Responses

Create a model response

Changed on

Creates a model response. Provide text or image inputs to generate text or JSON outputs. Have the model call your own custom code or use built-in tools like web search or file search to use your own data as input for the model's response.

post/responses

Request

  • Base URL
    https://api.openai.com/v1
  • URL
    https://api.openai.com/v1/responses
  • Auth
    HTTP bearer

Request body

metadataMetadata nullable

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_logprobsinteger

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.

temperaturenumber nullable

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

top_pnumber nullable

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.

userstring nullable

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.

safety_identifierstring nullable

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 128 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.

prompt_cache_keystring nullable

Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.

prompt_cache_retention'in_memory' | '24h' nullable

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. 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.
previous_response_idstring nullable

The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.

backgroundboolean nullable

Whether to run the model response in the background. Learn more.

max_tool_callsinteger nullable

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.

service_tier'auto' | 'default' | 'flex' | 'scale' | 'priority' | 'fast' | 'ultrafast' nullable

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', then the request will be processed with the Flex Processing service tier.
  • To opt-in to 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.

truncation'auto' | 'disabled' nullable

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.
includeIncludeEnum[] nullable

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

  • web_search_call.action.sources: Include the sources of the web search tool call.
  • code_interpreter_call.outputs: Includes the outputs of python code execution in code interpreter tool call items.
  • computer_call_output.output.image_url: Include image urls from the computer call output.
  • 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.
  • message.output_text.logprobs: Include logprobs with assistant messages.
  • reasoning.encrypted_content: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the store parameter is set to false, or when an organization is enrolled in the zero data retention program).
parallel_tool_callsboolean nullable

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

storeboolean nullable

Whether to store the generated model response for later retrieval via API. Defaults to true when omitted. If set to true, response data will be stored for at least 30 days, subject to the data retention exceptions.

instructionsstring nullable

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.

streamboolean nullable

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.

max_output_tokensinteger nullable

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

Response

OK

metadataMetadata nullable required

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_logprobsinteger nullable

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.

temperaturenumber nullable required

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

top_pnumber nullable required

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.

userstring nullable

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.

safety_identifierstring nullable

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 128 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.

prompt_cache_keystring nullable

Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.

prompt_cache_retention'in_memory' | '24h' nullable

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. 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.
previous_response_idstring nullable

The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.

backgroundboolean nullable

Whether to run the model response in the background. Learn more.

max_tool_callsinteger nullable

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.

service_tier'auto' | 'default' | 'flex' | 'scale' | 'priority' | 'fast' | 'ultrafast' nullable

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', then the request will be processed with the Flex Processing service tier.
  • To opt-in to 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.

truncation'auto' | 'disabled' nullable

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.
idstring required

Unique identifier for this Response.

object'response' required

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

status'completed' | 'failed' | 'in_progress' | 'cancelled' | 'queued' | 'incomplete'

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

created_atnumber required

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

completed_atnumber nullable

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

errorResponseError required(unresolved $ref)
output_textstring nullable

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.

parallel_tool_callsboolean required

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

max_output_tokensinteger nullable

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

Example response

{
  "id": "resp_67ccd3a9da748190baa7f1570fe91ac604becb25c45c1d41",
  "object": "response",
  "access_programs": null,
  "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": [],
          "logprobs": []
        }
      ]
    }
  ],
  "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,
  "metadata": {}
}

Changes

  • 6f5c52c2ff04Revision changes
    • info

      added the new optional request property ///////////

    • info

      added the new optional request property ///////////

    • info

      added the new optional request property ///////////

    • info

      added the new optional request property //////////

    • info

      added the new optional request property //////////

    • info

      added the new optional request property //////////

    • info

      added the new optional request property //////////

    • info

      added the new optional request property //////////

    • info

      added the new optional request property //////////

    • info

      added the new optional request property ///////////

    • info

      added the new optional request property ///////////

    • info

      added the new optional request property ///////////

    • info

      added the optional property /////////// to the response with the status (media type: application/json)

    • info

      added the optional property /////////// to the response with the status (media type: application/json)

    • info

      added the optional property /////////// to the response with the status (media type: application/json)

    • info

      added the optional property /////////// to the response with the status (media type: application/json)

    • info

      added the optional property /////////// to the response with the status (media type: application/json)

    • info

      added the optional property /////////// to the response with the status (media type: application/json)

    • info

      added the optional property /////////// to the response with the status (media type: application/json)

    • info

      added the optional property /////////// to the response with the status (media type: application/json)

    • info

      added the optional property /////////// to the response with the status (media type: application/json)

    • info

      added the optional property //////////// to the response with the status (media type: application/json)

    • info

      added the optional property //////////// to the response with the status (media type: application/json)

    • info

      added the optional property //////////// to the response with the status (media type: application/json)

    • info

      added the optional property ///////////// to the response with the status (media type: application/json)

    • info

      added the optional property ///////////// to the response with the status (media type: application/json)

    • info

      added the optional property ///////////// to the response with the status (media type: application/json)

    • info

      added the optional property ////////// to the response with the status (media type: application/json)

    • info

      added the optional property ////////// to the response with the status (media type: application/json)

    • info

      added the optional property ////////// to the response with the status (media type: application/json)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ////////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ////////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ////////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ////////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ////////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ////////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ////////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ////////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ////////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ////////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ////////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ////////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ////////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ////////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ////////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ///////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property ////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property /////////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////// to the response with the status (media type: text/event-stream)

    • info

      added the optional property //////////// to the response with the status (media type: text/event-stream)

  • 5fc8dd29d58fRevision changes
    • warning

      added the new gpt-6.1-terra enum value to the ///////// response property for the response status (media type: application/json)

    • warning

      added the new gpt-6.1-terra enum value to the ////////////// response property for the response status (media type: text/event-stream)

    • warning

      added the new gpt-6.1-terra enum value to the ////////////// response property for the response status (media type: text/event-stream)

    • warning

      added the new gpt-6.1-terra enum value to the ////////////// response property for the response status (media type: text/event-stream)

    • warning

      added the new gpt-6.1-terra enum value to the ////////////// response property for the response status (media type: text/event-stream)

    • warning

      added the new gpt-6.1-terra enum value to the ////////////// response property for the response status (media type: text/event-stream)

    • warning

      added the new gpt-6.1-terra enum value to the /////////// response property for the response status (media type: text/event-stream)

    • info

      added the new gpt-6.1-terra enum value to the request property /////////