Creates a model response. Provide [text](/docs/guides/text) or [image](/docs/guides/images) inputs to generate [text](/docs/guides/text) or [JSON](/docs/guides/structured-outputs) outputs. Have the model call your own [custom code](/docs/guides/function-calling) or use built-in [tools](/docs/guides/tools) like [web search](/docs/guides/tools-web-search) or [file search](/docs/guides/tools-file-search) to use your own data as input for the model's response.

POST /responses
Api key auth
application/json

Body Required

  • metadata object | null

    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.

    Hide metadata attribute Show metadata attribute object | null
    • * string Additional properties
  • temperature number | null

    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.

    Minimum value is 0, maximum value is 2. Default value is 1.

  • top_p number | null

    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.

    Minimum value is 0, maximum value is 1. Default value is 1.

  • user string

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

  • previous_response_id string | null

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

  • model string

    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.

    Any of:
    string-1 string string-2 string string-2 string
  • reasoning object | null

    o-series models only

    Configuration options for reasoning models.

    Hide reasoning attributes Show reasoning attributes object | null
    • effort string | null

      o-series models only

      Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

      Values are low, medium, or high. Default value is medium.

    • generate_summary string | null

      computer_use_preview only

      A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of concise or detailed.

      Values are concise or detailed.

  • max_output_tokens integer | null

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

  • instructions string | null

    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 be not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.

  • text object

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

    Hide text attribute Show text attribute object

    • format object

      An object specifying the format that the model must output.

      Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

      The default format is { "type": "text" } with no additional options.

      Not recommended for gpt-4o and newer models:

      Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.

      One of:
      ResponseFormatText object TextResponseFormatJsonSchema object ResponseFormatJsonObject object

      Default response format. Used to generate text responses.

      Hide attribute Show attribute
      • type string Required

        The type of response format being defined. Always text.

        Value is text.

  • tools array[object]

    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.
    One of:
    FileSearchTool object FunctionTool object ComputerTool object WebSearchTool object

    A tool that searches for relevant content from uploaded files. Learn more about the file search tool.

    Hide attributes Show attributes
    • type string Required

      The type of the file search tool. Always file_search.

      Value is file_search.

    • vector_store_ids array[string] Required

      The IDs of the vector stores to search.

    • max_num_results integer

      The maximum number of results to return. This number should be between 1 and 50 inclusive.

    • filters object

      A filter to apply based on file attributes.

      One of:
      ComparisonFilter object CompoundFilter object

      A filter used to compare a specified attribute key to a given value using a defined comparison operation.

      Hide attributes Show attributes
      • type string Required

        Specifies the comparison operator: eq, ne, gt, gte, lt, lte.

        • eq: equals
        • ne: not equal
        • gt: greater than
        • gte: greater than or equal
        • lt: less than
        • lte: less than or equal

        Values are eq, ne, gt, gte, lt, or lte. Default value is eq.

      • key string Required

        The key to compare against the value.

      • value string | number | boolean Required

        The value to compare against the attribute key; supports string, number, or boolean types.

        One of:
        string-1 string number-2 number boolean-3 boolean
    • ranking_options object

      Ranking options for search.

      Additional properties are NOT allowed.

      Hide ranking_options attributes Show ranking_options attributes object
      • ranker string

        The ranker to use for the file search.

        Values are auto or default-2024-11-15. Default value is auto.

      • score_threshold number

        The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.

        Minimum value is 0, maximum value is 1. Default value is 0.

  • tool_choice string | object

    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.

    One of:
    ToolChoiceOptions string ToolChoiceTypes object ToolChoiceFunction object

    Controls which (if any) tool is called by the model.

    none means the model will not call any tool and instead generates a message.

    auto means the model can pick between generating a message or calling one or more tools.

    required means the model must call one or more tools.

    Values are none, auto, or required.

  • truncation string | null

    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.

    Values are auto or disabled. Default value is disabled.

  • input string | array[object] Required

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

    Learn more:

    One of:
    Text input string Input item list array[object]

    A text input to the model, equivalent to a text input with the user role.

  • include array[string] | null

    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.

    Values are file_search_call.results, message.input_image.image_url, or computer_call_output.output.image_url.

  • parallel_tool_calls boolean | null

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

    Default value is true.

  • store boolean | null

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

    Default value is true.

  • stream boolean | null

    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.

    Default value is false.

Responses

  • 200

    OK

    Hide response attributes Show response attributes object
    • metadata object | null

      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.

      Hide metadata attribute Show metadata attribute object | null
      • * string Additional properties
    • temperature number | null

      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.

      Minimum value is 0, maximum value is 2. Default value is 1.

    • top_p number | null

      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.

      Minimum value is 0, maximum value is 1. Default value is 1.

    • user string

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

    • previous_response_id string | null

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

    • model string

      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.

      Any of:
      string-1 string string-2 string string-2 string
    • reasoning object | null

      o-series models only

      Configuration options for reasoning models.

      Hide reasoning attributes Show reasoning attributes object | null
      • effort string | null

        o-series models only

        Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

        Values are low, medium, or high. Default value is medium.

      • generate_summary string | null

        computer_use_preview only

        A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of concise or detailed.

        Values are concise or detailed.

    • max_output_tokens integer | null

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

    • instructions string | null

      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 be not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.

    • text object

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

      Hide text attribute Show text attribute object

      • format object

        An object specifying the format that the model must output.

        Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

        The default format is { "type": "text" } with no additional options.

        Not recommended for gpt-4o and newer models:

        Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.

        One of:
        ResponseFormatText object TextResponseFormatJsonSchema object ResponseFormatJsonObject object

        Default response format. Used to generate text responses.

        Hide attribute Show attribute
        • type string Required

          The type of response format being defined. Always text.

          Value is text.

    • tools array[object]

      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.
      One of:
      FileSearchTool object FunctionTool object ComputerTool object WebSearchTool object

      A tool that searches for relevant content from uploaded files. Learn more about the file search tool.

      Hide attributes Show attributes
      • type string Required

        The type of the file search tool. Always file_search.

        Value is file_search.

      • vector_store_ids array[string] Required

        The IDs of the vector stores to search.

      • max_num_results integer

        The maximum number of results to return. This number should be between 1 and 50 inclusive.

      • filters object

        A filter to apply based on file attributes.

        One of:
        ComparisonFilter object CompoundFilter object

        A filter used to compare a specified attribute key to a given value using a defined comparison operation.

        Hide attributes Show attributes
        • type string Required

          Specifies the comparison operator: eq, ne, gt, gte, lt, lte.

          • eq: equals
          • ne: not equal
          • gt: greater than
          • gte: greater than or equal
          • lt: less than
          • lte: less than or equal

          Values are eq, ne, gt, gte, lt, or lte. Default value is eq.

        • key string Required

          The key to compare against the value.

        • value string | number | boolean Required

          The value to compare against the attribute key; supports string, number, or boolean types.

          One of:
          string-1 string number-2 number boolean-3 boolean
      • ranking_options object

        Ranking options for search.

        Additional properties are NOT allowed.

        Hide ranking_options attributes Show ranking_options attributes object
        • ranker string

          The ranker to use for the file search.

          Values are auto or default-2024-11-15. Default value is auto.

        • score_threshold number

          The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.

          Minimum value is 0, maximum value is 1. Default value is 0.

    • tool_choice string | object

      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.

      One of:
      ToolChoiceOptions string ToolChoiceTypes object ToolChoiceFunction object

      Controls which (if any) tool is called by the model.

      none means the model will not call any tool and instead generates a message.

      auto means the model can pick between generating a message or calling one or more tools.

      required means the model must call one or more tools.

      Values are none, auto, or required.

    • truncation string | null

      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.

      Values are auto or disabled. Default value is disabled.

    • id string Required

      Unique identifier for this Response.

    • object string Required

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

      Value is response.

    • status string

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

      Values are completed, failed, in_progress, or incomplete.

    • created_at number Required

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

    • error object | null Required

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

      Hide error attributes Show error attributes object | null
      • code string Required

        The error code for the response.

        Values are server_error, rate_limit_exceeded, invalid_prompt, vector_store_timeout, invalid_image, invalid_image_format, invalid_base64_image, invalid_image_url, image_too_large, image_too_small, image_parse_error, image_content_policy_violation, invalid_image_mode, image_file_too_large, unsupported_image_media_type, empty_image_file, failed_to_download_image, or image_file_not_found.

      • message string Required

        A human-readable description of the error.

    • incomplete_details object | null Required

      Details about why the response is incomplete.

      Hide incomplete_details attribute Show incomplete_details attribute object | null
      • reason string

        The reason why the response is incomplete.

        Values are max_output_tokens or content_filter.

    • output array[object] 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.
      Any of:
      OutputMessage object FileSearchToolCall object FunctionToolCall object WebSearchToolCall object ComputerToolCall object ReasoningItem object

      An output message from the model.

      Hide attributes Show attributes
      • id string Required

        The unique ID of the output message.

      • type string Required Discriminator

        The type of the output message. Always message.

        Value is message.

      • role string Required

        The role of the output message. Always assistant.

        Value is assistant.

      • content array[object] Required

        The content of the output message.

        One of:
        OutputText object Refusal object

        A text output from the model.

        Hide attributes Show attributes
        • type string Required

          The type of the output text. Always output_text.

          Value is output_text.

        • text string Required

          The text output from the model.

        • annotations array[object] Required

          The annotations of the text output.

          One of:
          FileCitation object UrlCitation object FilePath object

          A citation to a file.

          Hide attributes Show attributes
          • type string Required

            The type of the file citation. Always file_citation.

            Value is file_citation.

          • index integer Required

            The index of the file in the list of files.

          • file_id string Required

            The ID of the file.

      • status string Required

        The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.

        Values are in_progress, completed, or incomplete.

    • output_text string | null

      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.

    • usage object

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

      Hide usage attributes Show usage attributes object
      • input_tokens integer Required

        The number of input tokens.

      • input_tokens_details object Required

        A detailed breakdown of the input tokens.

        Hide input_tokens_details attribute Show input_tokens_details attribute object
      • output_tokens integer Required

        The number of output tokens.

      • output_tokens_details object Required

        A detailed breakdown of the output tokens.

        Hide output_tokens_details attribute Show output_tokens_details attribute object
        • reasoning_tokens integer Required

          The number of reasoning tokens.

      • total_tokens integer Required

        The total number of tokens used.

    • parallel_tool_calls boolean Required

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

      Default value is true.
POST /responses 
curl \
 --request POST 'https://api.openai.com/v1/responses' \
 --header "Authorization: Bearer $ACCESS_TOKEN" \
 --header "Content-Type: application/json" \
 --data '{"metadata":{"additionalProperty1":"string","additionalProperty2":"string"},"temperature":1,"top_p":1,"user":"user-1234","previous_response_id":"string","model":"gpt-4o","reasoning":{"effort":"medium","generate_summary":"concise"},"max_output_tokens":42,"instructions":"string","text":{"format":{"type":"text"}},"tools":[{"type":"file_search","vector_store_ids":["string"],"max_num_results":42,"filters":{"type":"eq","key":"string","value":"string"},"ranking_options":{"ranker":"auto","score_threshold":0}}],"tool_choice":"none","truncation":"disabled","input":"string","include":["file_search_call.results"],"parallel_tool_calls":true,"store":true,"stream":false}'
Request examples 
{
  "metadata": {
    "additionalProperty1": "string",
    "additionalProperty2": "string"
  },
  "temperature": 1,
  "top_p": 1,
  "user": "user-1234",
  "previous_response_id": "string",
  "model": "gpt-4o",
  "reasoning": {
    "effort": "medium",
    "generate_summary": "concise"
  },
  "max_output_tokens": 42,
  "instructions": "string",
  "text": {
    "format": {
      "type": "text"
    }
  },
  "tools": [
    {
      "type": "file_search",
      "vector_store_ids": [
        "string"
      ],
      "max_num_results": 42,
      "filters": {
        "type": "eq",
        "key": "string",
        "value": "string"
      },
      "ranking_options": {
        "ranker": "auto",
        "score_threshold": 0
      }
    }
  ],
  "tool_choice": "none",
  "truncation": "disabled",
  "input": "string",
  "include": [
    "file_search_call.results"
  ],
  "parallel_tool_calls": true,
  "store": true,
  "stream": false
}
Response examples (200) 
{
  "metadata": {
    "additionalProperty1": "string",
    "additionalProperty2": "string"
  },
  "temperature": 1,
  "top_p": 1,
  "user": "user-1234",
  "previous_response_id": "string",
  "model": "gpt-4o",
  "reasoning": {
    "effort": "medium",
    "generate_summary": "concise"
  },
  "max_output_tokens": 42,
  "instructions": "string",
  "text": {
    "format": {
      "type": "text"
    }
  },
  "tools": [
    {
      "type": "file_search",
      "vector_store_ids": [
        "string"
      ],
      "max_num_results": 42,
      "filters": {
        "type": "eq",
        "key": "string",
        "value": "string"
      },
      "ranking_options": {
        "ranker": "auto",
        "score_threshold": 0
      }
    }
  ],
  "tool_choice": "none",
  "truncation": "disabled",
  "id": "string",
  "object": "response",
  "status": "completed",
  "created_at": 42.0,
  "error": {
    "code": "server_error",
    "message": "string"
  },
  "incomplete_details": {
    "reason": "max_output_tokens"
  },
  "output": [
    {
      "id": "string",
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "string",
          "annotations": [
            {
              "type": "file_citation",
              "index": 42,
              "file_id": "string"
            }
          ]
        }
      ],
      "status": "in_progress"
    }
  ],
  "output_text": "string",
  "usage": {
    "input_tokens": 42,
    "input_tokens_details": {
      "cached_tokens": 42
    },
    "output_tokens": 42,
    "output_tokens_details": {
      "reasoning_tokens": 42
    },
    "total_tokens": 42
  },
  "parallel_tool_calls": true
}