msg_67ccd3acc8d48190a77525dc6de64b4104becb25c45c1d41",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "The image depicts a scenic landscape with a wooden boardwalk or pathway leading through lush, green grass under a blue sky with some clouds. The setting suggests a peaceful natural area, possibly a park or nature reserve. There are trees and shrubs in the background.",
          "annotations": []
        }
      ]
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": null,
  "reasoning": {
    "effort": null,
    "summary": null,
    "context": null
  },
  "store": true,
  "temperature": 1,
  "text": {
    "format": {
      "type": "text"
    }
  },
  "tool_choice": "auto",
  "tools": [],
  "top_p": 1,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 328,
    "input_tokens_details": {
      "cached_tokens": 0,
      "cache_write_tokens": 0
    },
    "output_tokens": 52,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 380
  },
  "user": null
}

Request

Response

Errors