Get a model response
Retrieves a model response with the given ID.
ParametersExpand Collapse
ResponseRetrieveParams params
Additional fields to include in the response. See the include
parameter for Response creation above for more information.
Additional fields to include in the response. See the include
parameter for Response creation above for more information.
When true, stream obfuscation will be enabled. Stream obfuscation adds
random characters to an obfuscation field on streaming delta events
to normalize payload sizes as a mitigation to certain side-channel
attacks. These obfuscation fields are included by default, but add a
small amount of overhead to the data stream. You can set
include_obfuscation to false to optimize for bandwidth if you trust
the network links between your application and the OpenAI API.
The sequence number of the event after which to start streaming.
ReturnsExpand Collapse
class Response:
Unique identifier for this Response.
Unix timestamp (in seconds) of when this Response was created.
An error object returned when the model fails to generate a Response.
An error object returned when the model fails to generate a Response.
Code codeThe error code for the response.
The error code for the response.
A human-readable description of the error.
Optional<IncompleteDetails> incompleteDetailsDetails about why the response is incomplete.
Details about why the response is incomplete.
Optional<Reason> reasonThe reason why the response is incomplete.
The reason why the response is incomplete.
Optional<Instructions> instructionsA 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.
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.
List<ResponseInputItem>
class EasyInputMessage:A message input to the model with a role indicating instruction following
hierarchy. Instructions given with the developer or system role take
precedence over instructions given with the user role. Messages with the
assistant role are presumed to have been generated by the model in previous
interactions.
A message input to the model with a role indicating instruction following
hierarchy. Instructions given with the developer or system role take
precedence over instructions given with the user role. Messages with the
assistant role are presumed to have been generated by the model in previous
interactions.
Content contentText, image, or audio input to the model, used to generate a response.
Can also contain previous assistant responses.
Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
List<ResponseInputContent>
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Role roleThe role of the message input. One of user, assistant, system, or
developer.
The role of the message input. One of user, assistant, system, or
developer.
The type of the message input. Always message.
Message
List<ResponseInputContent> contentA list of one or many input items to the model, containing different content
types.
A list of one or many input items to the model, containing different content types.
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Role roleThe role of the message input. One of user, system, or developer.
The role of the message input. One of user, system, or developer.
Optional<Status> statusThe status of item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the message input. Always set to message.
class ResponseOutputMessage:An output message from the model.
An output message from the model.
The unique ID of the output message.
List<Content> contentThe content of the output message.
The content of the output message.
class ResponseOutputText:A text output from the model.
A text output from the model.
List<Annotation> annotationsThe annotations of the text output.
The annotations of the text output.
class FileCitation:A citation to a file.
A citation to a file.
The ID of the file.
The filename of the file cited.
The index of the file in the list of files.
The type of the file citation. Always file_citation.
class UrlCitation:A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
The index of the last character of the URL citation in the message.
The index of the first character of the URL citation in the message.
The title of the web resource.
The type of the URL citation. Always url_citation.
The URL of the web resource.
class ContainerFileCitation:A citation for a container file used to generate a model response.
A citation for a container file used to generate a model response.
The ID of the container file.
The index of the last character of the container file citation in the message.
The ID of the file.
The filename of the container file cited.
The index of the first character of the container file citation in the message.
The type of the container file citation. Always container_file_citation.
class FilePath:A path to a file.
A path to a file.
The ID of the file.
The index of the file in the list of files.
The type of the file path. Always file_path.
The text output from the model.
The type of the output text. Always output_text.
Optional<List<Logprob>> logprobs
List<TopLogprob> topLogprobs
class ResponseOutputRefusal:A refusal from the model.
A refusal from the model.
The refusal explanation from the model.
The type of the refusal. Always refusal.
The role of the output message. Always assistant.
Status statusThe status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The type of the output message. Always message.
class ResponseFileSearchToolCall:The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
The unique ID of the file search tool call.
The queries used to search for files.
Status statusThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The type of the file search tool call. Always file_search_call.
Optional<List<Result>> resultsThe results of the file search tool call.
The results of the file search tool call.
Optional<Attributes> attributesSet 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, booleans, or numbers.
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, booleans, or numbers.
The unique ID of the file.
The name of the file.
The relevance score of the file - a value between 0 and 1.
The text that was retrieved from the file.
class ResponseComputerToolCall:A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
The unique ID of the computer call.
Action actionA click action.
A click action.
class Click:A click action.
A click action.
Button buttonIndicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Specifies the event type. For a click action, this property is always click.
The x-coordinate where the click occurred.
The y-coordinate where the click occurred.
class DoubleClick:A double click action.
A double click action.
Specifies the event type. For a double click action, this property is always set to double_click.
The x-coordinate where the double click occurred.
The y-coordinate where the double click occurred.
class Drag:A drag action.
A drag action.
List<Path> pathAn array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]
An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]The x-coordinate.
The y-coordinate.
Specifies the event type. For a drag action, this property is always set to drag.
class Keypress:A collection of keypresses the model would like to perform.
A collection of keypresses the model would like to perform.
The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
Specifies the event type. For a keypress action, this property is always set to keypress.
class Move:A mouse move action.
A mouse move action.
Specifies the event type. For a move action, this property is always set to move.
The x-coordinate to move to.
The y-coordinate to move to.
JsonValue;
Specifies the event type. For a screenshot action, this property is always set to screenshot.
class Scroll:A scroll action.
A scroll action.
The horizontal scroll distance.
The vertical scroll distance.
Specifies the event type. For a scroll action, this property is always set to scroll.
The x-coordinate where the scroll occurred.
The y-coordinate where the scroll occurred.
class Type:An action to type in text.
An action to type in text.
The text to type.
Specifies the event type. For a type action, this property is always set to type.
JsonValue;
Specifies the event type. For a wait action, this property is always set to wait.
An identifier used when responding to the tool call with output.
List<PendingSafetyCheck> pendingSafetyChecksThe pending safety checks for the computer call.
The pending safety checks for the computer call.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Status statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the computer call. Always computer_call.
ComputerCallOutput
The ID of the computer tool call that produced the output.
A computer screenshot image used with the computer use tool.
A computer screenshot image used with the computer use tool.
Specifies the event type. For a computer screenshot, this property is
always set to computer_screenshot.
The identifier of an uploaded file that contains the screenshot.
The URL of the screenshot image.
The type of the computer tool call output. Always computer_call_output.
The ID of the computer tool call output.
Optional<List<AcknowledgedSafetyCheck>> acknowledgedSafetyChecksThe safety checks reported by the API that have been acknowledged by the developer.
The safety checks reported by the API that have been acknowledged by the developer.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Optional<Status> statusThe status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
class ResponseFunctionWebSearch:The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
The unique ID of the web search tool call.
Action actionAn object describing the specific action taken in this web search call.
Includes details on how the model used the web (search, open_page, find_in_page).
An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
class Search:Action type "search" - Performs a web search query.
Action type "search" - Performs a web search query.
[DEPRECATED] The search query.
The action type.
The search queries.
Optional<List<Source>> sourcesThe sources used in the search.
The sources used in the search.
The type of source. Always url.
The URL of the source.
class OpenPage:Action type "open_page" - Opens a specific URL from search results.
Action type "open_page" - Opens a specific URL from search results.
The action type.
The URL opened by the model.
class FindInPage:Action type "find_in_page": Searches for a pattern within a loaded page.
Action type "find_in_page": Searches for a pattern within a loaded page.
The pattern or text to search for within the page.
The action type.
The URL of the page searched for the pattern.
Status statusThe status of the web search tool call.
The status of the web search tool call.
The type of the web search tool call. Always web_search_call.
class ResponseFunctionToolCall:A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
A JSON string of the arguments to pass to the function.
The unique ID of the function tool call generated by the model.
The name of the function to run.
The type of the function tool call. Always function_call.
The unique ID of the function tool call.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
FunctionCallOutput
The unique ID of the function tool call generated by the model.
Output outputText, image, or file output of the function tool call.
Text, image, or file output of the function tool call.
class ResponseInputTextContent:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImageContent:An image input to the model. Learn about image inputs
An image input to the model. Learn about image inputs
The type of the input item. Always input_image.
Optional<Detail> detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFileContent:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The base64-encoded data of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
The type of the function tool call output. Always function_call_output.
The unique ID of the function tool call output. Populated when this item is returned via API.
Optional<Status> statusThe status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
class ResponseReasoningItem:A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
The unique identifier of the reasoning content.
List<Summary> summaryReasoning summary content.
Reasoning summary content.
A summary of the reasoning output from the model so far.
The type of the object. Always summary_text.
The type of the object. Always reasoning.
Optional<List<Content>> contentReasoning text content.
Reasoning text content.
The reasoning text from the model.
The type of the reasoning text. Always reasoning_text.
The encrypted content of the reasoning item - populated when a response is
generated with reasoning.encrypted_content in the include parameter.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseCompactionItemParam:A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
The encrypted content of the compaction summary.
The type of the item. Always compaction.
The ID of the compaction item.
ImageGenerationCall
The unique ID of the image generation call.
The generated image encoded in base64.
Status statusThe status of the image generation call.
The status of the image generation call.
The type of the image generation call. Always image_generation_call.
class ResponseCodeInterpreterToolCall:A tool call to run code.
A tool call to run code.
The unique ID of the code interpreter tool call.
The code to run, or null if not available.
The ID of the container used to run the code.
Optional<List<Output>> outputsThe outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
class Logs:The logs output from the code interpreter.
The logs output from the code interpreter.
The logs output from the code interpreter.
The type of the output. Always logs.
class Image:The image output from the code interpreter.
The image output from the code interpreter.
The type of the output. Always image.
The URL of the image output from the code interpreter.
Status statusThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The type of the code interpreter tool call. Always code_interpreter_call.
LocalShellCall
The unique ID of the local shell call.
Action actionExecute a shell command on the server.
Execute a shell command on the server.
The command to run.
Environment variables to set for the command.
The type of the local shell action. Always exec.
Optional timeout in milliseconds for the command.
Optional user to run the command as.
Optional working directory to run the command in.
The unique ID of the local shell tool call generated by the model.
Status statusThe status of the local shell call.
The status of the local shell call.
The type of the local shell call. Always local_shell_call.
LocalShellCallOutput
The unique ID of the local shell tool call generated by the model.
A JSON string of the output of the local shell tool call.
The type of the local shell tool call output. Always local_shell_call_output.
Optional<Status> statusThe status of the item. One of in_progress, completed, or incomplete.
The status of the item. One of in_progress, completed, or incomplete.
ShellCall
Action actionThe shell commands and limits that describe how to run the tool call.
The shell commands and limits that describe how to run the tool call.
Ordered shell commands for the execution environment to run.
Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
Maximum wall-clock time in milliseconds to allow the shell commands to run.
The unique ID of the shell tool call generated by the model.
The type of the item. Always shell_call.
The unique ID of the shell tool call. Populated when this item is returned via API.
Optional<Status> statusThe status of the shell call. One of in_progress, completed, or incomplete.
The status of the shell call. One of in_progress, completed, or incomplete.
ShellCallOutput
The unique ID of the shell tool call generated by the model.
List<ResponseFunctionShellCallOutputContent> outputCaptured chunks of stdout and stderr output, along with their associated outcomes.
Captured chunks of stdout and stderr output, along with their associated outcomes.
Outcome outcomeThe exit or timeout outcome associated with this shell call.
The exit or timeout outcome associated with this shell call.
JsonValue;
The outcome type. Always timeout.
class Exit:Indicates that the shell commands finished and returned an exit code.
Indicates that the shell commands finished and returned an exit code.
The exit code returned by the shell process.
The outcome type. Always exit.
Captured stderr output for the shell call.
Captured stdout output for the shell call.
The type of the item. Always shell_call_output.
The unique ID of the shell tool call output. Populated when this item is returned via API.
The maximum number of UTF-8 characters captured for this shell call's combined output.
Optional<Status> statusThe status of the shell call output.
The status of the shell call output.
ApplyPatchCall
The unique ID of the apply patch tool call generated by the model.
Operation operationThe specific create, delete, or update instruction for the apply_patch tool call.
The specific create, delete, or update instruction for the apply_patch tool call.
class CreateFile:Instruction for creating a new file via the apply_patch tool.
Instruction for creating a new file via the apply_patch tool.
Unified diff content to apply when creating the file.
Path of the file to create relative to the workspace root.
The operation type. Always create_file.
class DeleteFile:Instruction for deleting an existing file via the apply_patch tool.
Instruction for deleting an existing file via the apply_patch tool.
Path of the file to delete relative to the workspace root.
The operation type. Always delete_file.
class UpdateFile:Instruction for updating an existing file via the apply_patch tool.
Instruction for updating an existing file via the apply_patch tool.
Unified diff content to apply to the existing file.
Path of the file to update relative to the workspace root.
The operation type. Always update_file.
Status statusThe status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
The type of the item. Always apply_patch_call.
The unique ID of the apply patch tool call. Populated when this item is returned via API.
ApplyPatchCallOutput
The unique ID of the apply patch tool call generated by the model.
Status statusThe status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
The type of the item. Always apply_patch_call_output.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
McpListTools
The unique ID of the list.
The label of the MCP server.
List<Tool> toolsThe tools available on the server.
The tools available on the server.
The JSON schema describing the tool's input.
The name of the tool.
Additional annotations about the tool.
The description of the tool.
The type of the item. Always mcp_list_tools.
Error message if the server could not list tools.
McpApprovalRequest
The unique ID of the approval request.
A JSON string of arguments for the tool.
The name of the tool to run.
The label of the MCP server making the request.
The type of the item. Always mcp_approval_request.
McpApprovalResponse
The ID of the approval request being answered.
Whether the request was approved.
The type of the item. Always mcp_approval_response.
The unique ID of the approval response
Optional reason for the decision.
McpCall
The unique ID of the tool call.
A JSON string of the arguments passed to the tool.
The name of the tool that was run.
The label of the MCP server running the tool.
The type of the item. Always mcp_call.
Unique identifier for the MCP tool call approval request.
Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
The error from the tool call, if any.
The output from the tool call.
Optional<Status> statusThe status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
class ResponseCustomToolCallOutput:The output of a custom tool call from your code, being sent back to the model.
The output of a custom tool call from your code, being sent back to the model.
The call ID, used to map this custom tool call output to a custom tool call.
Output outputThe output from the custom tool call generated by your code.
Can be a string or an list of output content.
The output from the custom tool call generated by your code. Can be a string or an list of output content.
List<FunctionAndCustomToolCallOutput>
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
The type of the custom tool call output. Always custom_tool_call_output.
The unique ID of the custom tool call output in the OpenAI platform.
class ResponseCustomToolCall:A call to a custom tool created by the model.
A call to a custom tool created by the model.
An identifier used to map this custom tool call to a tool call output.
The input for the custom tool call generated by the model.
The name of the custom tool being called.
The type of the custom tool call. Always custom_tool_call.
The unique ID of the custom tool call in the OpenAI platform.
ItemReference
The ID of the item to reference.
The type of item to reference. Always item_reference.
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.
ResponsesModel modelModel ID used to generate the response, like gpt-4o or o3. 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.
Model ID used to generate the response, like gpt-4o or o3. 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.
enum ChatModel:
ResponsesOnlyModel
The object type of this resource - always set to response.
List<ResponseOutputItem> outputAn 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.
An array of content items generated by the model.
- The length and order of items in the
outputarray is dependent on the model's response. - Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs.
class ResponseOutputMessage:An output message from the model.
An output message from the model.
The unique ID of the output message.
List<Content> contentThe content of the output message.
The content of the output message.
class ResponseOutputText:A text output from the model.
A text output from the model.
List<Annotation> annotationsThe annotations of the text output.
The annotations of the text output.
class FileCitation:A citation to a file.
A citation to a file.
The ID of the file.
The filename of the file cited.
The index of the file in the list of files.
The type of the file citation. Always file_citation.
class UrlCitation:A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
The index of the last character of the URL citation in the message.
The index of the first character of the URL citation in the message.
The title of the web resource.
The type of the URL citation. Always url_citation.
The URL of the web resource.
class ContainerFileCitation:A citation for a container file used to generate a model response.
A citation for a container file used to generate a model response.
The ID of the container file.
The index of the last character of the container file citation in the message.
The ID of the file.
The filename of the container file cited.
The index of the first character of the container file citation in the message.
The type of the container file citation. Always container_file_citation.
class FilePath:A path to a file.
A path to a file.
The ID of the file.
The index of the file in the list of files.
The type of the file path. Always file_path.
The text output from the model.
The type of the output text. Always output_text.
Optional<List<Logprob>> logprobs
List<TopLogprob> topLogprobs
class ResponseOutputRefusal:A refusal from the model.
A refusal from the model.
The refusal explanation from the model.
The type of the refusal. Always refusal.
The role of the output message. Always assistant.
Status statusThe status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The type of the output message. Always message.
class ResponseFileSearchToolCall:The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
The unique ID of the file search tool call.
The queries used to search for files.
Status statusThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The type of the file search tool call. Always file_search_call.
Optional<List<Result>> resultsThe results of the file search tool call.
The results of the file search tool call.
Optional<Attributes> attributesSet 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, booleans, or numbers.
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, booleans, or numbers.
The unique ID of the file.
The name of the file.
The relevance score of the file - a value between 0 and 1.
The text that was retrieved from the file.
class ResponseFunctionToolCall:A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
A JSON string of the arguments to pass to the function.
The unique ID of the function tool call generated by the model.
The name of the function to run.
The type of the function tool call. Always function_call.
The unique ID of the function tool call.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseFunctionWebSearch:The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
The unique ID of the web search tool call.
Action actionAn object describing the specific action taken in this web search call.
Includes details on how the model used the web (search, open_page, find_in_page).
An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
class Search:Action type "search" - Performs a web search query.
Action type "search" - Performs a web search query.
[DEPRECATED] The search query.
The action type.
The search queries.
Optional<List<Source>> sourcesThe sources used in the search.
The sources used in the search.
The type of source. Always url.
The URL of the source.
class OpenPage:Action type "open_page" - Opens a specific URL from search results.
Action type "open_page" - Opens a specific URL from search results.
The action type.
The URL opened by the model.
class FindInPage:Action type "find_in_page": Searches for a pattern within a loaded page.
Action type "find_in_page": Searches for a pattern within a loaded page.
The pattern or text to search for within the page.
The action type.
The URL of the page searched for the pattern.
Status statusThe status of the web search tool call.
The status of the web search tool call.
The type of the web search tool call. Always web_search_call.
class ResponseComputerToolCall:A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
The unique ID of the computer call.
Action actionA click action.
A click action.
class Click:A click action.
A click action.
Button buttonIndicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Specifies the event type. For a click action, this property is always click.
The x-coordinate where the click occurred.
The y-coordinate where the click occurred.
class DoubleClick:A double click action.
A double click action.
Specifies the event type. For a double click action, this property is always set to double_click.
The x-coordinate where the double click occurred.
The y-coordinate where the double click occurred.
class Drag:A drag action.
A drag action.
List<Path> pathAn array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]
An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]The x-coordinate.
The y-coordinate.
Specifies the event type. For a drag action, this property is always set to drag.
class Keypress:A collection of keypresses the model would like to perform.
A collection of keypresses the model would like to perform.
The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
Specifies the event type. For a keypress action, this property is always set to keypress.
class Move:A mouse move action.
A mouse move action.
Specifies the event type. For a move action, this property is always set to move.
The x-coordinate to move to.
The y-coordinate to move to.
JsonValue;
Specifies the event type. For a screenshot action, this property is always set to screenshot.
class Scroll:A scroll action.
A scroll action.
The horizontal scroll distance.
The vertical scroll distance.
Specifies the event type. For a scroll action, this property is always set to scroll.
The x-coordinate where the scroll occurred.
The y-coordinate where the scroll occurred.
class Type:An action to type in text.
An action to type in text.
The text to type.
Specifies the event type. For a type action, this property is always set to type.
JsonValue;
Specifies the event type. For a wait action, this property is always set to wait.
An identifier used when responding to the tool call with output.
List<PendingSafetyCheck> pendingSafetyChecksThe pending safety checks for the computer call.
The pending safety checks for the computer call.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Status statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the computer call. Always computer_call.
class ResponseReasoningItem:A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
The unique identifier of the reasoning content.
List<Summary> summaryReasoning summary content.
Reasoning summary content.
A summary of the reasoning output from the model so far.
The type of the object. Always summary_text.
The type of the object. Always reasoning.
Optional<List<Content>> contentReasoning text content.
Reasoning text content.
The reasoning text from the model.
The type of the reasoning text. Always reasoning_text.
The encrypted content of the reasoning item - populated when a response is
generated with reasoning.encrypted_content in the include parameter.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseCompactionItem:A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
The unique ID of the compaction item.
The encrypted content that was produced by compaction.
The type of the item. Always compaction.
The identifier of the actor that created the item.
ImageGenerationCall
The unique ID of the image generation call.
The generated image encoded in base64.
Status statusThe status of the image generation call.
The status of the image generation call.
The type of the image generation call. Always image_generation_call.
class ResponseCodeInterpreterToolCall:A tool call to run code.
A tool call to run code.
The unique ID of the code interpreter tool call.
The code to run, or null if not available.
The ID of the container used to run the code.
Optional<List<Output>> outputsThe outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
class Logs:The logs output from the code interpreter.
The logs output from the code interpreter.
The logs output from the code interpreter.
The type of the output. Always logs.
class Image:The image output from the code interpreter.
The image output from the code interpreter.
The type of the output. Always image.
The URL of the image output from the code interpreter.
Status statusThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The type of the code interpreter tool call. Always code_interpreter_call.
LocalShellCall
The unique ID of the local shell call.
Action actionExecute a shell command on the server.
Execute a shell command on the server.
The command to run.
Environment variables to set for the command.
The type of the local shell action. Always exec.
Optional timeout in milliseconds for the command.
Optional user to run the command as.
Optional working directory to run the command in.
The unique ID of the local shell tool call generated by the model.
Status statusThe status of the local shell call.
The status of the local shell call.
The type of the local shell call. Always local_shell_call.
class ResponseFunctionShellToolCall:A tool call that executes one or more shell commands in a managed environment.
A tool call that executes one or more shell commands in a managed environment.
The unique ID of the shell tool call. Populated when this item is returned via API.
Action actionThe shell commands and limits that describe how to run the tool call.
The shell commands and limits that describe how to run the tool call.
Optional maximum number of characters to return from each command.
Optional timeout in milliseconds for the commands.
The unique ID of the shell tool call generated by the model.
Status statusThe status of the shell call. One of in_progress, completed, or incomplete.
The status of the shell call. One of in_progress, completed, or incomplete.
The type of the item. Always shell_call.
The ID of the entity that created this tool call.
class ResponseFunctionShellToolCallOutput:The output of a shell tool call that was emitted.
The output of a shell tool call that was emitted.
The unique ID of the shell call output. Populated when this item is returned via API.
The unique ID of the shell tool call generated by the model.
The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
List<Output> outputAn array of shell call output contents
An array of shell call output contents
Outcome outcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
JsonValue;
The outcome type. Always timeout.
class Exit:Indicates that the shell commands finished and returned an exit code.
Indicates that the shell commands finished and returned an exit code.
Exit code from the shell process.
The outcome type. Always exit.
The standard error output that was captured.
The standard output that was captured.
The identifier of the actor that created the item.
Status statusThe status of the shell call output. One of in_progress, completed, or incomplete.
The status of the shell call output. One of in_progress, completed, or incomplete.
The type of the shell call output. Always shell_call_output.
The identifier of the actor that created the item.
class ResponseApplyPatchToolCall:A tool call that applies file diffs by creating, deleting, or updating files.
A tool call that applies file diffs by creating, deleting, or updating files.
The unique ID of the apply patch tool call. Populated when this item is returned via API.
The unique ID of the apply patch tool call generated by the model.
Operation operationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
One of the create_file, delete_file, or update_file operations applied via apply_patch.
class CreateFile:Instruction describing how to create a file via the apply_patch tool.
Instruction describing how to create a file via the apply_patch tool.
Diff to apply.
Path of the file to create.
Create a new file with the provided diff.
class DeleteFile:Instruction describing how to delete a file via the apply_patch tool.
Instruction describing how to delete a file via the apply_patch tool.
Path of the file to delete.
Delete the specified file.
class UpdateFile:Instruction describing how to update a file via the apply_patch tool.
Instruction describing how to update a file via the apply_patch tool.
Diff to apply.
Path of the file to update.
Update an existing file with the provided diff.
Status statusThe status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
The type of the item. Always apply_patch_call.
The ID of the entity that created this tool call.
class ResponseApplyPatchToolCallOutput:The output emitted by an apply patch tool call.
The output emitted by an apply patch tool call.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
The unique ID of the apply patch tool call generated by the model.
Status statusThe status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
The type of the item. Always apply_patch_call_output.
The ID of the entity that created this tool call output.
Optional textual output returned by the apply patch tool.
McpCall
The unique ID of the tool call.
A JSON string of the arguments passed to the tool.
The name of the tool that was run.
The label of the MCP server running the tool.
The type of the item. Always mcp_call.
Unique identifier for the MCP tool call approval request.
Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
The error from the tool call, if any.
The output from the tool call.
Optional<Status> statusThe status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
McpListTools
The unique ID of the list.
The label of the MCP server.
List<Tool> toolsThe tools available on the server.
The tools available on the server.
The JSON schema describing the tool's input.
The name of the tool.
Additional annotations about the tool.
The description of the tool.
The type of the item. Always mcp_list_tools.
Error message if the server could not list tools.
McpApprovalRequest
The unique ID of the approval request.
A JSON string of arguments for the tool.
The name of the tool to run.
The label of the MCP server making the request.
The type of the item. Always mcp_approval_request.
class ResponseCustomToolCall:A call to a custom tool created by the model.
A call to a custom tool created by the model.
An identifier used to map this custom tool call to a tool call output.
The input for the custom tool call generated by the model.
The name of the custom tool being called.
The type of the custom tool call. Always custom_tool_call.
The unique ID of the custom tool call in the OpenAI platform.
Whether to allow the model to run tool calls in parallel.
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.
ToolChoice toolChoiceHow 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.
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.
enum ToolChoiceOptions: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.
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.
class ToolChoiceAllowed:Constrains the tools available to the model to a pre-defined set.
Constrains the tools available to the model to a pre-defined set.
Mode modeConstrains the tools available to the model to a pre-defined set.
auto allows the model to pick from among the allowed tools and generate a
message.
required requires the model to call one or more of the allowed tools.
Constrains the tools available to the model to a pre-defined set.
auto allows the model to pick from among the allowed tools and generate a
message.
required requires the model to call one or more of the allowed tools.
A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[
{ "type": "function", "name": "get_weather" },
{ "type": "mcp", "server_label": "deepwiki" },
{ "type": "image_generation" }
]Allowed tool configuration type. Always allowed_tools.
class ToolChoiceTypes:Indicates that the model should use a built-in tool to generate a response.
Learn more about built-in tools.
Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
Type typeThe type of hosted tool the model should to use. Learn more about
built-in tools.
Allowed values are:
file_searchweb_search_previewcomputer_use_previewcode_interpreterimage_generation
The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
file_searchweb_search_previewcomputer_use_previewcode_interpreterimage_generation
class ToolChoiceFunction:Use this option to force the model to call a specific function.
Use this option to force the model to call a specific function.
The name of the function to call.
For function calling, the type is always function.
class ToolChoiceMcp:Use this option to force the model to call a specific tool on a remote MCP server.
Use this option to force the model to call a specific tool on a remote MCP server.
The label of the MCP server to use.
For MCP tools, the type is always mcp.
The name of the tool to call on the server.
class ToolChoiceCustom:Use this option to force the model to call a specific custom tool.
Use this option to force the model to call a specific custom tool.
The name of the custom tool to call.
For custom tool calling, the type is always custom.
class ToolChoiceApplyPatch:Forces the model to call the apply_patch tool when executing a tool call.
Forces the model to call the apply_patch tool when executing a tool call.
The tool to call. Always apply_patch.
class ToolChoiceShell:Forces the model to call the shell tool when a tool call is required.
Forces the model to call the shell tool when a tool call is required.
The tool to call. Always shell.
List<Tool> toolsAn 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
or file search. Learn more about
built-in 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.
- 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. You can also use
custom tools to call your own code.
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 or file search. Learn more about built-in 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.
- 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. You can also use custom tools to call your own code.
class FunctionTool:Defines a function in your own code the model can choose to call. Learn more about function calling.
Defines a function in your own code the model can choose to call. Learn more about function calling.
The name of the function to call.
A JSON schema object describing the parameters of the function.
Whether to enforce strict parameter validation. Default true.
The type of the function tool. Always function.
A description of the function. Used by the model to determine whether or not to call the function.
class FileSearchTool:A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
The type of the file search tool. Always file_search.
The IDs of the vector stores to search.
Optional<Filters> filtersA filter to apply.
A filter to apply.
class ComparisonFilter:A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
The key to compare against the value.
Type typeSpecifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Value valueThe value to compare against the attribute key; supports string, number, or boolean types.
The value to compare against the attribute key; supports string, number, or boolean types.
List<ComparisonFilterValueItem>
class CompoundFilter:Combine multiple filters using and or or.
Combine multiple filters using and or or.
List<Filter> filtersArray of filters to combine. Items can be ComparisonFilter or CompoundFilter.
Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
class ComparisonFilter:A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
The key to compare against the value.
Type typeSpecifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Value valueThe value to compare against the attribute key; supports string, number, or boolean types.
The value to compare against the attribute key; supports string, number, or boolean types.
List<ComparisonFilterValueItem>
Type typeType of operation: and or or.
Type of operation: and or or.
The maximum number of results to return. This number should be between 1 and 50 inclusive.
Optional<RankingOptions> rankingOptionsRanking options for search.
Ranking options for search.
Optional<HybridSearch> hybridSearchWeights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
The weight of the embedding in the reciprocal ranking fusion.
The weight of the text in the reciprocal ranking fusion.
Optional<Ranker> rankerThe ranker to use for the file search.
The ranker to use for the file search.
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.
class ComputerTool:A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
The height of the computer display.
The width of the computer display.
Environment environmentThe type of computer environment to control.
The type of computer environment to control.
The type of the computer use tool. Always computer_use_preview.
class WebSearchTool:Search the Internet for sources related to the prompt. Learn more about the
web search tool.
Search the Internet for sources related to the prompt. Learn more about the web search tool.
Type typeThe type of the web search tool. One of web_search or web_search_2025_08_26.
The type of the web search tool. One of web_search or web_search_2025_08_26.
Optional<Filters> filtersFilters for the search.
Filters for the search.
Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example: ["pubmed.ncbi.nlm.nih.gov"]
Optional<SearchContextSize> searchContextSizeHigh level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
Optional<UserLocation> userLocationThe approximate location of the user.
The approximate location of the user.
Free text input for the city of the user, e.g. San Francisco.
The two-letter ISO country code of the user, e.g. US.
Free text input for the region of the user, e.g. California.
The IANA timezone of the user, e.g. America/Los_Angeles.
The type of location approximation. Always approximate.
Mcp
A label for this MCP server, used to identify it in tool calls.
The type of the MCP tool. Always mcp.
Optional<AllowedTools> allowedToolsList of allowed tool names or a filter object.
List of allowed tool names or a filter object.
class McpToolFilter:A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
Optional<ConnectorId> connectorIdIdentifier for service connectors, like those available in ChatGPT. One of
server_url or connector_id must be provided. Learn more about service
connectors here.
Currently supported connector_id values are:
- Dropbox:
connector_dropbox
- Gmail:
connector_gmail
- Google Calendar:
connector_googlecalendar
- Google Drive:
connector_googledrive
- Microsoft Teams:
connector_microsoftteams
- Outlook Calendar:
connector_outlookcalendar
- Outlook Email:
connector_outlookemail
- SharePoint:
connector_sharepoint
Identifier for service connectors, like those available in ChatGPT. One of
server_url or connector_id must be provided. Learn more about service
connectors here.
Currently supported connector_id values are:
- Dropbox:
connector_dropbox - Gmail:
connector_gmail - Google Calendar:
connector_googlecalendar - Google Drive:
connector_googledrive - Microsoft Teams:
connector_microsoftteams - Outlook Calendar:
connector_outlookcalendar - Outlook Email:
connector_outlookemail - SharePoint:
connector_sharepoint
Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
Optional<RequireApproval> requireApprovalSpecify which of the MCP server's tools require approval.
Specify which of the MCP server's tools require approval.
class McpToolApprovalFilter:Specify which of the MCP server's tools require approval. Can be
always, never, or a filter object associated with tools
that require approval.
Specify which of the MCP server's tools require approval. Can be
always, never, or a filter object associated with tools
that require approval.
Optional<Always> alwaysA filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
Optional<Never> neverA filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
enum McpToolApprovalSetting:Specify a single approval policy for all tools. One of always or
never. When set to always, all tools will require approval. When
set to never, all tools will not require approval.
Specify a single approval policy for all tools. One of always or
never. When set to always, all tools will require approval. When
set to never, all tools will not require approval.
Optional description of the MCP server, used to provide more context.
The URL for the MCP server. One of server_url or connector_id must be
provided.
CodeInterpreter
Container containerThe code interpreter container. Can be a container ID or an object that
specifies uploaded file IDs to make available to your code, along with an
optional memory_limit setting.
The code interpreter container. Can be a container ID or an object that
specifies uploaded file IDs to make available to your code, along with an
optional memory_limit setting.
class CodeInterpreterToolAuto:Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
Always auto.
An optional list of uploaded files to make available to your code.
Optional<MemoryLimit> memoryLimitThe memory limit for the code interpreter container.
The memory limit for the code interpreter container.
The type of the code interpreter tool. Always code_interpreter.
ImageGeneration
The type of the image generation tool. Always image_generation.
Optional<Action> actionWhether to generate a new image or edit an existing image. Default: auto.
Whether to generate a new image or edit an existing image. Default: auto.
Optional<Background> backgroundBackground type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Optional<InputFidelity> inputFidelityControl how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Optional<InputImageMask> inputImageMaskOptional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
File ID for the mask image.
Base64-encoded mask image.
Optional<Model> modelThe image generation model to use. Default: gpt-image-1.
The image generation model to use. Default: gpt-image-1.
Optional<Moderation> moderationModeration level for the generated image. Default: auto.
Moderation level for the generated image. Default: auto.
Compression level for the output image. Default: 100.
Optional<OutputFormat> outputFormatThe output format of the generated image. One of png, webp, or
jpeg. Default: png.
The output format of the generated image. One of png, webp, or
jpeg. Default: png.
Number of partial images to generate in streaming mode, from 0 (default value) to 3.
Optional<Quality> qualityThe quality of the generated image. One of low, medium, high,
or auto. Default: auto.
The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
Optional<Size> sizeThe size of the generated image. One of 1024x1024, 1024x1536,
1536x1024, or auto. Default: auto.
The size of the generated image. One of 1024x1024, 1024x1536,
1536x1024, or auto. Default: auto.
JsonValue;
The type of the local shell tool. Always local_shell.
class FunctionShellTool:A tool that allows the model to execute shell commands.
A tool that allows the model to execute shell commands.
The type of the shell tool. Always shell.
class CustomTool:A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
The name of the custom tool, used to identify it in tool calls.
The type of the custom tool. Always custom.
Optional description of the custom tool, used to provide more context.
The input format for the custom tool. Default is unconstrained text.
The input format for the custom tool. Default is unconstrained text.
JsonValue;
Unconstrained text format. Always text.
Grammar
The grammar definition.
Syntax syntaxThe syntax of the grammar definition. One of lark or regex.
The syntax of the grammar definition. One of lark or regex.
Grammar format. Always grammar.
class WebSearchPreviewTool:This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
Type typeThe type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
Optional<SearchContextSize> searchContextSizeHigh level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
Optional<UserLocation> userLocationThe user's location.
The user's location.
The type of location approximation. Always approximate.
Free text input for the city of the user, e.g. San Francisco.
The two-letter ISO country code of the user, e.g. US.
Free text input for the region of the user, e.g. California.
The IANA timezone of the user, e.g. America/Los_Angeles.
class ApplyPatchTool:Allows the assistant to create, delete, or update files using unified diffs.
Allows the assistant to create, delete, or update files using unified diffs.
The type of the tool. Always apply_patch.
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.
Whether to run the model response in the background. Learn more.
Unix timestamp (in seconds) of when this Response was completed.
Only present when the status is completed.
Optional<Conversation> conversationThe conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
The unique ID of the conversation that this response was associated with.
An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
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.
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.
Reference to a prompt template and its variables.
Learn more.
Reference to a prompt template and its variables. Learn more.
The unique identifier of the prompt template to use.
Optional<Variables> variablesOptional map of values to substitute in for variables in your
prompt. The substitution values can either be strings, or other
Response input types like images or files.
Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Optional version of the prompt template.
Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
Optional<PromptCacheRetention> promptCacheRetentionThe 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.
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.
gpt-5 and o-series models only
Configuration options for
reasoning models.
gpt-5 and o-series models only
Configuration options for reasoning models.
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1 default to medium reasoning effort, and do not support none.
- The
gpt-5-pro model defaults to (and only supports) high reasoning effort.
xhigh is supported for all models after gpt-5.1-codex-max.
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. - The
gpt-5-promodel defaults to (and only supports)highreasoning effort. xhighis supported for all models aftergpt-5.1-codex-max.
DeprecatedOptional<GenerateSummary> generateSummaryDeprecated: use summary instead.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
Deprecated: use summary instead.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
Optional<Summary> summaryA summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
concise is supported for computer-use-preview models and all reasoning models after gpt-5.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
concise is supported for computer-use-preview models and all reasoning models after gpt-5.
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. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
Optional<ServiceTier> serviceTierSpecifies 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' or 'priority', then the request will be processed with the corresponding service tier.
- 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.
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' or 'priority', then the request will be processed with the corresponding service tier.
- 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.
The status of the response generation. One of completed, failed,
in_progress, cancelled, queued, or incomplete.
The status of the response generation. One of completed, failed,
in_progress, cancelled, queued, or incomplete.
Configuration options for a text response from the model. Can be plain
text or structured JSON data. Learn more:
Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
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.
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.
class ResponseFormatText:Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatTextJsonSchemaConfig:JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
The type of response format being defined. Always json_schema.
A description of what the response format is for, used by the model to determine how to respond in the format.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
class ResponseFormatJsonObject:JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
Optional<Verbosity> verbosityConstrains the verbosity of the model's response. Lower values will result in
more concise responses, while higher values will result in more verbose responses.
Currently supported values are low, medium, and high.
Constrains the verbosity of the model's response. Lower values will result in
more concise responses, while higher values will result in more verbose responses.
Currently supported values are low, medium, and high.
An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.
Optional<Truncation> truncationThe 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.
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.
Represents token usage details including input tokens, output tokens,
a breakdown of output tokens, and the total tokens used.
Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
The number of input tokens.
InputTokensDetails inputTokensDetailsA detailed breakdown of the input tokens.
A detailed breakdown of the input tokens.
The number of tokens that were retrieved from the cache. More on prompt caching.
The number of output tokens.
OutputTokensDetails outputTokensDetailsA detailed breakdown of the output tokens.
A detailed breakdown of the output tokens.
The number of reasoning tokens.
The total number of tokens used.
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.
class ResponseStreamEvent: A class that can be one of several variants.union Emitted when there is a partial audio response.
Emitted when there is a partial audio response.
class ResponseAudioDeltaEvent:Emitted when there is a partial audio response.
Emitted when there is a partial audio response.
A chunk of Base64 encoded response audio bytes.
A sequence number for this chunk of the stream response.
The type of the event. Always response.audio.delta.
class ResponseAudioDoneEvent:Emitted when the audio response is complete.
Emitted when the audio response is complete.
The sequence number of the delta.
The type of the event. Always response.audio.done.
class ResponseAudioTranscriptDeltaEvent:Emitted when there is a partial transcript of audio.
Emitted when there is a partial transcript of audio.
The partial transcript of the audio response.
The sequence number of this event.
The type of the event. Always response.audio.transcript.delta.
class ResponseAudioTranscriptDoneEvent:Emitted when the full audio transcript is completed.
Emitted when the full audio transcript is completed.
The sequence number of this event.
The type of the event. Always response.audio.transcript.done.
class ResponseCodeInterpreterCallCodeDeltaEvent:Emitted when a partial code snippet is streamed by the code interpreter.
Emitted when a partial code snippet is streamed by the code interpreter.
The partial code snippet being streamed by the code interpreter.
The unique identifier of the code interpreter tool call item.
The index of the output item in the response for which the code is being streamed.
The sequence number of this event, used to order streaming events.
The type of the event. Always response.code_interpreter_call_code.delta.
class ResponseCodeInterpreterCallCodeDoneEvent:Emitted when the code snippet is finalized by the code interpreter.
Emitted when the code snippet is finalized by the code interpreter.
The final code snippet output by the code interpreter.
The unique identifier of the code interpreter tool call item.
The index of the output item in the response for which the code is finalized.
The sequence number of this event, used to order streaming events.
The type of the event. Always response.code_interpreter_call_code.done.
class ResponseCodeInterpreterCallCompletedEvent:Emitted when the code interpreter call is completed.
Emitted when the code interpreter call is completed.
The unique identifier of the code interpreter tool call item.
The index of the output item in the response for which the code interpreter call is completed.
The sequence number of this event, used to order streaming events.
The type of the event. Always response.code_interpreter_call.completed.
class ResponseCodeInterpreterCallInProgressEvent:Emitted when a code interpreter call is in progress.
Emitted when a code interpreter call is in progress.
The unique identifier of the code interpreter tool call item.
The index of the output item in the response for which the code interpreter call is in progress.
The sequence number of this event, used to order streaming events.
The type of the event. Always response.code_interpreter_call.in_progress.
class ResponseCodeInterpreterCallInterpretingEvent:Emitted when the code interpreter is actively interpreting the code snippet.
Emitted when the code interpreter is actively interpreting the code snippet.
The unique identifier of the code interpreter tool call item.
The index of the output item in the response for which the code interpreter is interpreting code.
The sequence number of this event, used to order streaming events.
The type of the event. Always response.code_interpreter_call.interpreting.
class ResponseCompletedEvent:Emitted when the model response is complete.
Emitted when the model response is complete.
Response responseProperties of the completed response.
Properties of the completed response.
Unique identifier for this Response.
Unix timestamp (in seconds) of when this Response was created.
An error object returned when the model fails to generate a Response.
An error object returned when the model fails to generate a Response.
Code codeThe error code for the response.
The error code for the response.
A human-readable description of the error.
Optional<IncompleteDetails> incompleteDetailsDetails about why the response is incomplete.
Details about why the response is incomplete.
Optional<Reason> reasonThe reason why the response is incomplete.
The reason why the response is incomplete.
Optional<Instructions> instructionsA 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.
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.
List<ResponseInputItem>
class EasyInputMessage:A message input to the model with a role indicating instruction following
hierarchy. Instructions given with the developer or system role take
precedence over instructions given with the user role. Messages with the
assistant role are presumed to have been generated by the model in previous
interactions.
A message input to the model with a role indicating instruction following
hierarchy. Instructions given with the developer or system role take
precedence over instructions given with the user role. Messages with the
assistant role are presumed to have been generated by the model in previous
interactions.
Content contentText, image, or audio input to the model, used to generate a response.
Can also contain previous assistant responses.
Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
List<ResponseInputContent>
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Role roleThe role of the message input. One of user, assistant, system, or
developer.
The role of the message input. One of user, assistant, system, or
developer.
The type of the message input. Always message.
Message
List<ResponseInputContent> contentA list of one or many input items to the model, containing different content
types.
A list of one or many input items to the model, containing different content types.
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Role roleThe role of the message input. One of user, system, or developer.
The role of the message input. One of user, system, or developer.
Optional<Status> statusThe status of item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the message input. Always set to message.
class ResponseOutputMessage:An output message from the model.
An output message from the model.
The unique ID of the output message.
List<Content> contentThe content of the output message.
The content of the output message.
class ResponseOutputText:A text output from the model.
A text output from the model.
List<Annotation> annotationsThe annotations of the text output.
The annotations of the text output.
class FileCitation:A citation to a file.
A citation to a file.
The ID of the file.
The filename of the file cited.
The index of the file in the list of files.
The type of the file citation. Always file_citation.
class UrlCitation:A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
The index of the last character of the URL citation in the message.
The index of the first character of the URL citation in the message.
The title of the web resource.
The type of the URL citation. Always url_citation.
The URL of the web resource.
class ContainerFileCitation:A citation for a container file used to generate a model response.
A citation for a container file used to generate a model response.
The ID of the container file.
The index of the last character of the container file citation in the message.
The ID of the file.
The filename of the container file cited.
The index of the first character of the container file citation in the message.
The type of the container file citation. Always container_file_citation.
class FilePath:A path to a file.
A path to a file.
The ID of the file.
The index of the file in the list of files.
The type of the file path. Always file_path.
The text output from the model.
The type of the output text. Always output_text.
Optional<List<Logprob>> logprobs
List<TopLogprob> topLogprobs
class ResponseOutputRefusal:A refusal from the model.
A refusal from the model.
The refusal explanation from the model.
The type of the refusal. Always refusal.
The role of the output message. Always assistant.
Status statusThe status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The type of the output message. Always message.
class ResponseFileSearchToolCall:The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
The unique ID of the file search tool call.
The queries used to search for files.
Status statusThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The type of the file search tool call. Always file_search_call.
Optional<List<Result>> resultsThe results of the file search tool call.
The results of the file search tool call.
Optional<Attributes> attributesSet 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, booleans, or numbers.
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, booleans, or numbers.
The unique ID of the file.
The name of the file.
The relevance score of the file - a value between 0 and 1.
The text that was retrieved from the file.
class ResponseComputerToolCall:A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
The unique ID of the computer call.
Action actionA click action.
A click action.
class Click:A click action.
A click action.
Button buttonIndicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Specifies the event type. For a click action, this property is always click.
The x-coordinate where the click occurred.
The y-coordinate where the click occurred.
class DoubleClick:A double click action.
A double click action.
Specifies the event type. For a double click action, this property is always set to double_click.
The x-coordinate where the double click occurred.
The y-coordinate where the double click occurred.
class Drag:A drag action.
A drag action.
List<Path> pathAn array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]
An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]The x-coordinate.
The y-coordinate.
Specifies the event type. For a drag action, this property is always set to drag.
class Keypress:A collection of keypresses the model would like to perform.
A collection of keypresses the model would like to perform.
The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
Specifies the event type. For a keypress action, this property is always set to keypress.
class Move:A mouse move action.
A mouse move action.
Specifies the event type. For a move action, this property is always set to move.
The x-coordinate to move to.
The y-coordinate to move to.
JsonValue;
Specifies the event type. For a screenshot action, this property is always set to screenshot.
class Scroll:A scroll action.
A scroll action.
The horizontal scroll distance.
The vertical scroll distance.
Specifies the event type. For a scroll action, this property is always set to scroll.
The x-coordinate where the scroll occurred.
The y-coordinate where the scroll occurred.
class Type:An action to type in text.
An action to type in text.
The text to type.
Specifies the event type. For a type action, this property is always set to type.
JsonValue;
Specifies the event type. For a wait action, this property is always set to wait.
An identifier used when responding to the tool call with output.
List<PendingSafetyCheck> pendingSafetyChecksThe pending safety checks for the computer call.
The pending safety checks for the computer call.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Status statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the computer call. Always computer_call.
ComputerCallOutput
The ID of the computer tool call that produced the output.
A computer screenshot image used with the computer use tool.
A computer screenshot image used with the computer use tool.
Specifies the event type. For a computer screenshot, this property is
always set to computer_screenshot.
The identifier of an uploaded file that contains the screenshot.
The URL of the screenshot image.
The type of the computer tool call output. Always computer_call_output.
The ID of the computer tool call output.
Optional<List<AcknowledgedSafetyCheck>> acknowledgedSafetyChecksThe safety checks reported by the API that have been acknowledged by the developer.
The safety checks reported by the API that have been acknowledged by the developer.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Optional<Status> statusThe status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
class ResponseFunctionWebSearch:The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
The unique ID of the web search tool call.
Action actionAn object describing the specific action taken in this web search call.
Includes details on how the model used the web (search, open_page, find_in_page).
An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
class Search:Action type "search" - Performs a web search query.
Action type "search" - Performs a web search query.
[DEPRECATED] The search query.
The action type.
The search queries.
Optional<List<Source>> sourcesThe sources used in the search.
The sources used in the search.
The type of source. Always url.
The URL of the source.
class OpenPage:Action type "open_page" - Opens a specific URL from search results.
Action type "open_page" - Opens a specific URL from search results.
The action type.
The URL opened by the model.
class FindInPage:Action type "find_in_page": Searches for a pattern within a loaded page.
Action type "find_in_page": Searches for a pattern within a loaded page.
The pattern or text to search for within the page.
The action type.
The URL of the page searched for the pattern.
Status statusThe status of the web search tool call.
The status of the web search tool call.
The type of the web search tool call. Always web_search_call.
class ResponseFunctionToolCall:A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
A JSON string of the arguments to pass to the function.
The unique ID of the function tool call generated by the model.
The name of the function to run.
The type of the function tool call. Always function_call.
The unique ID of the function tool call.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
FunctionCallOutput
The unique ID of the function tool call generated by the model.
Output outputText, image, or file output of the function tool call.
Text, image, or file output of the function tool call.
class ResponseInputTextContent:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImageContent:An image input to the model. Learn about image inputs
An image input to the model. Learn about image inputs
The type of the input item. Always input_image.
Optional<Detail> detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFileContent:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The base64-encoded data of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
The type of the function tool call output. Always function_call_output.
The unique ID of the function tool call output. Populated when this item is returned via API.
Optional<Status> statusThe status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
class ResponseReasoningItem:A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
The unique identifier of the reasoning content.
List<Summary> summaryReasoning summary content.
Reasoning summary content.
A summary of the reasoning output from the model so far.
The type of the object. Always summary_text.
The type of the object. Always reasoning.
Optional<List<Content>> contentReasoning text content.
Reasoning text content.
The reasoning text from the model.
The type of the reasoning text. Always reasoning_text.
The encrypted content of the reasoning item - populated when a response is
generated with reasoning.encrypted_content in the include parameter.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseCompactionItemParam:A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
The encrypted content of the compaction summary.
The type of the item. Always compaction.
The ID of the compaction item.
ImageGenerationCall
The unique ID of the image generation call.
The generated image encoded in base64.
Status statusThe status of the image generation call.
The status of the image generation call.
The type of the image generation call. Always image_generation_call.
class ResponseCodeInterpreterToolCall:A tool call to run code.
A tool call to run code.
The unique ID of the code interpreter tool call.
The code to run, or null if not available.
The ID of the container used to run the code.
Optional<List<Output>> outputsThe outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
class Logs:The logs output from the code interpreter.
The logs output from the code interpreter.
The logs output from the code interpreter.
The type of the output. Always logs.
class Image:The image output from the code interpreter.
The image output from the code interpreter.
The type of the output. Always image.
The URL of the image output from the code interpreter.
Status statusThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The type of the code interpreter tool call. Always code_interpreter_call.
LocalShellCall
The unique ID of the local shell call.
Action actionExecute a shell command on the server.
Execute a shell command on the server.
The command to run.
Environment variables to set for the command.
The type of the local shell action. Always exec.
Optional timeout in milliseconds for the command.
Optional user to run the command as.
Optional working directory to run the command in.
The unique ID of the local shell tool call generated by the model.
Status statusThe status of the local shell call.
The status of the local shell call.
The type of the local shell call. Always local_shell_call.
LocalShellCallOutput
The unique ID of the local shell tool call generated by the model.
A JSON string of the output of the local shell tool call.
The type of the local shell tool call output. Always local_shell_call_output.
Optional<Status> statusThe status of the item. One of in_progress, completed, or incomplete.
The status of the item. One of in_progress, completed, or incomplete.
ShellCall
Action actionThe shell commands and limits that describe how to run the tool call.
The shell commands and limits that describe how to run the tool call.
Ordered shell commands for the execution environment to run.
Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
Maximum wall-clock time in milliseconds to allow the shell commands to run.
The unique ID of the shell tool call generated by the model.
The type of the item. Always shell_call.
The unique ID of the shell tool call. Populated when this item is returned via API.
Optional<Status> statusThe status of the shell call. One of in_progress, completed, or incomplete.
The status of the shell call. One of in_progress, completed, or incomplete.
ShellCallOutput
The unique ID of the shell tool call generated by the model.
List<ResponseFunctionShellCallOutputContent> outputCaptured chunks of stdout and stderr output, along with their associated outcomes.
Captured chunks of stdout and stderr output, along with their associated outcomes.
Outcome outcomeThe exit or timeout outcome associated with this shell call.
The exit or timeout outcome associated with this shell call.
JsonValue;
The outcome type. Always timeout.
class Exit:Indicates that the shell commands finished and returned an exit code.
Indicates that the shell commands finished and returned an exit code.
The exit code returned by the shell process.
The outcome type. Always exit.
Captured stderr output for the shell call.
Captured stdout output for the shell call.
The type of the item. Always shell_call_output.
The unique ID of the shell tool call output. Populated when this item is returned via API.
The maximum number of UTF-8 characters captured for this shell call's combined output.
Optional<Status> statusThe status of the shell call output.
The status of the shell call output.
ApplyPatchCall
The unique ID of the apply patch tool call generated by the model.
Operation operationThe specific create, delete, or update instruction for the apply_patch tool call.
The specific create, delete, or update instruction for the apply_patch tool call.
class CreateFile:Instruction for creating a new file via the apply_patch tool.
Instruction for creating a new file via the apply_patch tool.
Unified diff content to apply when creating the file.
Path of the file to create relative to the workspace root.
The operation type. Always create_file.
class DeleteFile:Instruction for deleting an existing file via the apply_patch tool.
Instruction for deleting an existing file via the apply_patch tool.
Path of the file to delete relative to the workspace root.
The operation type. Always delete_file.
class UpdateFile:Instruction for updating an existing file via the apply_patch tool.
Instruction for updating an existing file via the apply_patch tool.
Unified diff content to apply to the existing file.
Path of the file to update relative to the workspace root.
The operation type. Always update_file.
Status statusThe status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
The type of the item. Always apply_patch_call.
The unique ID of the apply patch tool call. Populated when this item is returned via API.
ApplyPatchCallOutput
The unique ID of the apply patch tool call generated by the model.
Status statusThe status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
The type of the item. Always apply_patch_call_output.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
McpListTools
The unique ID of the list.
The label of the MCP server.
List<Tool> toolsThe tools available on the server.
The tools available on the server.
The JSON schema describing the tool's input.
The name of the tool.
Additional annotations about the tool.
The description of the tool.
The type of the item. Always mcp_list_tools.
Error message if the server could not list tools.
McpApprovalRequest
The unique ID of the approval request.
A JSON string of arguments for the tool.
The name of the tool to run.
The label of the MCP server making the request.
The type of the item. Always mcp_approval_request.
McpApprovalResponse
The ID of the approval request being answered.
Whether the request was approved.
The type of the item. Always mcp_approval_response.
The unique ID of the approval response
Optional reason for the decision.
McpCall
The unique ID of the tool call.
A JSON string of the arguments passed to the tool.
The name of the tool that was run.
The label of the MCP server running the tool.
The type of the item. Always mcp_call.
Unique identifier for the MCP tool call approval request.
Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
The error from the tool call, if any.
The output from the tool call.
Optional<Status> statusThe status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
class ResponseCustomToolCallOutput:The output of a custom tool call from your code, being sent back to the model.
The output of a custom tool call from your code, being sent back to the model.
The call ID, used to map this custom tool call output to a custom tool call.
Output outputThe output from the custom tool call generated by your code.
Can be a string or an list of output content.
The output from the custom tool call generated by your code. Can be a string or an list of output content.
List<FunctionAndCustomToolCallOutput>
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
The type of the custom tool call output. Always custom_tool_call_output.
The unique ID of the custom tool call output in the OpenAI platform.
class ResponseCustomToolCall:A call to a custom tool created by the model.
A call to a custom tool created by the model.
An identifier used to map this custom tool call to a tool call output.
The input for the custom tool call generated by the model.
The name of the custom tool being called.
The type of the custom tool call. Always custom_tool_call.
The unique ID of the custom tool call in the OpenAI platform.
ItemReference
The ID of the item to reference.
The type of item to reference. Always item_reference.
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.
ResponsesModel modelModel ID used to generate the response, like gpt-4o or o3. 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.
Model ID used to generate the response, like gpt-4o or o3. 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.
enum ChatModel:
ResponsesOnlyModel
The object type of this resource - always set to response.
List<ResponseOutputItem> outputAn 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.
An array of content items generated by the model.
- The length and order of items in the
outputarray is dependent on the model's response. - Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs.
class ResponseOutputMessage:An output message from the model.
An output message from the model.
The unique ID of the output message.
List<Content> contentThe content of the output message.
The content of the output message.
class ResponseOutputText:A text output from the model.
A text output from the model.
List<Annotation> annotationsThe annotations of the text output.
The annotations of the text output.
class FileCitation:A citation to a file.
A citation to a file.
The ID of the file.
The filename of the file cited.
The index of the file in the list of files.
The type of the file citation. Always file_citation.
class UrlCitation:A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
The index of the last character of the URL citation in the message.
The index of the first character of the URL citation in the message.
The title of the web resource.
The type of the URL citation. Always url_citation.
The URL of the web resource.
class ContainerFileCitation:A citation for a container file used to generate a model response.
A citation for a container file used to generate a model response.
The ID of the container file.
The index of the last character of the container file citation in the message.
The ID of the file.
The filename of the container file cited.
The index of the first character of the container file citation in the message.
The type of the container file citation. Always container_file_citation.
class FilePath:A path to a file.
A path to a file.
The ID of the file.
The index of the file in the list of files.
The type of the file path. Always file_path.
The text output from the model.
The type of the output text. Always output_text.
Optional<List<Logprob>> logprobs
List<TopLogprob> topLogprobs
class ResponseOutputRefusal:A refusal from the model.
A refusal from the model.
The refusal explanation from the model.
The type of the refusal. Always refusal.
The role of the output message. Always assistant.
Status statusThe status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The type of the output message. Always message.
class ResponseFileSearchToolCall:The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
The unique ID of the file search tool call.
The queries used to search for files.
Status statusThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The type of the file search tool call. Always file_search_call.
Optional<List<Result>> resultsThe results of the file search tool call.
The results of the file search tool call.
Optional<Attributes> attributesSet 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, booleans, or numbers.
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, booleans, or numbers.
The unique ID of the file.
The name of the file.
The relevance score of the file - a value between 0 and 1.
The text that was retrieved from the file.
class ResponseFunctionToolCall:A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
A JSON string of the arguments to pass to the function.
The unique ID of the function tool call generated by the model.
The name of the function to run.
The type of the function tool call. Always function_call.
The unique ID of the function tool call.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseFunctionWebSearch:The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
The unique ID of the web search tool call.
Action actionAn object describing the specific action taken in this web search call.
Includes details on how the model used the web (search, open_page, find_in_page).
An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
class Search:Action type "search" - Performs a web search query.
Action type "search" - Performs a web search query.
[DEPRECATED] The search query.
The action type.
The search queries.
Optional<List<Source>> sourcesThe sources used in the search.
The sources used in the search.
The type of source. Always url.
The URL of the source.
class OpenPage:Action type "open_page" - Opens a specific URL from search results.
Action type "open_page" - Opens a specific URL from search results.
The action type.
The URL opened by the model.
class FindInPage:Action type "find_in_page": Searches for a pattern within a loaded page.
Action type "find_in_page": Searches for a pattern within a loaded page.
The pattern or text to search for within the page.
The action type.
The URL of the page searched for the pattern.
Status statusThe status of the web search tool call.
The status of the web search tool call.
The type of the web search tool call. Always web_search_call.
class ResponseComputerToolCall:A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
The unique ID of the computer call.
Action actionA click action.
A click action.
class Click:A click action.
A click action.
Button buttonIndicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Specifies the event type. For a click action, this property is always click.
The x-coordinate where the click occurred.
The y-coordinate where the click occurred.
class DoubleClick:A double click action.
A double click action.
Specifies the event type. For a double click action, this property is always set to double_click.
The x-coordinate where the double click occurred.
The y-coordinate where the double click occurred.
class Drag:A drag action.
A drag action.
List<Path> pathAn array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]
An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]The x-coordinate.
The y-coordinate.
Specifies the event type. For a drag action, this property is always set to drag.
class Keypress:A collection of keypresses the model would like to perform.
A collection of keypresses the model would like to perform.
The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
Specifies the event type. For a keypress action, this property is always set to keypress.
class Move:A mouse move action.
A mouse move action.
Specifies the event type. For a move action, this property is always set to move.
The x-coordinate to move to.
The y-coordinate to move to.
JsonValue;
Specifies the event type. For a screenshot action, this property is always set to screenshot.
class Scroll:A scroll action.
A scroll action.
The horizontal scroll distance.
The vertical scroll distance.
Specifies the event type. For a scroll action, this property is always set to scroll.
The x-coordinate where the scroll occurred.
The y-coordinate where the scroll occurred.
class Type:An action to type in text.
An action to type in text.
The text to type.
Specifies the event type. For a type action, this property is always set to type.
JsonValue;
Specifies the event type. For a wait action, this property is always set to wait.
An identifier used when responding to the tool call with output.
List<PendingSafetyCheck> pendingSafetyChecksThe pending safety checks for the computer call.
The pending safety checks for the computer call.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Status statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the computer call. Always computer_call.
class ResponseReasoningItem:A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
The unique identifier of the reasoning content.
List<Summary> summaryReasoning summary content.
Reasoning summary content.
A summary of the reasoning output from the model so far.
The type of the object. Always summary_text.
The type of the object. Always reasoning.
Optional<List<Content>> contentReasoning text content.
Reasoning text content.
The reasoning text from the model.
The type of the reasoning text. Always reasoning_text.
The encrypted content of the reasoning item - populated when a response is
generated with reasoning.encrypted_content in the include parameter.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseCompactionItem:A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
The unique ID of the compaction item.
The encrypted content that was produced by compaction.
The type of the item. Always compaction.
The identifier of the actor that created the item.
ImageGenerationCall
The unique ID of the image generation call.
The generated image encoded in base64.
Status statusThe status of the image generation call.
The status of the image generation call.
The type of the image generation call. Always image_generation_call.
class ResponseCodeInterpreterToolCall:A tool call to run code.
A tool call to run code.
The unique ID of the code interpreter tool call.
The code to run, or null if not available.
The ID of the container used to run the code.
Optional<List<Output>> outputsThe outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
class Logs:The logs output from the code interpreter.
The logs output from the code interpreter.
The logs output from the code interpreter.
The type of the output. Always logs.
class Image:The image output from the code interpreter.
The image output from the code interpreter.
The type of the output. Always image.
The URL of the image output from the code interpreter.
Status statusThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The type of the code interpreter tool call. Always code_interpreter_call.
LocalShellCall
The unique ID of the local shell call.
Action actionExecute a shell command on the server.
Execute a shell command on the server.
The command to run.
Environment variables to set for the command.
The type of the local shell action. Always exec.
Optional timeout in milliseconds for the command.
Optional user to run the command as.
Optional working directory to run the command in.
The unique ID of the local shell tool call generated by the model.
Status statusThe status of the local shell call.
The status of the local shell call.
The type of the local shell call. Always local_shell_call.
class ResponseFunctionShellToolCall:A tool call that executes one or more shell commands in a managed environment.
A tool call that executes one or more shell commands in a managed environment.
The unique ID of the shell tool call. Populated when this item is returned via API.
Action actionThe shell commands and limits that describe how to run the tool call.
The shell commands and limits that describe how to run the tool call.
Optional maximum number of characters to return from each command.
Optional timeout in milliseconds for the commands.
The unique ID of the shell tool call generated by the model.
Status statusThe status of the shell call. One of in_progress, completed, or incomplete.
The status of the shell call. One of in_progress, completed, or incomplete.
The type of the item. Always shell_call.
The ID of the entity that created this tool call.
class ResponseFunctionShellToolCallOutput:The output of a shell tool call that was emitted.
The output of a shell tool call that was emitted.
The unique ID of the shell call output. Populated when this item is returned via API.
The unique ID of the shell tool call generated by the model.
The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
List<Output> outputAn array of shell call output contents
An array of shell call output contents
Outcome outcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
JsonValue;
The outcome type. Always timeout.
class Exit:Indicates that the shell commands finished and returned an exit code.
Indicates that the shell commands finished and returned an exit code.
Exit code from the shell process.
The outcome type. Always exit.
The standard error output that was captured.
The standard output that was captured.
The identifier of the actor that created the item.
Status statusThe status of the shell call output. One of in_progress, completed, or incomplete.
The status of the shell call output. One of in_progress, completed, or incomplete.
The type of the shell call output. Always shell_call_output.
The identifier of the actor that created the item.
class ResponseApplyPatchToolCall:A tool call that applies file diffs by creating, deleting, or updating files.
A tool call that applies file diffs by creating, deleting, or updating files.
The unique ID of the apply patch tool call. Populated when this item is returned via API.
The unique ID of the apply patch tool call generated by the model.
Operation operationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
One of the create_file, delete_file, or update_file operations applied via apply_patch.
class CreateFile:Instruction describing how to create a file via the apply_patch tool.
Instruction describing how to create a file via the apply_patch tool.
Diff to apply.
Path of the file to create.
Create a new file with the provided diff.
class DeleteFile:Instruction describing how to delete a file via the apply_patch tool.
Instruction describing how to delete a file via the apply_patch tool.
Path of the file to delete.
Delete the specified file.
class UpdateFile:Instruction describing how to update a file via the apply_patch tool.
Instruction describing how to update a file via the apply_patch tool.
Diff to apply.
Path of the file to update.
Update an existing file with the provided diff.
Status statusThe status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
The type of the item. Always apply_patch_call.
The ID of the entity that created this tool call.
class ResponseApplyPatchToolCallOutput:The output emitted by an apply patch tool call.
The output emitted by an apply patch tool call.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
The unique ID of the apply patch tool call generated by the model.
Status statusThe status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
The type of the item. Always apply_patch_call_output.
The ID of the entity that created this tool call output.
Optional textual output returned by the apply patch tool.
McpCall
The unique ID of the tool call.
A JSON string of the arguments passed to the tool.
The name of the tool that was run.
The label of the MCP server running the tool.
The type of the item. Always mcp_call.
Unique identifier for the MCP tool call approval request.
Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
The error from the tool call, if any.
The output from the tool call.
Optional<Status> statusThe status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
McpListTools
The unique ID of the list.
The label of the MCP server.
List<Tool> toolsThe tools available on the server.
The tools available on the server.
The JSON schema describing the tool's input.
The name of the tool.
Additional annotations about the tool.
The description of the tool.
The type of the item. Always mcp_list_tools.
Error message if the server could not list tools.
McpApprovalRequest
The unique ID of the approval request.
A JSON string of arguments for the tool.
The name of the tool to run.
The label of the MCP server making the request.
The type of the item. Always mcp_approval_request.
class ResponseCustomToolCall:A call to a custom tool created by the model.
A call to a custom tool created by the model.
An identifier used to map this custom tool call to a tool call output.
The input for the custom tool call generated by the model.
The name of the custom tool being called.
The type of the custom tool call. Always custom_tool_call.
The unique ID of the custom tool call in the OpenAI platform.
Whether to allow the model to run tool calls in parallel.
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.
ToolChoice toolChoiceHow 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.
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.
enum ToolChoiceOptions: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.
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.
class ToolChoiceAllowed:Constrains the tools available to the model to a pre-defined set.
Constrains the tools available to the model to a pre-defined set.
Mode modeConstrains the tools available to the model to a pre-defined set.
auto allows the model to pick from among the allowed tools and generate a
message.
required requires the model to call one or more of the allowed tools.
Constrains the tools available to the model to a pre-defined set.
auto allows the model to pick from among the allowed tools and generate a
message.
required requires the model to call one or more of the allowed tools.
A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[
{ "type": "function", "name": "get_weather" },
{ "type": "mcp", "server_label": "deepwiki" },
{ "type": "image_generation" }
]Allowed tool configuration type. Always allowed_tools.
class ToolChoiceTypes:Indicates that the model should use a built-in tool to generate a response.
Learn more about built-in tools.
Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
Type typeThe type of hosted tool the model should to use. Learn more about
built-in tools.
Allowed values are:
file_searchweb_search_previewcomputer_use_previewcode_interpreterimage_generation
The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
file_searchweb_search_previewcomputer_use_previewcode_interpreterimage_generation
class ToolChoiceFunction:Use this option to force the model to call a specific function.
Use this option to force the model to call a specific function.
The name of the function to call.
For function calling, the type is always function.
class ToolChoiceMcp:Use this option to force the model to call a specific tool on a remote MCP server.
Use this option to force the model to call a specific tool on a remote MCP server.
The label of the MCP server to use.
For MCP tools, the type is always mcp.
The name of the tool to call on the server.
class ToolChoiceCustom:Use this option to force the model to call a specific custom tool.
Use this option to force the model to call a specific custom tool.
The name of the custom tool to call.
For custom tool calling, the type is always custom.
class ToolChoiceApplyPatch:Forces the model to call the apply_patch tool when executing a tool call.
Forces the model to call the apply_patch tool when executing a tool call.
The tool to call. Always apply_patch.
class ToolChoiceShell:Forces the model to call the shell tool when a tool call is required.
Forces the model to call the shell tool when a tool call is required.
The tool to call. Always shell.
List<Tool> toolsAn 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
or file search. Learn more about
built-in 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.
- 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. You can also use
custom tools to call your own code.
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 or file search. Learn more about built-in 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.
- 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. You can also use custom tools to call your own code.
class FunctionTool:Defines a function in your own code the model can choose to call. Learn more about function calling.
Defines a function in your own code the model can choose to call. Learn more about function calling.
The name of the function to call.
A JSON schema object describing the parameters of the function.
Whether to enforce strict parameter validation. Default true.
The type of the function tool. Always function.
A description of the function. Used by the model to determine whether or not to call the function.
class FileSearchTool:A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
The type of the file search tool. Always file_search.
The IDs of the vector stores to search.
Optional<Filters> filtersA filter to apply.
A filter to apply.
class ComparisonFilter:A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
The key to compare against the value.
Type typeSpecifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Value valueThe value to compare against the attribute key; supports string, number, or boolean types.
The value to compare against the attribute key; supports string, number, or boolean types.
List<ComparisonFilterValueItem>
class CompoundFilter:Combine multiple filters using and or or.
Combine multiple filters using and or or.
List<Filter> filtersArray of filters to combine. Items can be ComparisonFilter or CompoundFilter.
Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
class ComparisonFilter:A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
The key to compare against the value.
Type typeSpecifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Value valueThe value to compare against the attribute key; supports string, number, or boolean types.
The value to compare against the attribute key; supports string, number, or boolean types.
List<ComparisonFilterValueItem>
Type typeType of operation: and or or.
Type of operation: and or or.
The maximum number of results to return. This number should be between 1 and 50 inclusive.
Optional<RankingOptions> rankingOptionsRanking options for search.
Ranking options for search.
Optional<HybridSearch> hybridSearchWeights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
The weight of the embedding in the reciprocal ranking fusion.
The weight of the text in the reciprocal ranking fusion.
Optional<Ranker> rankerThe ranker to use for the file search.
The ranker to use for the file search.
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.
class ComputerTool:A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
The height of the computer display.
The width of the computer display.
Environment environmentThe type of computer environment to control.
The type of computer environment to control.
The type of the computer use tool. Always computer_use_preview.
class WebSearchTool:Search the Internet for sources related to the prompt. Learn more about the
web search tool.
Search the Internet for sources related to the prompt. Learn more about the web search tool.
Type typeThe type of the web search tool. One of web_search or web_search_2025_08_26.
The type of the web search tool. One of web_search or web_search_2025_08_26.
Optional<Filters> filtersFilters for the search.
Filters for the search.
Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example: ["pubmed.ncbi.nlm.nih.gov"]
Optional<SearchContextSize> searchContextSizeHigh level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
Optional<UserLocation> userLocationThe approximate location of the user.
The approximate location of the user.
Free text input for the city of the user, e.g. San Francisco.
The two-letter ISO country code of the user, e.g. US.
Free text input for the region of the user, e.g. California.
The IANA timezone of the user, e.g. America/Los_Angeles.
The type of location approximation. Always approximate.
Mcp
A label for this MCP server, used to identify it in tool calls.
The type of the MCP tool. Always mcp.
Optional<AllowedTools> allowedToolsList of allowed tool names or a filter object.
List of allowed tool names or a filter object.
class McpToolFilter:A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
Optional<ConnectorId> connectorIdIdentifier for service connectors, like those available in ChatGPT. One of
server_url or connector_id must be provided. Learn more about service
connectors here.
Currently supported connector_id values are:
- Dropbox:
connector_dropbox
- Gmail:
connector_gmail
- Google Calendar:
connector_googlecalendar
- Google Drive:
connector_googledrive
- Microsoft Teams:
connector_microsoftteams
- Outlook Calendar:
connector_outlookcalendar
- Outlook Email:
connector_outlookemail
- SharePoint:
connector_sharepoint
Identifier for service connectors, like those available in ChatGPT. One of
server_url or connector_id must be provided. Learn more about service
connectors here.
Currently supported connector_id values are:
- Dropbox:
connector_dropbox - Gmail:
connector_gmail - Google Calendar:
connector_googlecalendar - Google Drive:
connector_googledrive - Microsoft Teams:
connector_microsoftteams - Outlook Calendar:
connector_outlookcalendar - Outlook Email:
connector_outlookemail - SharePoint:
connector_sharepoint
Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
Optional<RequireApproval> requireApprovalSpecify which of the MCP server's tools require approval.
Specify which of the MCP server's tools require approval.
class McpToolApprovalFilter:Specify which of the MCP server's tools require approval. Can be
always, never, or a filter object associated with tools
that require approval.
Specify which of the MCP server's tools require approval. Can be
always, never, or a filter object associated with tools
that require approval.
Optional<Always> alwaysA filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
Optional<Never> neverA filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
enum McpToolApprovalSetting:Specify a single approval policy for all tools. One of always or
never. When set to always, all tools will require approval. When
set to never, all tools will not require approval.
Specify a single approval policy for all tools. One of always or
never. When set to always, all tools will require approval. When
set to never, all tools will not require approval.
Optional description of the MCP server, used to provide more context.
The URL for the MCP server. One of server_url or connector_id must be
provided.
CodeInterpreter
Container containerThe code interpreter container. Can be a container ID or an object that
specifies uploaded file IDs to make available to your code, along with an
optional memory_limit setting.
The code interpreter container. Can be a container ID or an object that
specifies uploaded file IDs to make available to your code, along with an
optional memory_limit setting.
class CodeInterpreterToolAuto:Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
Always auto.
An optional list of uploaded files to make available to your code.
Optional<MemoryLimit> memoryLimitThe memory limit for the code interpreter container.
The memory limit for the code interpreter container.
The type of the code interpreter tool. Always code_interpreter.
ImageGeneration
The type of the image generation tool. Always image_generation.
Optional<Action> actionWhether to generate a new image or edit an existing image. Default: auto.
Whether to generate a new image or edit an existing image. Default: auto.
Optional<Background> backgroundBackground type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Optional<InputFidelity> inputFidelityControl how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Optional<InputImageMask> inputImageMaskOptional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
File ID for the mask image.
Base64-encoded mask image.
Optional<Model> modelThe image generation model to use. Default: gpt-image-1.
The image generation model to use. Default: gpt-image-1.
Optional<Moderation> moderationModeration level for the generated image. Default: auto.
Moderation level for the generated image. Default: auto.
Compression level for the output image. Default: 100.
Optional<OutputFormat> outputFormatThe output format of the generated image. One of png, webp, or
jpeg. Default: png.
The output format of the generated image. One of png, webp, or
jpeg. Default: png.
Number of partial images to generate in streaming mode, from 0 (default value) to 3.
Optional<Quality> qualityThe quality of the generated image. One of low, medium, high,
or auto. Default: auto.
The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
Optional<Size> sizeThe size of the generated image. One of 1024x1024, 1024x1536,
1536x1024, or auto. Default: auto.
The size of the generated image. One of 1024x1024, 1024x1536,
1536x1024, or auto. Default: auto.
JsonValue;
The type of the local shell tool. Always local_shell.
class FunctionShellTool:A tool that allows the model to execute shell commands.
A tool that allows the model to execute shell commands.
The type of the shell tool. Always shell.
class CustomTool:A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
The name of the custom tool, used to identify it in tool calls.
The type of the custom tool. Always custom.
Optional description of the custom tool, used to provide more context.
The input format for the custom tool. Default is unconstrained text.
The input format for the custom tool. Default is unconstrained text.
JsonValue;
Unconstrained text format. Always text.
Grammar
The grammar definition.
Syntax syntaxThe syntax of the grammar definition. One of lark or regex.
The syntax of the grammar definition. One of lark or regex.
Grammar format. Always grammar.
class WebSearchPreviewTool:This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
Type typeThe type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
Optional<SearchContextSize> searchContextSizeHigh level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
Optional<UserLocation> userLocationThe user's location.
The user's location.
The type of location approximation. Always approximate.
Free text input for the city of the user, e.g. San Francisco.
The two-letter ISO country code of the user, e.g. US.
Free text input for the region of the user, e.g. California.
The IANA timezone of the user, e.g. America/Los_Angeles.
class ApplyPatchTool:Allows the assistant to create, delete, or update files using unified diffs.
Allows the assistant to create, delete, or update files using unified diffs.
The type of the tool. Always apply_patch.
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.
Whether to run the model response in the background. Learn more.
Unix timestamp (in seconds) of when this Response was completed.
Only present when the status is completed.
Optional<Conversation> conversationThe conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
The unique ID of the conversation that this response was associated with.
An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
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.
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.
Reference to a prompt template and its variables.
Learn more.
Reference to a prompt template and its variables. Learn more.
The unique identifier of the prompt template to use.
Optional<Variables> variablesOptional map of values to substitute in for variables in your
prompt. The substitution values can either be strings, or other
Response input types like images or files.
Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Optional version of the prompt template.
Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
Optional<PromptCacheRetention> promptCacheRetentionThe 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.
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.
gpt-5 and o-series models only
Configuration options for
reasoning models.
gpt-5 and o-series models only
Configuration options for reasoning models.
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1 default to medium reasoning effort, and do not support none.
- The
gpt-5-pro model defaults to (and only supports) high reasoning effort.
xhigh is supported for all models after gpt-5.1-codex-max.
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. - The
gpt-5-promodel defaults to (and only supports)highreasoning effort. xhighis supported for all models aftergpt-5.1-codex-max.
DeprecatedOptional<GenerateSummary> generateSummaryDeprecated: use summary instead.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
Deprecated: use summary instead.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
Optional<Summary> summaryA summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
concise is supported for computer-use-preview models and all reasoning models after gpt-5.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
concise is supported for computer-use-preview models and all reasoning models after gpt-5.
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. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
Optional<ServiceTier> serviceTierSpecifies 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' or 'priority', then the request will be processed with the corresponding service tier.
- 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.
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' or 'priority', then the request will be processed with the corresponding service tier.
- 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.
The status of the response generation. One of completed, failed,
in_progress, cancelled, queued, or incomplete.
The status of the response generation. One of completed, failed,
in_progress, cancelled, queued, or incomplete.
Configuration options for a text response from the model. Can be plain
text or structured JSON data. Learn more:
Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
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.
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.
class ResponseFormatText:Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatTextJsonSchemaConfig:JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
The type of response format being defined. Always json_schema.
A description of what the response format is for, used by the model to determine how to respond in the format.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
class ResponseFormatJsonObject:JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
Optional<Verbosity> verbosityConstrains the verbosity of the model's response. Lower values will result in
more concise responses, while higher values will result in more verbose responses.
Currently supported values are low, medium, and high.
Constrains the verbosity of the model's response. Lower values will result in
more concise responses, while higher values will result in more verbose responses.
Currently supported values are low, medium, and high.
An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.
Optional<Truncation> truncationThe 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.
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.
Represents token usage details including input tokens, output tokens,
a breakdown of output tokens, and the total tokens used.
Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
The number of input tokens.
InputTokensDetails inputTokensDetailsA detailed breakdown of the input tokens.
A detailed breakdown of the input tokens.
The number of tokens that were retrieved from the cache. More on prompt caching.
The number of output tokens.
OutputTokensDetails outputTokensDetailsA detailed breakdown of the output tokens.
A detailed breakdown of the output tokens.
The number of reasoning tokens.
The total number of tokens used.
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.
The sequence number for this event.
The type of the event. Always response.completed.
class ResponseContentPartAddedEvent:Emitted when a new content part is added.
Emitted when a new content part is added.
The index of the content part that was added.
The ID of the output item that the content part was added to.
The index of the output item that the content part was added to.
Part partThe content part that was added.
The content part that was added.
class ResponseOutputText:A text output from the model.
A text output from the model.
List<Annotation> annotationsThe annotations of the text output.
The annotations of the text output.
class FileCitation:A citation to a file.
A citation to a file.
The ID of the file.
The filename of the file cited.
The index of the file in the list of files.
The type of the file citation. Always file_citation.
class UrlCitation:A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
The index of the last character of the URL citation in the message.
The index of the first character of the URL citation in the message.
The title of the web resource.
The type of the URL citation. Always url_citation.
The URL of the web resource.
class ContainerFileCitation:A citation for a container file used to generate a model response.
A citation for a container file used to generate a model response.
The ID of the container file.
The index of the last character of the container file citation in the message.
The ID of the file.
The filename of the container file cited.
The index of the first character of the container file citation in the message.
The type of the container file citation. Always container_file_citation.
class FilePath:A path to a file.
A path to a file.
The ID of the file.
The index of the file in the list of files.
The type of the file path. Always file_path.
The text output from the model.
The type of the output text. Always output_text.
Optional<List<Logprob>> logprobs
List<TopLogprob> topLogprobs
class ResponseOutputRefusal:A refusal from the model.
A refusal from the model.
The refusal explanation from the model.
The type of the refusal. Always refusal.
class ReasoningText:Reasoning text from the model.
Reasoning text from the model.
The reasoning text from the model.
The type of the reasoning text. Always reasoning_text.
The sequence number of this event.
The type of the event. Always response.content_part.added.
class ResponseContentPartDoneEvent:Emitted when a content part is done.
Emitted when a content part is done.
The index of the content part that is done.
The ID of the output item that the content part was added to.
The index of the output item that the content part was added to.
Part partThe content part that is done.
The content part that is done.
class ResponseOutputText:A text output from the model.
A text output from the model.
List<Annotation> annotationsThe annotations of the text output.
The annotations of the text output.
class FileCitation:A citation to a file.
A citation to a file.
The ID of the file.
The filename of the file cited.
The index of the file in the list of files.
The type of the file citation. Always file_citation.
class UrlCitation:A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
The index of the last character of the URL citation in the message.
The index of the first character of the URL citation in the message.
The title of the web resource.
The type of the URL citation. Always url_citation.
The URL of the web resource.
class ContainerFileCitation:A citation for a container file used to generate a model response.
A citation for a container file used to generate a model response.
The ID of the container file.
The index of the last character of the container file citation in the message.
The ID of the file.
The filename of the container file cited.
The index of the first character of the container file citation in the message.
The type of the container file citation. Always container_file_citation.
class FilePath:A path to a file.
A path to a file.
The ID of the file.
The index of the file in the list of files.
The type of the file path. Always file_path.
The text output from the model.
The type of the output text. Always output_text.
Optional<List<Logprob>> logprobs
List<TopLogprob> topLogprobs
class ResponseOutputRefusal:A refusal from the model.
A refusal from the model.
The refusal explanation from the model.
The type of the refusal. Always refusal.
class ReasoningText:Reasoning text from the model.
Reasoning text from the model.
The reasoning text from the model.
The type of the reasoning text. Always reasoning_text.
The sequence number of this event.
The type of the event. Always response.content_part.done.
class ResponseCreatedEvent:An event that is emitted when a response is created.
An event that is emitted when a response is created.
Response responseThe response that was created.
The response that was created.
Unique identifier for this Response.
Unix timestamp (in seconds) of when this Response was created.
An error object returned when the model fails to generate a Response.
An error object returned when the model fails to generate a Response.
Code codeThe error code for the response.
The error code for the response.
A human-readable description of the error.
Optional<IncompleteDetails> incompleteDetailsDetails about why the response is incomplete.
Details about why the response is incomplete.
Optional<Reason> reasonThe reason why the response is incomplete.
The reason why the response is incomplete.
Optional<Instructions> instructionsA 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.
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.
List<ResponseInputItem>
class EasyInputMessage:A message input to the model with a role indicating instruction following
hierarchy. Instructions given with the developer or system role take
precedence over instructions given with the user role. Messages with the
assistant role are presumed to have been generated by the model in previous
interactions.
A message input to the model with a role indicating instruction following
hierarchy. Instructions given with the developer or system role take
precedence over instructions given with the user role. Messages with the
assistant role are presumed to have been generated by the model in previous
interactions.
Content contentText, image, or audio input to the model, used to generate a response.
Can also contain previous assistant responses.
Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
List<ResponseInputContent>
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Role roleThe role of the message input. One of user, assistant, system, or
developer.
The role of the message input. One of user, assistant, system, or
developer.
The type of the message input. Always message.
Message
List<ResponseInputContent> contentA list of one or many input items to the model, containing different content
types.
A list of one or many input items to the model, containing different content types.
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Role roleThe role of the message input. One of user, system, or developer.
The role of the message input. One of user, system, or developer.
Optional<Status> statusThe status of item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the message input. Always set to message.
class ResponseOutputMessage:An output message from the model.
An output message from the model.
The unique ID of the output message.
List<Content> contentThe content of the output message.
The content of the output message.
class ResponseOutputText:A text output from the model.
A text output from the model.
List<Annotation> annotationsThe annotations of the text output.
The annotations of the text output.
class FileCitation:A citation to a file.
A citation to a file.
The ID of the file.
The filename of the file cited.
The index of the file in the list of files.
The type of the file citation. Always file_citation.
class UrlCitation:A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
The index of the last character of the URL citation in the message.
The index of the first character of the URL citation in the message.
The title of the web resource.
The type of the URL citation. Always url_citation.
The URL of the web resource.
class ContainerFileCitation:A citation for a container file used to generate a model response.
A citation for a container file used to generate a model response.
The ID of the container file.
The index of the last character of the container file citation in the message.
The ID of the file.
The filename of the container file cited.
The index of the first character of the container file citation in the message.
The type of the container file citation. Always container_file_citation.
class FilePath:A path to a file.
A path to a file.
The ID of the file.
The index of the file in the list of files.
The type of the file path. Always file_path.
The text output from the model.
The type of the output text. Always output_text.
Optional<List<Logprob>> logprobs
List<TopLogprob> topLogprobs
class ResponseOutputRefusal:A refusal from the model.
A refusal from the model.
The refusal explanation from the model.
The type of the refusal. Always refusal.
The role of the output message. Always assistant.
Status statusThe status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The type of the output message. Always message.
class ResponseFileSearchToolCall:The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
The unique ID of the file search tool call.
The queries used to search for files.
Status statusThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The type of the file search tool call. Always file_search_call.
Optional<List<Result>> resultsThe results of the file search tool call.
The results of the file search tool call.
Optional<Attributes> attributesSet 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, booleans, or numbers.
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, booleans, or numbers.
The unique ID of the file.
The name of the file.
The relevance score of the file - a value between 0 and 1.
The text that was retrieved from the file.
class ResponseComputerToolCall:A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
The unique ID of the computer call.
Action actionA click action.
A click action.
class Click:A click action.
A click action.
Button buttonIndicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Specifies the event type. For a click action, this property is always click.
The x-coordinate where the click occurred.
The y-coordinate where the click occurred.
class DoubleClick:A double click action.
A double click action.
Specifies the event type. For a double click action, this property is always set to double_click.
The x-coordinate where the double click occurred.
The y-coordinate where the double click occurred.
class Drag:A drag action.
A drag action.
List<Path> pathAn array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]
An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]The x-coordinate.
The y-coordinate.
Specifies the event type. For a drag action, this property is always set to drag.
class Keypress:A collection of keypresses the model would like to perform.
A collection of keypresses the model would like to perform.
The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
Specifies the event type. For a keypress action, this property is always set to keypress.
class Move:A mouse move action.
A mouse move action.
Specifies the event type. For a move action, this property is always set to move.
The x-coordinate to move to.
The y-coordinate to move to.
JsonValue;
Specifies the event type. For a screenshot action, this property is always set to screenshot.
class Scroll:A scroll action.
A scroll action.
The horizontal scroll distance.
The vertical scroll distance.
Specifies the event type. For a scroll action, this property is always set to scroll.
The x-coordinate where the scroll occurred.
The y-coordinate where the scroll occurred.
class Type:An action to type in text.
An action to type in text.
The text to type.
Specifies the event type. For a type action, this property is always set to type.
JsonValue;
Specifies the event type. For a wait action, this property is always set to wait.
An identifier used when responding to the tool call with output.
List<PendingSafetyCheck> pendingSafetyChecksThe pending safety checks for the computer call.
The pending safety checks for the computer call.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Status statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the computer call. Always computer_call.
ComputerCallOutput
The ID of the computer tool call that produced the output.
A computer screenshot image used with the computer use tool.
A computer screenshot image used with the computer use tool.
Specifies the event type. For a computer screenshot, this property is
always set to computer_screenshot.
The identifier of an uploaded file that contains the screenshot.
The URL of the screenshot image.
The type of the computer tool call output. Always computer_call_output.
The ID of the computer tool call output.
Optional<List<AcknowledgedSafetyCheck>> acknowledgedSafetyChecksThe safety checks reported by the API that have been acknowledged by the developer.
The safety checks reported by the API that have been acknowledged by the developer.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Optional<Status> statusThe status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
class ResponseFunctionWebSearch:The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
The unique ID of the web search tool call.
Action actionAn object describing the specific action taken in this web search call.
Includes details on how the model used the web (search, open_page, find_in_page).
An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
class Search:Action type "search" - Performs a web search query.
Action type "search" - Performs a web search query.
[DEPRECATED] The search query.
The action type.
The search queries.
Optional<List<Source>> sourcesThe sources used in the search.
The sources used in the search.
The type of source. Always url.
The URL of the source.
class OpenPage:Action type "open_page" - Opens a specific URL from search results.
Action type "open_page" - Opens a specific URL from search results.
The action type.
The URL opened by the model.
class FindInPage:Action type "find_in_page": Searches for a pattern within a loaded page.
Action type "find_in_page": Searches for a pattern within a loaded page.
The pattern or text to search for within the page.
The action type.
The URL of the page searched for the pattern.
Status statusThe status of the web search tool call.
The status of the web search tool call.
The type of the web search tool call. Always web_search_call.
class ResponseFunctionToolCall:A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
A JSON string of the arguments to pass to the function.
The unique ID of the function tool call generated by the model.
The name of the function to run.
The type of the function tool call. Always function_call.
The unique ID of the function tool call.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
FunctionCallOutput
The unique ID of the function tool call generated by the model.
Output outputText, image, or file output of the function tool call.
Text, image, or file output of the function tool call.
class ResponseInputTextContent:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImageContent:An image input to the model. Learn about image inputs
An image input to the model. Learn about image inputs
The type of the input item. Always input_image.
Optional<Detail> detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFileContent:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The base64-encoded data of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
The type of the function tool call output. Always function_call_output.
The unique ID of the function tool call output. Populated when this item is returned via API.
Optional<Status> statusThe status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
class ResponseReasoningItem:A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
The unique identifier of the reasoning content.
List<Summary> summaryReasoning summary content.
Reasoning summary content.
A summary of the reasoning output from the model so far.
The type of the object. Always summary_text.
The type of the object. Always reasoning.
Optional<List<Content>> contentReasoning text content.
Reasoning text content.
The reasoning text from the model.
The type of the reasoning text. Always reasoning_text.
The encrypted content of the reasoning item - populated when a response is
generated with reasoning.encrypted_content in the include parameter.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseCompactionItemParam:A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
The encrypted content of the compaction summary.
The type of the item. Always compaction.
The ID of the compaction item.
ImageGenerationCall
The unique ID of the image generation call.
The generated image encoded in base64.
Status statusThe status of the image generation call.
The status of the image generation call.
The type of the image generation call. Always image_generation_call.
class ResponseCodeInterpreterToolCall:A tool call to run code.
A tool call to run code.
The unique ID of the code interpreter tool call.
The code to run, or null if not available.
The ID of the container used to run the code.
Optional<List<Output>> outputsThe outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
class Logs:The logs output from the code interpreter.
The logs output from the code interpreter.
The logs output from the code interpreter.
The type of the output. Always logs.
class Image:The image output from the code interpreter.
The image output from the code interpreter.
The type of the output. Always image.
The URL of the image output from the code interpreter.
Status statusThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The type of the code interpreter tool call. Always code_interpreter_call.
LocalShellCall
The unique ID of the local shell call.
Action actionExecute a shell command on the server.
Execute a shell command on the server.
The command to run.
Environment variables to set for the command.
The type of the local shell action. Always exec.
Optional timeout in milliseconds for the command.
Optional user to run the command as.
Optional working directory to run the command in.
The unique ID of the local shell tool call generated by the model.
Status statusThe status of the local shell call.
The status of the local shell call.
The type of the local shell call. Always local_shell_call.
LocalShellCallOutput
The unique ID of the local shell tool call generated by the model.
A JSON string of the output of the local shell tool call.
The type of the local shell tool call output. Always local_shell_call_output.
Optional<Status> statusThe status of the item. One of in_progress, completed, or incomplete.
The status of the item. One of in_progress, completed, or incomplete.
ShellCall
Action actionThe shell commands and limits that describe how to run the tool call.
The shell commands and limits that describe how to run the tool call.
Ordered shell commands for the execution environment to run.
Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
Maximum wall-clock time in milliseconds to allow the shell commands to run.
The unique ID of the shell tool call generated by the model.
The type of the item. Always shell_call.
The unique ID of the shell tool call. Populated when this item is returned via API.
Optional<Status> statusThe status of the shell call. One of in_progress, completed, or incomplete.
The status of the shell call. One of in_progress, completed, or incomplete.
ShellCallOutput
The unique ID of the shell tool call generated by the model.
List<ResponseFunctionShellCallOutputContent> outputCaptured chunks of stdout and stderr output, along with their associated outcomes.
Captured chunks of stdout and stderr output, along with their associated outcomes.
Outcome outcomeThe exit or timeout outcome associated with this shell call.
The exit or timeout outcome associated with this shell call.
JsonValue;
The outcome type. Always timeout.
class Exit:Indicates that the shell commands finished and returned an exit code.
Indicates that the shell commands finished and returned an exit code.
The exit code returned by the shell process.
The outcome type. Always exit.
Captured stderr output for the shell call.
Captured stdout output for the shell call.
The type of the item. Always shell_call_output.
The unique ID of the shell tool call output. Populated when this item is returned via API.
The maximum number of UTF-8 characters captured for this shell call's combined output.
Optional<Status> statusThe status of the shell call output.
The status of the shell call output.
ApplyPatchCall
The unique ID of the apply patch tool call generated by the model.
Operation operationThe specific create, delete, or update instruction for the apply_patch tool call.
The specific create, delete, or update instruction for the apply_patch tool call.
class CreateFile:Instruction for creating a new file via the apply_patch tool.
Instruction for creating a new file via the apply_patch tool.
Unified diff content to apply when creating the file.
Path of the file to create relative to the workspace root.
The operation type. Always create_file.
class DeleteFile:Instruction for deleting an existing file via the apply_patch tool.
Instruction for deleting an existing file via the apply_patch tool.
Path of the file to delete relative to the workspace root.
The operation type. Always delete_file.
class UpdateFile:Instruction for updating an existing file via the apply_patch tool.
Instruction for updating an existing file via the apply_patch tool.
Unified diff content to apply to the existing file.
Path of the file to update relative to the workspace root.
The operation type. Always update_file.
Status statusThe status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
The type of the item. Always apply_patch_call.
The unique ID of the apply patch tool call. Populated when this item is returned via API.
ApplyPatchCallOutput
The unique ID of the apply patch tool call generated by the model.
Status statusThe status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
The type of the item. Always apply_patch_call_output.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
McpListTools
The unique ID of the list.
The label of the MCP server.
List<Tool> toolsThe tools available on the server.
The tools available on the server.
The JSON schema describing the tool's input.
The name of the tool.
Additional annotations about the tool.
The description of the tool.
The type of the item. Always mcp_list_tools.
Error message if the server could not list tools.
McpApprovalRequest
The unique ID of the approval request.
A JSON string of arguments for the tool.
The name of the tool to run.
The label of the MCP server making the request.
The type of the item. Always mcp_approval_request.
McpApprovalResponse
The ID of the approval request being answered.
Whether the request was approved.
The type of the item. Always mcp_approval_response.
The unique ID of the approval response
Optional reason for the decision.
McpCall
The unique ID of the tool call.
A JSON string of the arguments passed to the tool.
The name of the tool that was run.
The label of the MCP server running the tool.
The type of the item. Always mcp_call.
Unique identifier for the MCP tool call approval request.
Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
The error from the tool call, if any.
The output from the tool call.
Optional<Status> statusThe status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
class ResponseCustomToolCallOutput:The output of a custom tool call from your code, being sent back to the model.
The output of a custom tool call from your code, being sent back to the model.
The call ID, used to map this custom tool call output to a custom tool call.
Output outputThe output from the custom tool call generated by your code.
Can be a string or an list of output content.
The output from the custom tool call generated by your code. Can be a string or an list of output content.
List<FunctionAndCustomToolCallOutput>
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
The type of the custom tool call output. Always custom_tool_call_output.
The unique ID of the custom tool call output in the OpenAI platform.
class ResponseCustomToolCall:A call to a custom tool created by the model.
A call to a custom tool created by the model.
An identifier used to map this custom tool call to a tool call output.
The input for the custom tool call generated by the model.
The name of the custom tool being called.
The type of the custom tool call. Always custom_tool_call.
The unique ID of the custom tool call in the OpenAI platform.
ItemReference
The ID of the item to reference.
The type of item to reference. Always item_reference.
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.
ResponsesModel modelModel ID used to generate the response, like gpt-4o or o3. 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.
Model ID used to generate the response, like gpt-4o or o3. 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.
enum ChatModel:
ResponsesOnlyModel
The object type of this resource - always set to response.
List<ResponseOutputItem> outputAn 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.
An array of content items generated by the model.
- The length and order of items in the
outputarray is dependent on the model's response. - Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs.
class ResponseOutputMessage:An output message from the model.
An output message from the model.
The unique ID of the output message.
List<Content> contentThe content of the output message.
The content of the output message.
class ResponseOutputText:A text output from the model.
A text output from the model.
List<Annotation> annotationsThe annotations of the text output.
The annotations of the text output.
class FileCitation:A citation to a file.
A citation to a file.
The ID of the file.
The filename of the file cited.
The index of the file in the list of files.
The type of the file citation. Always file_citation.
class UrlCitation:A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
The index of the last character of the URL citation in the message.
The index of the first character of the URL citation in the message.
The title of the web resource.
The type of the URL citation. Always url_citation.
The URL of the web resource.
class ContainerFileCitation:A citation for a container file used to generate a model response.
A citation for a container file used to generate a model response.
The ID of the container file.
The index of the last character of the container file citation in the message.
The ID of the file.
The filename of the container file cited.
The index of the first character of the container file citation in the message.
The type of the container file citation. Always container_file_citation.
class FilePath:A path to a file.
A path to a file.
The ID of the file.
The index of the file in the list of files.
The type of the file path. Always file_path.
The text output from the model.
The type of the output text. Always output_text.
Optional<List<Logprob>> logprobs
List<TopLogprob> topLogprobs
class ResponseOutputRefusal:A refusal from the model.
A refusal from the model.
The refusal explanation from the model.
The type of the refusal. Always refusal.
The role of the output message. Always assistant.
Status statusThe status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The type of the output message. Always message.
class ResponseFileSearchToolCall:The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
The unique ID of the file search tool call.
The queries used to search for files.
Status statusThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The type of the file search tool call. Always file_search_call.
Optional<List<Result>> resultsThe results of the file search tool call.
The results of the file search tool call.
Optional<Attributes> attributesSet 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, booleans, or numbers.
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, booleans, or numbers.
The unique ID of the file.
The name of the file.
The relevance score of the file - a value between 0 and 1.
The text that was retrieved from the file.
class ResponseFunctionToolCall:A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
A JSON string of the arguments to pass to the function.
The unique ID of the function tool call generated by the model.
The name of the function to run.
The type of the function tool call. Always function_call.
The unique ID of the function tool call.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseFunctionWebSearch:The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
The unique ID of the web search tool call.
Action actionAn object describing the specific action taken in this web search call.
Includes details on how the model used the web (search, open_page, find_in_page).
An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
class Search:Action type "search" - Performs a web search query.
Action type "search" - Performs a web search query.
[DEPRECATED] The search query.
The action type.
The search queries.
Optional<List<Source>> sourcesThe sources used in the search.
The sources used in the search.
The type of source. Always url.
The URL of the source.
class OpenPage:Action type "open_page" - Opens a specific URL from search results.
Action type "open_page" - Opens a specific URL from search results.
The action type.
The URL opened by the model.
class FindInPage:Action type "find_in_page": Searches for a pattern within a loaded page.
Action type "find_in_page": Searches for a pattern within a loaded page.
The pattern or text to search for within the page.
The action type.
The URL of the page searched for the pattern.
Status statusThe status of the web search tool call.
The status of the web search tool call.
The type of the web search tool call. Always web_search_call.
class ResponseComputerToolCall:A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
The unique ID of the computer call.
Action actionA click action.
A click action.
class Click:A click action.
A click action.
Button buttonIndicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Specifies the event type. For a click action, this property is always click.
The x-coordinate where the click occurred.
The y-coordinate where the click occurred.
class DoubleClick:A double click action.
A double click action.
Specifies the event type. For a double click action, this property is always set to double_click.
The x-coordinate where the double click occurred.
The y-coordinate where the double click occurred.
class Drag:A drag action.
A drag action.
List<Path> pathAn array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]
An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]The x-coordinate.
The y-coordinate.
Specifies the event type. For a drag action, this property is always set to drag.
class Keypress:A collection of keypresses the model would like to perform.
A collection of keypresses the model would like to perform.
The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
Specifies the event type. For a keypress action, this property is always set to keypress.
class Move:A mouse move action.
A mouse move action.
Specifies the event type. For a move action, this property is always set to move.
The x-coordinate to move to.
The y-coordinate to move to.
JsonValue;
Specifies the event type. For a screenshot action, this property is always set to screenshot.
class Scroll:A scroll action.
A scroll action.
The horizontal scroll distance.
The vertical scroll distance.
Specifies the event type. For a scroll action, this property is always set to scroll.
The x-coordinate where the scroll occurred.
The y-coordinate where the scroll occurred.
class Type:An action to type in text.
An action to type in text.
The text to type.
Specifies the event type. For a type action, this property is always set to type.
JsonValue;
Specifies the event type. For a wait action, this property is always set to wait.
An identifier used when responding to the tool call with output.
List<PendingSafetyCheck> pendingSafetyChecksThe pending safety checks for the computer call.
The pending safety checks for the computer call.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Status statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the computer call. Always computer_call.
class ResponseReasoningItem:A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
The unique identifier of the reasoning content.
List<Summary> summaryReasoning summary content.
Reasoning summary content.
A summary of the reasoning output from the model so far.
The type of the object. Always summary_text.
The type of the object. Always reasoning.
Optional<List<Content>> contentReasoning text content.
Reasoning text content.
The reasoning text from the model.
The type of the reasoning text. Always reasoning_text.
The encrypted content of the reasoning item - populated when a response is
generated with reasoning.encrypted_content in the include parameter.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseCompactionItem:A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
The unique ID of the compaction item.
The encrypted content that was produced by compaction.
The type of the item. Always compaction.
The identifier of the actor that created the item.
ImageGenerationCall
The unique ID of the image generation call.
The generated image encoded in base64.
Status statusThe status of the image generation call.
The status of the image generation call.
The type of the image generation call. Always image_generation_call.
class ResponseCodeInterpreterToolCall:A tool call to run code.
A tool call to run code.
The unique ID of the code interpreter tool call.
The code to run, or null if not available.
The ID of the container used to run the code.
Optional<List<Output>> outputsThe outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
class Logs:The logs output from the code interpreter.
The logs output from the code interpreter.
The logs output from the code interpreter.
The type of the output. Always logs.
class Image:The image output from the code interpreter.
The image output from the code interpreter.
The type of the output. Always image.
The URL of the image output from the code interpreter.
Status statusThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The type of the code interpreter tool call. Always code_interpreter_call.
LocalShellCall
The unique ID of the local shell call.
Action actionExecute a shell command on the server.
Execute a shell command on the server.
The command to run.
Environment variables to set for the command.
The type of the local shell action. Always exec.
Optional timeout in milliseconds for the command.
Optional user to run the command as.
Optional working directory to run the command in.
The unique ID of the local shell tool call generated by the model.
Status statusThe status of the local shell call.
The status of the local shell call.
The type of the local shell call. Always local_shell_call.
class ResponseFunctionShellToolCall:A tool call that executes one or more shell commands in a managed environment.
A tool call that executes one or more shell commands in a managed environment.
The unique ID of the shell tool call. Populated when this item is returned via API.
Action actionThe shell commands and limits that describe how to run the tool call.
The shell commands and limits that describe how to run the tool call.
Optional maximum number of characters to return from each command.
Optional timeout in milliseconds for the commands.
The unique ID of the shell tool call generated by the model.
Status statusThe status of the shell call. One of in_progress, completed, or incomplete.
The status of the shell call. One of in_progress, completed, or incomplete.
The type of the item. Always shell_call.
The ID of the entity that created this tool call.
class ResponseFunctionShellToolCallOutput:The output of a shell tool call that was emitted.
The output of a shell tool call that was emitted.
The unique ID of the shell call output. Populated when this item is returned via API.
The unique ID of the shell tool call generated by the model.
The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
List<Output> outputAn array of shell call output contents
An array of shell call output contents
Outcome outcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
JsonValue;
The outcome type. Always timeout.
class Exit:Indicates that the shell commands finished and returned an exit code.
Indicates that the shell commands finished and returned an exit code.
Exit code from the shell process.
The outcome type. Always exit.
The standard error output that was captured.
The standard output that was captured.
The identifier of the actor that created the item.
Status statusThe status of the shell call output. One of in_progress, completed, or incomplete.
The status of the shell call output. One of in_progress, completed, or incomplete.
The type of the shell call output. Always shell_call_output.
The identifier of the actor that created the item.
class ResponseApplyPatchToolCall:A tool call that applies file diffs by creating, deleting, or updating files.
A tool call that applies file diffs by creating, deleting, or updating files.
The unique ID of the apply patch tool call. Populated when this item is returned via API.
The unique ID of the apply patch tool call generated by the model.
Operation operationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
One of the create_file, delete_file, or update_file operations applied via apply_patch.
class CreateFile:Instruction describing how to create a file via the apply_patch tool.
Instruction describing how to create a file via the apply_patch tool.
Diff to apply.
Path of the file to create.
Create a new file with the provided diff.
class DeleteFile:Instruction describing how to delete a file via the apply_patch tool.
Instruction describing how to delete a file via the apply_patch tool.
Path of the file to delete.
Delete the specified file.
class UpdateFile:Instruction describing how to update a file via the apply_patch tool.
Instruction describing how to update a file via the apply_patch tool.
Diff to apply.
Path of the file to update.
Update an existing file with the provided diff.
Status statusThe status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
The type of the item. Always apply_patch_call.
The ID of the entity that created this tool call.
class ResponseApplyPatchToolCallOutput:The output emitted by an apply patch tool call.
The output emitted by an apply patch tool call.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
The unique ID of the apply patch tool call generated by the model.
Status statusThe status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
The type of the item. Always apply_patch_call_output.
The ID of the entity that created this tool call output.
Optional textual output returned by the apply patch tool.
McpCall
The unique ID of the tool call.
A JSON string of the arguments passed to the tool.
The name of the tool that was run.
The label of the MCP server running the tool.
The type of the item. Always mcp_call.
Unique identifier for the MCP tool call approval request.
Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
The error from the tool call, if any.
The output from the tool call.
Optional<Status> statusThe status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
McpListTools
The unique ID of the list.
The label of the MCP server.
List<Tool> toolsThe tools available on the server.
The tools available on the server.
The JSON schema describing the tool's input.
The name of the tool.
Additional annotations about the tool.
The description of the tool.
The type of the item. Always mcp_list_tools.
Error message if the server could not list tools.
McpApprovalRequest
The unique ID of the approval request.
A JSON string of arguments for the tool.
The name of the tool to run.
The label of the MCP server making the request.
The type of the item. Always mcp_approval_request.
class ResponseCustomToolCall:A call to a custom tool created by the model.
A call to a custom tool created by the model.
An identifier used to map this custom tool call to a tool call output.
The input for the custom tool call generated by the model.
The name of the custom tool being called.
The type of the custom tool call. Always custom_tool_call.
The unique ID of the custom tool call in the OpenAI platform.
Whether to allow the model to run tool calls in parallel.
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.
ToolChoice toolChoiceHow 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.
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.
enum ToolChoiceOptions: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.
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.
class ToolChoiceAllowed:Constrains the tools available to the model to a pre-defined set.
Constrains the tools available to the model to a pre-defined set.
Mode modeConstrains the tools available to the model to a pre-defined set.
auto allows the model to pick from among the allowed tools and generate a
message.
required requires the model to call one or more of the allowed tools.
Constrains the tools available to the model to a pre-defined set.
auto allows the model to pick from among the allowed tools and generate a
message.
required requires the model to call one or more of the allowed tools.
A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[
{ "type": "function", "name": "get_weather" },
{ "type": "mcp", "server_label": "deepwiki" },
{ "type": "image_generation" }
]Allowed tool configuration type. Always allowed_tools.
class ToolChoiceTypes:Indicates that the model should use a built-in tool to generate a response.
Learn more about built-in tools.
Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
Type typeThe type of hosted tool the model should to use. Learn more about
built-in tools.
Allowed values are:
file_searchweb_search_previewcomputer_use_previewcode_interpreterimage_generation
The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
file_searchweb_search_previewcomputer_use_previewcode_interpreterimage_generation
class ToolChoiceFunction:Use this option to force the model to call a specific function.
Use this option to force the model to call a specific function.
The name of the function to call.
For function calling, the type is always function.
class ToolChoiceMcp:Use this option to force the model to call a specific tool on a remote MCP server.
Use this option to force the model to call a specific tool on a remote MCP server.
The label of the MCP server to use.
For MCP tools, the type is always mcp.
The name of the tool to call on the server.
class ToolChoiceCustom:Use this option to force the model to call a specific custom tool.
Use this option to force the model to call a specific custom tool.
The name of the custom tool to call.
For custom tool calling, the type is always custom.
class ToolChoiceApplyPatch:Forces the model to call the apply_patch tool when executing a tool call.
Forces the model to call the apply_patch tool when executing a tool call.
The tool to call. Always apply_patch.
class ToolChoiceShell:Forces the model to call the shell tool when a tool call is required.
Forces the model to call the shell tool when a tool call is required.
The tool to call. Always shell.
List<Tool> toolsAn 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
or file search. Learn more about
built-in 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.
- 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. You can also use
custom tools to call your own code.
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 or file search. Learn more about built-in 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.
- 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. You can also use custom tools to call your own code.
class FunctionTool:Defines a function in your own code the model can choose to call. Learn more about function calling.
Defines a function in your own code the model can choose to call. Learn more about function calling.
The name of the function to call.
A JSON schema object describing the parameters of the function.
Whether to enforce strict parameter validation. Default true.
The type of the function tool. Always function.
A description of the function. Used by the model to determine whether or not to call the function.
class FileSearchTool:A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
The type of the file search tool. Always file_search.
The IDs of the vector stores to search.
Optional<Filters> filtersA filter to apply.
A filter to apply.
class ComparisonFilter:A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
The key to compare against the value.
Type typeSpecifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Value valueThe value to compare against the attribute key; supports string, number, or boolean types.
The value to compare against the attribute key; supports string, number, or boolean types.
List<ComparisonFilterValueItem>
class CompoundFilter:Combine multiple filters using and or or.
Combine multiple filters using and or or.
List<Filter> filtersArray of filters to combine. Items can be ComparisonFilter or CompoundFilter.
Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
class ComparisonFilter:A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
The key to compare against the value.
Type typeSpecifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Value valueThe value to compare against the attribute key; supports string, number, or boolean types.
The value to compare against the attribute key; supports string, number, or boolean types.
List<ComparisonFilterValueItem>
Type typeType of operation: and or or.
Type of operation: and or or.
The maximum number of results to return. This number should be between 1 and 50 inclusive.
Optional<RankingOptions> rankingOptionsRanking options for search.
Ranking options for search.
Optional<HybridSearch> hybridSearchWeights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
The weight of the embedding in the reciprocal ranking fusion.
The weight of the text in the reciprocal ranking fusion.
Optional<Ranker> rankerThe ranker to use for the file search.
The ranker to use for the file search.
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.
class ComputerTool:A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
The height of the computer display.
The width of the computer display.
Environment environmentThe type of computer environment to control.
The type of computer environment to control.
The type of the computer use tool. Always computer_use_preview.
class WebSearchTool:Search the Internet for sources related to the prompt. Learn more about the
web search tool.
Search the Internet for sources related to the prompt. Learn more about the web search tool.
Type typeThe type of the web search tool. One of web_search or web_search_2025_08_26.
The type of the web search tool. One of web_search or web_search_2025_08_26.
Optional<Filters> filtersFilters for the search.
Filters for the search.
Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example: ["pubmed.ncbi.nlm.nih.gov"]
Optional<SearchContextSize> searchContextSizeHigh level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
Optional<UserLocation> userLocationThe approximate location of the user.
The approximate location of the user.
Free text input for the city of the user, e.g. San Francisco.
The two-letter ISO country code of the user, e.g. US.
Free text input for the region of the user, e.g. California.
The IANA timezone of the user, e.g. America/Los_Angeles.
The type of location approximation. Always approximate.
Mcp
A label for this MCP server, used to identify it in tool calls.
The type of the MCP tool. Always mcp.
Optional<AllowedTools> allowedToolsList of allowed tool names or a filter object.
List of allowed tool names or a filter object.
class McpToolFilter:A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
Optional<ConnectorId> connectorIdIdentifier for service connectors, like those available in ChatGPT. One of
server_url or connector_id must be provided. Learn more about service
connectors here.
Currently supported connector_id values are:
- Dropbox:
connector_dropbox
- Gmail:
connector_gmail
- Google Calendar:
connector_googlecalendar
- Google Drive:
connector_googledrive
- Microsoft Teams:
connector_microsoftteams
- Outlook Calendar:
connector_outlookcalendar
- Outlook Email:
connector_outlookemail
- SharePoint:
connector_sharepoint
Identifier for service connectors, like those available in ChatGPT. One of
server_url or connector_id must be provided. Learn more about service
connectors here.
Currently supported connector_id values are:
- Dropbox:
connector_dropbox - Gmail:
connector_gmail - Google Calendar:
connector_googlecalendar - Google Drive:
connector_googledrive - Microsoft Teams:
connector_microsoftteams - Outlook Calendar:
connector_outlookcalendar - Outlook Email:
connector_outlookemail - SharePoint:
connector_sharepoint
Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
Optional<RequireApproval> requireApprovalSpecify which of the MCP server's tools require approval.
Specify which of the MCP server's tools require approval.
class McpToolApprovalFilter:Specify which of the MCP server's tools require approval. Can be
always, never, or a filter object associated with tools
that require approval.
Specify which of the MCP server's tools require approval. Can be
always, never, or a filter object associated with tools
that require approval.
Optional<Always> alwaysA filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
Optional<Never> neverA filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
enum McpToolApprovalSetting:Specify a single approval policy for all tools. One of always or
never. When set to always, all tools will require approval. When
set to never, all tools will not require approval.
Specify a single approval policy for all tools. One of always or
never. When set to always, all tools will require approval. When
set to never, all tools will not require approval.
Optional description of the MCP server, used to provide more context.
The URL for the MCP server. One of server_url or connector_id must be
provided.
CodeInterpreter
Container containerThe code interpreter container. Can be a container ID or an object that
specifies uploaded file IDs to make available to your code, along with an
optional memory_limit setting.
The code interpreter container. Can be a container ID or an object that
specifies uploaded file IDs to make available to your code, along with an
optional memory_limit setting.
class CodeInterpreterToolAuto:Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
Always auto.
An optional list of uploaded files to make available to your code.
Optional<MemoryLimit> memoryLimitThe memory limit for the code interpreter container.
The memory limit for the code interpreter container.
The type of the code interpreter tool. Always code_interpreter.
ImageGeneration
The type of the image generation tool. Always image_generation.
Optional<Action> actionWhether to generate a new image or edit an existing image. Default: auto.
Whether to generate a new image or edit an existing image. Default: auto.
Optional<Background> backgroundBackground type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Optional<InputFidelity> inputFidelityControl how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Optional<InputImageMask> inputImageMaskOptional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
File ID for the mask image.
Base64-encoded mask image.
Optional<Model> modelThe image generation model to use. Default: gpt-image-1.
The image generation model to use. Default: gpt-image-1.
Optional<Moderation> moderationModeration level for the generated image. Default: auto.
Moderation level for the generated image. Default: auto.
Compression level for the output image. Default: 100.
Optional<OutputFormat> outputFormatThe output format of the generated image. One of png, webp, or
jpeg. Default: png.
The output format of the generated image. One of png, webp, or
jpeg. Default: png.
Number of partial images to generate in streaming mode, from 0 (default value) to 3.
Optional<Quality> qualityThe quality of the generated image. One of low, medium, high,
or auto. Default: auto.
The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
Optional<Size> sizeThe size of the generated image. One of 1024x1024, 1024x1536,
1536x1024, or auto. Default: auto.
The size of the generated image. One of 1024x1024, 1024x1536,
1536x1024, or auto. Default: auto.
JsonValue;
The type of the local shell tool. Always local_shell.
class FunctionShellTool:A tool that allows the model to execute shell commands.
A tool that allows the model to execute shell commands.
The type of the shell tool. Always shell.
class CustomTool:A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
The name of the custom tool, used to identify it in tool calls.
The type of the custom tool. Always custom.
Optional description of the custom tool, used to provide more context.
The input format for the custom tool. Default is unconstrained text.
The input format for the custom tool. Default is unconstrained text.
JsonValue;
Unconstrained text format. Always text.
Grammar
The grammar definition.
Syntax syntaxThe syntax of the grammar definition. One of lark or regex.
The syntax of the grammar definition. One of lark or regex.
Grammar format. Always grammar.
class WebSearchPreviewTool:This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
Type typeThe type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
Optional<SearchContextSize> searchContextSizeHigh level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
Optional<UserLocation> userLocationThe user's location.
The user's location.
The type of location approximation. Always approximate.
Free text input for the city of the user, e.g. San Francisco.
The two-letter ISO country code of the user, e.g. US.
Free text input for the region of the user, e.g. California.
The IANA timezone of the user, e.g. America/Los_Angeles.
class ApplyPatchTool:Allows the assistant to create, delete, or update files using unified diffs.
Allows the assistant to create, delete, or update files using unified diffs.
The type of the tool. Always apply_patch.
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.
Whether to run the model response in the background. Learn more.
Unix timestamp (in seconds) of when this Response was completed.
Only present when the status is completed.
Optional<Conversation> conversationThe conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
The unique ID of the conversation that this response was associated with.
An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
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.
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.
Reference to a prompt template and its variables.
Learn more.
Reference to a prompt template and its variables. Learn more.
The unique identifier of the prompt template to use.
Optional<Variables> variablesOptional map of values to substitute in for variables in your
prompt. The substitution values can either be strings, or other
Response input types like images or files.
Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Optional version of the prompt template.
Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
Optional<PromptCacheRetention> promptCacheRetentionThe 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.
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.
gpt-5 and o-series models only
Configuration options for
reasoning models.
gpt-5 and o-series models only
Configuration options for reasoning models.
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1 default to medium reasoning effort, and do not support none.
- The
gpt-5-pro model defaults to (and only supports) high reasoning effort.
xhigh is supported for all models after gpt-5.1-codex-max.
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. - The
gpt-5-promodel defaults to (and only supports)highreasoning effort. xhighis supported for all models aftergpt-5.1-codex-max.
DeprecatedOptional<GenerateSummary> generateSummaryDeprecated: use summary instead.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
Deprecated: use summary instead.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
Optional<Summary> summaryA summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
concise is supported for computer-use-preview models and all reasoning models after gpt-5.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
concise is supported for computer-use-preview models and all reasoning models after gpt-5.
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. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
Optional<ServiceTier> serviceTierSpecifies 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' or 'priority', then the request will be processed with the corresponding service tier.
- 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.
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' or 'priority', then the request will be processed with the corresponding service tier.
- 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.
The status of the response generation. One of completed, failed,
in_progress, cancelled, queued, or incomplete.
The status of the response generation. One of completed, failed,
in_progress, cancelled, queued, or incomplete.
Configuration options for a text response from the model. Can be plain
text or structured JSON data. Learn more:
Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
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.
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.
class ResponseFormatText:Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatTextJsonSchemaConfig:JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
The type of response format being defined. Always json_schema.
A description of what the response format is for, used by the model to determine how to respond in the format.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
class ResponseFormatJsonObject:JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
Optional<Verbosity> verbosityConstrains the verbosity of the model's response. Lower values will result in
more concise responses, while higher values will result in more verbose responses.
Currently supported values are low, medium, and high.
Constrains the verbosity of the model's response. Lower values will result in
more concise responses, while higher values will result in more verbose responses.
Currently supported values are low, medium, and high.
An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.
Optional<Truncation> truncationThe 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.
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.
Represents token usage details including input tokens, output tokens,
a breakdown of output tokens, and the total tokens used.
Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
The number of input tokens.
InputTokensDetails inputTokensDetailsA detailed breakdown of the input tokens.
A detailed breakdown of the input tokens.
The number of tokens that were retrieved from the cache. More on prompt caching.
The number of output tokens.
OutputTokensDetails outputTokensDetailsA detailed breakdown of the output tokens.
A detailed breakdown of the output tokens.
The number of reasoning tokens.
The total number of tokens used.
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.
The sequence number for this event.
The type of the event. Always response.created.
class ResponseErrorEvent:Emitted when an error occurs.
Emitted when an error occurs.
The error code.
The error message.
The error parameter.
The sequence number of this event.
The type of the event. Always error.
class ResponseFileSearchCallCompletedEvent:Emitted when a file search call is completed (results found).
Emitted when a file search call is completed (results found).
The ID of the output item that the file search call is initiated.
The index of the output item that the file search call is initiated.
The sequence number of this event.
The type of the event. Always response.file_search_call.completed.
class ResponseFileSearchCallInProgressEvent:Emitted when a file search call is initiated.
Emitted when a file search call is initiated.
The ID of the output item that the file search call is initiated.
The index of the output item that the file search call is initiated.
The sequence number of this event.
The type of the event. Always response.file_search_call.in_progress.
class ResponseFileSearchCallSearchingEvent:Emitted when a file search is currently searching.
Emitted when a file search is currently searching.
The ID of the output item that the file search call is initiated.
The index of the output item that the file search call is searching.
The sequence number of this event.
The type of the event. Always response.file_search_call.searching.
class ResponseFunctionCallArgumentsDeltaEvent:Emitted when there is a partial function-call arguments delta.
Emitted when there is a partial function-call arguments delta.
The function-call arguments delta that is added.
The ID of the output item that the function-call arguments delta is added to.
The index of the output item that the function-call arguments delta is added to.
The sequence number of this event.
The type of the event. Always response.function_call_arguments.delta.
class ResponseFunctionCallArgumentsDoneEvent:Emitted when function-call arguments are finalized.
Emitted when function-call arguments are finalized.
The function-call arguments.
The ID of the item.
The name of the function that was called.
The index of the output item.
The sequence number of this event.
class ResponseInProgressEvent:Emitted when the response is in progress.
Emitted when the response is in progress.
Response responseThe response that is in progress.
The response that is in progress.
Unique identifier for this Response.
Unix timestamp (in seconds) of when this Response was created.
An error object returned when the model fails to generate a Response.
An error object returned when the model fails to generate a Response.
Code codeThe error code for the response.
The error code for the response.
A human-readable description of the error.
Optional<IncompleteDetails> incompleteDetailsDetails about why the response is incomplete.
Details about why the response is incomplete.
Optional<Reason> reasonThe reason why the response is incomplete.
The reason why the response is incomplete.
Optional<Instructions> instructionsA 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.
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.
List<ResponseInputItem>
class EasyInputMessage:A message input to the model with a role indicating instruction following
hierarchy. Instructions given with the developer or system role take
precedence over instructions given with the user role. Messages with the
assistant role are presumed to have been generated by the model in previous
interactions.
A message input to the model with a role indicating instruction following
hierarchy. Instructions given with the developer or system role take
precedence over instructions given with the user role. Messages with the
assistant role are presumed to have been generated by the model in previous
interactions.
Content contentText, image, or audio input to the model, used to generate a response.
Can also contain previous assistant responses.
Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
List<ResponseInputContent>
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Role roleThe role of the message input. One of user, assistant, system, or
developer.
The role of the message input. One of user, assistant, system, or
developer.
The type of the message input. Always message.
Message
List<ResponseInputContent> contentA list of one or many input items to the model, containing different content
types.
A list of one or many input items to the model, containing different content types.
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Role roleThe role of the message input. One of user, system, or developer.
The role of the message input. One of user, system, or developer.
Optional<Status> statusThe status of item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the message input. Always set to message.
class ResponseOutputMessage:An output message from the model.
An output message from the model.
The unique ID of the output message.
List<Content> contentThe content of the output message.
The content of the output message.
class ResponseOutputText:A text output from the model.
A text output from the model.
List<Annotation> annotationsThe annotations of the text output.
The annotations of the text output.
class FileCitation:A citation to a file.
A citation to a file.
The ID of the file.
The filename of the file cited.
The index of the file in the list of files.
The type of the file citation. Always file_citation.
class UrlCitation:A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
The index of the last character of the URL citation in the message.
The index of the first character of the URL citation in the message.
The title of the web resource.
The type of the URL citation. Always url_citation.
The URL of the web resource.
class ContainerFileCitation:A citation for a container file used to generate a model response.
A citation for a container file used to generate a model response.
The ID of the container file.
The index of the last character of the container file citation in the message.
The ID of the file.
The filename of the container file cited.
The index of the first character of the container file citation in the message.
The type of the container file citation. Always container_file_citation.
class FilePath:A path to a file.
A path to a file.
The ID of the file.
The index of the file in the list of files.
The type of the file path. Always file_path.
The text output from the model.
The type of the output text. Always output_text.
Optional<List<Logprob>> logprobs
List<TopLogprob> topLogprobs
class ResponseOutputRefusal:A refusal from the model.
A refusal from the model.
The refusal explanation from the model.
The type of the refusal. Always refusal.
The role of the output message. Always assistant.
Status statusThe status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The type of the output message. Always message.
class ResponseFileSearchToolCall:The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
The unique ID of the file search tool call.
The queries used to search for files.
Status statusThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The type of the file search tool call. Always file_search_call.
Optional<List<Result>> resultsThe results of the file search tool call.
The results of the file search tool call.
Optional<Attributes> attributesSet 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, booleans, or numbers.
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, booleans, or numbers.
The unique ID of the file.
The name of the file.
The relevance score of the file - a value between 0 and 1.
The text that was retrieved from the file.
class ResponseComputerToolCall:A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
The unique ID of the computer call.
Action actionA click action.
A click action.
class Click:A click action.
A click action.
Button buttonIndicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Specifies the event type. For a click action, this property is always click.
The x-coordinate where the click occurred.
The y-coordinate where the click occurred.
class DoubleClick:A double click action.
A double click action.
Specifies the event type. For a double click action, this property is always set to double_click.
The x-coordinate where the double click occurred.
The y-coordinate where the double click occurred.
class Drag:A drag action.
A drag action.
List<Path> pathAn array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]
An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]The x-coordinate.
The y-coordinate.
Specifies the event type. For a drag action, this property is always set to drag.
class Keypress:A collection of keypresses the model would like to perform.
A collection of keypresses the model would like to perform.
The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
Specifies the event type. For a keypress action, this property is always set to keypress.
class Move:A mouse move action.
A mouse move action.
Specifies the event type. For a move action, this property is always set to move.
The x-coordinate to move to.
The y-coordinate to move to.
JsonValue;
Specifies the event type. For a screenshot action, this property is always set to screenshot.
class Scroll:A scroll action.
A scroll action.
The horizontal scroll distance.
The vertical scroll distance.
Specifies the event type. For a scroll action, this property is always set to scroll.
The x-coordinate where the scroll occurred.
The y-coordinate where the scroll occurred.
class Type:An action to type in text.
An action to type in text.
The text to type.
Specifies the event type. For a type action, this property is always set to type.
JsonValue;
Specifies the event type. For a wait action, this property is always set to wait.
An identifier used when responding to the tool call with output.
List<PendingSafetyCheck> pendingSafetyChecksThe pending safety checks for the computer call.
The pending safety checks for the computer call.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Status statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the computer call. Always computer_call.
ComputerCallOutput
The ID of the computer tool call that produced the output.
A computer screenshot image used with the computer use tool.
A computer screenshot image used with the computer use tool.
Specifies the event type. For a computer screenshot, this property is
always set to computer_screenshot.
The identifier of an uploaded file that contains the screenshot.
The URL of the screenshot image.
The type of the computer tool call output. Always computer_call_output.
The ID of the computer tool call output.
Optional<List<AcknowledgedSafetyCheck>> acknowledgedSafetyChecksThe safety checks reported by the API that have been acknowledged by the developer.
The safety checks reported by the API that have been acknowledged by the developer.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Optional<Status> statusThe status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
class ResponseFunctionWebSearch:The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
The unique ID of the web search tool call.
Action actionAn object describing the specific action taken in this web search call.
Includes details on how the model used the web (search, open_page, find_in_page).
An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
class Search:Action type "search" - Performs a web search query.
Action type "search" - Performs a web search query.
[DEPRECATED] The search query.
The action type.
The search queries.
Optional<List<Source>> sourcesThe sources used in the search.
The sources used in the search.
The type of source. Always url.
The URL of the source.
class OpenPage:Action type "open_page" - Opens a specific URL from search results.
Action type "open_page" - Opens a specific URL from search results.
The action type.
The URL opened by the model.
class FindInPage:Action type "find_in_page": Searches for a pattern within a loaded page.
Action type "find_in_page": Searches for a pattern within a loaded page.
The pattern or text to search for within the page.
The action type.
The URL of the page searched for the pattern.
Status statusThe status of the web search tool call.
The status of the web search tool call.
The type of the web search tool call. Always web_search_call.
class ResponseFunctionToolCall:A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
A JSON string of the arguments to pass to the function.
The unique ID of the function tool call generated by the model.
The name of the function to run.
The type of the function tool call. Always function_call.
The unique ID of the function tool call.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
FunctionCallOutput
The unique ID of the function tool call generated by the model.
Output outputText, image, or file output of the function tool call.
Text, image, or file output of the function tool call.
class ResponseInputTextContent:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImageContent:An image input to the model. Learn about image inputs
An image input to the model. Learn about image inputs
The type of the input item. Always input_image.
Optional<Detail> detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFileContent:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The base64-encoded data of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
The type of the function tool call output. Always function_call_output.
The unique ID of the function tool call output. Populated when this item is returned via API.
Optional<Status> statusThe status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
class ResponseReasoningItem:A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
The unique identifier of the reasoning content.
List<Summary> summaryReasoning summary content.
Reasoning summary content.
A summary of the reasoning output from the model so far.
The type of the object. Always summary_text.
The type of the object. Always reasoning.
Optional<List<Content>> contentReasoning text content.
Reasoning text content.
The reasoning text from the model.
The type of the reasoning text. Always reasoning_text.
The encrypted content of the reasoning item - populated when a response is
generated with reasoning.encrypted_content in the include parameter.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseCompactionItemParam:A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
The encrypted content of the compaction summary.
The type of the item. Always compaction.
The ID of the compaction item.
ImageGenerationCall
The unique ID of the image generation call.
The generated image encoded in base64.
Status statusThe status of the image generation call.
The status of the image generation call.
The type of the image generation call. Always image_generation_call.
class ResponseCodeInterpreterToolCall:A tool call to run code.
A tool call to run code.
The unique ID of the code interpreter tool call.
The code to run, or null if not available.
The ID of the container used to run the code.
Optional<List<Output>> outputsThe outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
class Logs:The logs output from the code interpreter.
The logs output from the code interpreter.
The logs output from the code interpreter.
The type of the output. Always logs.
class Image:The image output from the code interpreter.
The image output from the code interpreter.
The type of the output. Always image.
The URL of the image output from the code interpreter.
Status statusThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The type of the code interpreter tool call. Always code_interpreter_call.
LocalShellCall
The unique ID of the local shell call.
Action actionExecute a shell command on the server.
Execute a shell command on the server.
The command to run.
Environment variables to set for the command.
The type of the local shell action. Always exec.
Optional timeout in milliseconds for the command.
Optional user to run the command as.
Optional working directory to run the command in.
The unique ID of the local shell tool call generated by the model.
Status statusThe status of the local shell call.
The status of the local shell call.
The type of the local shell call. Always local_shell_call.
LocalShellCallOutput
The unique ID of the local shell tool call generated by the model.
A JSON string of the output of the local shell tool call.
The type of the local shell tool call output. Always local_shell_call_output.
Optional<Status> statusThe status of the item. One of in_progress, completed, or incomplete.
The status of the item. One of in_progress, completed, or incomplete.
ShellCall
Action actionThe shell commands and limits that describe how to run the tool call.
The shell commands and limits that describe how to run the tool call.
Ordered shell commands for the execution environment to run.
Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
Maximum wall-clock time in milliseconds to allow the shell commands to run.
The unique ID of the shell tool call generated by the model.
The type of the item. Always shell_call.
The unique ID of the shell tool call. Populated when this item is returned via API.
Optional<Status> statusThe status of the shell call. One of in_progress, completed, or incomplete.
The status of the shell call. One of in_progress, completed, or incomplete.
ShellCallOutput
The unique ID of the shell tool call generated by the model.
List<ResponseFunctionShellCallOutputContent> outputCaptured chunks of stdout and stderr output, along with their associated outcomes.
Captured chunks of stdout and stderr output, along with their associated outcomes.
Outcome outcomeThe exit or timeout outcome associated with this shell call.
The exit or timeout outcome associated with this shell call.
JsonValue;
The outcome type. Always timeout.
class Exit:Indicates that the shell commands finished and returned an exit code.
Indicates that the shell commands finished and returned an exit code.
The exit code returned by the shell process.
The outcome type. Always exit.
Captured stderr output for the shell call.
Captured stdout output for the shell call.
The type of the item. Always shell_call_output.
The unique ID of the shell tool call output. Populated when this item is returned via API.
The maximum number of UTF-8 characters captured for this shell call's combined output.
Optional<Status> statusThe status of the shell call output.
The status of the shell call output.
ApplyPatchCall
The unique ID of the apply patch tool call generated by the model.
Operation operationThe specific create, delete, or update instruction for the apply_patch tool call.
The specific create, delete, or update instruction for the apply_patch tool call.
class CreateFile:Instruction for creating a new file via the apply_patch tool.
Instruction for creating a new file via the apply_patch tool.
Unified diff content to apply when creating the file.
Path of the file to create relative to the workspace root.
The operation type. Always create_file.
class DeleteFile:Instruction for deleting an existing file via the apply_patch tool.
Instruction for deleting an existing file via the apply_patch tool.
Path of the file to delete relative to the workspace root.
The operation type. Always delete_file.
class UpdateFile:Instruction for updating an existing file via the apply_patch tool.
Instruction for updating an existing file via the apply_patch tool.
Unified diff content to apply to the existing file.
Path of the file to update relative to the workspace root.
The operation type. Always update_file.
Status statusThe status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
The type of the item. Always apply_patch_call.
The unique ID of the apply patch tool call. Populated when this item is returned via API.
ApplyPatchCallOutput
The unique ID of the apply patch tool call generated by the model.
Status statusThe status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
The type of the item. Always apply_patch_call_output.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
McpListTools
The unique ID of the list.
The label of the MCP server.
List<Tool> toolsThe tools available on the server.
The tools available on the server.
The JSON schema describing the tool's input.
The name of the tool.
Additional annotations about the tool.
The description of the tool.
The type of the item. Always mcp_list_tools.
Error message if the server could not list tools.
McpApprovalRequest
The unique ID of the approval request.
A JSON string of arguments for the tool.
The name of the tool to run.
The label of the MCP server making the request.
The type of the item. Always mcp_approval_request.
McpApprovalResponse
The ID of the approval request being answered.
Whether the request was approved.
The type of the item. Always mcp_approval_response.
The unique ID of the approval response
Optional reason for the decision.
McpCall
The unique ID of the tool call.
A JSON string of the arguments passed to the tool.
The name of the tool that was run.
The label of the MCP server running the tool.
The type of the item. Always mcp_call.
Unique identifier for the MCP tool call approval request.
Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
The error from the tool call, if any.
The output from the tool call.
Optional<Status> statusThe status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
class ResponseCustomToolCallOutput:The output of a custom tool call from your code, being sent back to the model.
The output of a custom tool call from your code, being sent back to the model.
The call ID, used to map this custom tool call output to a custom tool call.
Output outputThe output from the custom tool call generated by your code.
Can be a string or an list of output content.
The output from the custom tool call generated by your code. Can be a string or an list of output content.
List<FunctionAndCustomToolCallOutput>
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
The type of the custom tool call output. Always custom_tool_call_output.
The unique ID of the custom tool call output in the OpenAI platform.
class ResponseCustomToolCall:A call to a custom tool created by the model.
A call to a custom tool created by the model.
An identifier used to map this custom tool call to a tool call output.
The input for the custom tool call generated by the model.
The name of the custom tool being called.
The type of the custom tool call. Always custom_tool_call.
The unique ID of the custom tool call in the OpenAI platform.
ItemReference
The ID of the item to reference.
The type of item to reference. Always item_reference.
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.
ResponsesModel modelModel ID used to generate the response, like gpt-4o or o3. 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.
Model ID used to generate the response, like gpt-4o or o3. 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.
enum ChatModel:
ResponsesOnlyModel
The object type of this resource - always set to response.
List<ResponseOutputItem> outputAn 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.
An array of content items generated by the model.
- The length and order of items in the
outputarray is dependent on the model's response. - Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs.
class ResponseOutputMessage:An output message from the model.
An output message from the model.
The unique ID of the output message.
List<Content> contentThe content of the output message.
The content of the output message.
class ResponseOutputText:A text output from the model.
A text output from the model.
List<Annotation> annotationsThe annotations of the text output.
The annotations of the text output.
class FileCitation:A citation to a file.
A citation to a file.
The ID of the file.
The filename of the file cited.
The index of the file in the list of files.
The type of the file citation. Always file_citation.
class UrlCitation:A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
The index of the last character of the URL citation in the message.
The index of the first character of the URL citation in the message.
The title of the web resource.
The type of the URL citation. Always url_citation.
The URL of the web resource.
class ContainerFileCitation:A citation for a container file used to generate a model response.
A citation for a container file used to generate a model response.
The ID of the container file.
The index of the last character of the container file citation in the message.
The ID of the file.
The filename of the container file cited.
The index of the first character of the container file citation in the message.
The type of the container file citation. Always container_file_citation.
class FilePath:A path to a file.
A path to a file.
The ID of the file.
The index of the file in the list of files.
The type of the file path. Always file_path.
The text output from the model.
The type of the output text. Always output_text.
Optional<List<Logprob>> logprobs
List<TopLogprob> topLogprobs
class ResponseOutputRefusal:A refusal from the model.
A refusal from the model.
The refusal explanation from the model.
The type of the refusal. Always refusal.
The role of the output message. Always assistant.
Status statusThe status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The type of the output message. Always message.
class ResponseFileSearchToolCall:The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
The unique ID of the file search tool call.
The queries used to search for files.
Status statusThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The type of the file search tool call. Always file_search_call.
Optional<List<Result>> resultsThe results of the file search tool call.
The results of the file search tool call.
Optional<Attributes> attributesSet 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, booleans, or numbers.
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, booleans, or numbers.
The unique ID of the file.
The name of the file.
The relevance score of the file - a value between 0 and 1.
The text that was retrieved from the file.
class ResponseFunctionToolCall:A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
A JSON string of the arguments to pass to the function.
The unique ID of the function tool call generated by the model.
The name of the function to run.
The type of the function tool call. Always function_call.
The unique ID of the function tool call.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseFunctionWebSearch:The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
The unique ID of the web search tool call.
Action actionAn object describing the specific action taken in this web search call.
Includes details on how the model used the web (search, open_page, find_in_page).
An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
class Search:Action type "search" - Performs a web search query.
Action type "search" - Performs a web search query.
[DEPRECATED] The search query.
The action type.
The search queries.
Optional<List<Source>> sourcesThe sources used in the search.
The sources used in the search.
The type of source. Always url.
The URL of the source.
class OpenPage:Action type "open_page" - Opens a specific URL from search results.
Action type "open_page" - Opens a specific URL from search results.
The action type.
The URL opened by the model.
class FindInPage:Action type "find_in_page": Searches for a pattern within a loaded page.
Action type "find_in_page": Searches for a pattern within a loaded page.
The pattern or text to search for within the page.
The action type.
The URL of the page searched for the pattern.
Status statusThe status of the web search tool call.
The status of the web search tool call.
The type of the web search tool call. Always web_search_call.
class ResponseComputerToolCall:A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
The unique ID of the computer call.
Action actionA click action.
A click action.
class Click:A click action.
A click action.
Button buttonIndicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Specifies the event type. For a click action, this property is always click.
The x-coordinate where the click occurred.
The y-coordinate where the click occurred.
class DoubleClick:A double click action.
A double click action.
Specifies the event type. For a double click action, this property is always set to double_click.
The x-coordinate where the double click occurred.
The y-coordinate where the double click occurred.
class Drag:A drag action.
A drag action.
List<Path> pathAn array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]
An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]The x-coordinate.
The y-coordinate.
Specifies the event type. For a drag action, this property is always set to drag.
class Keypress:A collection of keypresses the model would like to perform.
A collection of keypresses the model would like to perform.
The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
Specifies the event type. For a keypress action, this property is always set to keypress.
class Move:A mouse move action.
A mouse move action.
Specifies the event type. For a move action, this property is always set to move.
The x-coordinate to move to.
The y-coordinate to move to.
JsonValue;
Specifies the event type. For a screenshot action, this property is always set to screenshot.
class Scroll:A scroll action.
A scroll action.
The horizontal scroll distance.
The vertical scroll distance.
Specifies the event type. For a scroll action, this property is always set to scroll.
The x-coordinate where the scroll occurred.
The y-coordinate where the scroll occurred.
class Type:An action to type in text.
An action to type in text.
The text to type.
Specifies the event type. For a type action, this property is always set to type.
JsonValue;
Specifies the event type. For a wait action, this property is always set to wait.
An identifier used when responding to the tool call with output.
List<PendingSafetyCheck> pendingSafetyChecksThe pending safety checks for the computer call.
The pending safety checks for the computer call.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Status statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the computer call. Always computer_call.
class ResponseReasoningItem:A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
The unique identifier of the reasoning content.
List<Summary> summaryReasoning summary content.
Reasoning summary content.
A summary of the reasoning output from the model so far.
The type of the object. Always summary_text.
The type of the object. Always reasoning.
Optional<List<Content>> contentReasoning text content.
Reasoning text content.
The reasoning text from the model.
The type of the reasoning text. Always reasoning_text.
The encrypted content of the reasoning item - populated when a response is
generated with reasoning.encrypted_content in the include parameter.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseCompactionItem:A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
The unique ID of the compaction item.
The encrypted content that was produced by compaction.
The type of the item. Always compaction.
The identifier of the actor that created the item.
ImageGenerationCall
The unique ID of the image generation call.
The generated image encoded in base64.
Status statusThe status of the image generation call.
The status of the image generation call.
The type of the image generation call. Always image_generation_call.
class ResponseCodeInterpreterToolCall:A tool call to run code.
A tool call to run code.
The unique ID of the code interpreter tool call.
The code to run, or null if not available.
The ID of the container used to run the code.
Optional<List<Output>> outputsThe outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
class Logs:The logs output from the code interpreter.
The logs output from the code interpreter.
The logs output from the code interpreter.
The type of the output. Always logs.
class Image:The image output from the code interpreter.
The image output from the code interpreter.
The type of the output. Always image.
The URL of the image output from the code interpreter.
Status statusThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The type of the code interpreter tool call. Always code_interpreter_call.
LocalShellCall
The unique ID of the local shell call.
Action actionExecute a shell command on the server.
Execute a shell command on the server.
The command to run.
Environment variables to set for the command.
The type of the local shell action. Always exec.
Optional timeout in milliseconds for the command.
Optional user to run the command as.
Optional working directory to run the command in.
The unique ID of the local shell tool call generated by the model.
Status statusThe status of the local shell call.
The status of the local shell call.
The type of the local shell call. Always local_shell_call.
class ResponseFunctionShellToolCall:A tool call that executes one or more shell commands in a managed environment.
A tool call that executes one or more shell commands in a managed environment.
The unique ID of the shell tool call. Populated when this item is returned via API.
Action actionThe shell commands and limits that describe how to run the tool call.
The shell commands and limits that describe how to run the tool call.
Optional maximum number of characters to return from each command.
Optional timeout in milliseconds for the commands.
The unique ID of the shell tool call generated by the model.
Status statusThe status of the shell call. One of in_progress, completed, or incomplete.
The status of the shell call. One of in_progress, completed, or incomplete.
The type of the item. Always shell_call.
The ID of the entity that created this tool call.
class ResponseFunctionShellToolCallOutput:The output of a shell tool call that was emitted.
The output of a shell tool call that was emitted.
The unique ID of the shell call output. Populated when this item is returned via API.
The unique ID of the shell tool call generated by the model.
The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
List<Output> outputAn array of shell call output contents
An array of shell call output contents
Outcome outcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
JsonValue;
The outcome type. Always timeout.
class Exit:Indicates that the shell commands finished and returned an exit code.
Indicates that the shell commands finished and returned an exit code.
Exit code from the shell process.
The outcome type. Always exit.
The standard error output that was captured.
The standard output that was captured.
The identifier of the actor that created the item.
Status statusThe status of the shell call output. One of in_progress, completed, or incomplete.
The status of the shell call output. One of in_progress, completed, or incomplete.
The type of the shell call output. Always shell_call_output.
The identifier of the actor that created the item.
class ResponseApplyPatchToolCall:A tool call that applies file diffs by creating, deleting, or updating files.
A tool call that applies file diffs by creating, deleting, or updating files.
The unique ID of the apply patch tool call. Populated when this item is returned via API.
The unique ID of the apply patch tool call generated by the model.
Operation operationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
One of the create_file, delete_file, or update_file operations applied via apply_patch.
class CreateFile:Instruction describing how to create a file via the apply_patch tool.
Instruction describing how to create a file via the apply_patch tool.
Diff to apply.
Path of the file to create.
Create a new file with the provided diff.
class DeleteFile:Instruction describing how to delete a file via the apply_patch tool.
Instruction describing how to delete a file via the apply_patch tool.
Path of the file to delete.
Delete the specified file.
class UpdateFile:Instruction describing how to update a file via the apply_patch tool.
Instruction describing how to update a file via the apply_patch tool.
Diff to apply.
Path of the file to update.
Update an existing file with the provided diff.
Status statusThe status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
The type of the item. Always apply_patch_call.
The ID of the entity that created this tool call.
class ResponseApplyPatchToolCallOutput:The output emitted by an apply patch tool call.
The output emitted by an apply patch tool call.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
The unique ID of the apply patch tool call generated by the model.
Status statusThe status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
The type of the item. Always apply_patch_call_output.
The ID of the entity that created this tool call output.
Optional textual output returned by the apply patch tool.
McpCall
The unique ID of the tool call.
A JSON string of the arguments passed to the tool.
The name of the tool that was run.
The label of the MCP server running the tool.
The type of the item. Always mcp_call.
Unique identifier for the MCP tool call approval request.
Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
The error from the tool call, if any.
The output from the tool call.
Optional<Status> statusThe status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
McpListTools
The unique ID of the list.
The label of the MCP server.
List<Tool> toolsThe tools available on the server.
The tools available on the server.
The JSON schema describing the tool's input.
The name of the tool.
Additional annotations about the tool.
The description of the tool.
The type of the item. Always mcp_list_tools.
Error message if the server could not list tools.
McpApprovalRequest
The unique ID of the approval request.
A JSON string of arguments for the tool.
The name of the tool to run.
The label of the MCP server making the request.
The type of the item. Always mcp_approval_request.
class ResponseCustomToolCall:A call to a custom tool created by the model.
A call to a custom tool created by the model.
An identifier used to map this custom tool call to a tool call output.
The input for the custom tool call generated by the model.
The name of the custom tool being called.
The type of the custom tool call. Always custom_tool_call.
The unique ID of the custom tool call in the OpenAI platform.
Whether to allow the model to run tool calls in parallel.
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.
ToolChoice toolChoiceHow 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.
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.
enum ToolChoiceOptions: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.
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.
class ToolChoiceAllowed:Constrains the tools available to the model to a pre-defined set.
Constrains the tools available to the model to a pre-defined set.
Mode modeConstrains the tools available to the model to a pre-defined set.
auto allows the model to pick from among the allowed tools and generate a
message.
required requires the model to call one or more of the allowed tools.
Constrains the tools available to the model to a pre-defined set.
auto allows the model to pick from among the allowed tools and generate a
message.
required requires the model to call one or more of the allowed tools.
A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[
{ "type": "function", "name": "get_weather" },
{ "type": "mcp", "server_label": "deepwiki" },
{ "type": "image_generation" }
]Allowed tool configuration type. Always allowed_tools.
class ToolChoiceTypes:Indicates that the model should use a built-in tool to generate a response.
Learn more about built-in tools.
Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
Type typeThe type of hosted tool the model should to use. Learn more about
built-in tools.
Allowed values are:
file_searchweb_search_previewcomputer_use_previewcode_interpreterimage_generation
The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
file_searchweb_search_previewcomputer_use_previewcode_interpreterimage_generation
class ToolChoiceFunction:Use this option to force the model to call a specific function.
Use this option to force the model to call a specific function.
The name of the function to call.
For function calling, the type is always function.
class ToolChoiceMcp:Use this option to force the model to call a specific tool on a remote MCP server.
Use this option to force the model to call a specific tool on a remote MCP server.
The label of the MCP server to use.
For MCP tools, the type is always mcp.
The name of the tool to call on the server.
class ToolChoiceCustom:Use this option to force the model to call a specific custom tool.
Use this option to force the model to call a specific custom tool.
The name of the custom tool to call.
For custom tool calling, the type is always custom.
class ToolChoiceApplyPatch:Forces the model to call the apply_patch tool when executing a tool call.
Forces the model to call the apply_patch tool when executing a tool call.
The tool to call. Always apply_patch.
class ToolChoiceShell:Forces the model to call the shell tool when a tool call is required.
Forces the model to call the shell tool when a tool call is required.
The tool to call. Always shell.
List<Tool> toolsAn 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
or file search. Learn more about
built-in 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.
- 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. You can also use
custom tools to call your own code.
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 or file search. Learn more about built-in 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.
- 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. You can also use custom tools to call your own code.
class FunctionTool:Defines a function in your own code the model can choose to call. Learn more about function calling.
Defines a function in your own code the model can choose to call. Learn more about function calling.
The name of the function to call.
A JSON schema object describing the parameters of the function.
Whether to enforce strict parameter validation. Default true.
The type of the function tool. Always function.
A description of the function. Used by the model to determine whether or not to call the function.
class FileSearchTool:A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
The type of the file search tool. Always file_search.
The IDs of the vector stores to search.
Optional<Filters> filtersA filter to apply.
A filter to apply.
class ComparisonFilter:A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
The key to compare against the value.
Type typeSpecifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Value valueThe value to compare against the attribute key; supports string, number, or boolean types.
The value to compare against the attribute key; supports string, number, or boolean types.
List<ComparisonFilterValueItem>
class CompoundFilter:Combine multiple filters using and or or.
Combine multiple filters using and or or.
List<Filter> filtersArray of filters to combine. Items can be ComparisonFilter or CompoundFilter.
Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
class ComparisonFilter:A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
The key to compare against the value.
Type typeSpecifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Value valueThe value to compare against the attribute key; supports string, number, or boolean types.
The value to compare against the attribute key; supports string, number, or boolean types.
List<ComparisonFilterValueItem>
Type typeType of operation: and or or.
Type of operation: and or or.
The maximum number of results to return. This number should be between 1 and 50 inclusive.
Optional<RankingOptions> rankingOptionsRanking options for search.
Ranking options for search.
Optional<HybridSearch> hybridSearchWeights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
The weight of the embedding in the reciprocal ranking fusion.
The weight of the text in the reciprocal ranking fusion.
Optional<Ranker> rankerThe ranker to use for the file search.
The ranker to use for the file search.
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.
class ComputerTool:A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
The height of the computer display.
The width of the computer display.
Environment environmentThe type of computer environment to control.
The type of computer environment to control.
The type of the computer use tool. Always computer_use_preview.
class WebSearchTool:Search the Internet for sources related to the prompt. Learn more about the
web search tool.
Search the Internet for sources related to the prompt. Learn more about the web search tool.
Type typeThe type of the web search tool. One of web_search or web_search_2025_08_26.
The type of the web search tool. One of web_search or web_search_2025_08_26.
Optional<Filters> filtersFilters for the search.
Filters for the search.
Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example: ["pubmed.ncbi.nlm.nih.gov"]
Optional<SearchContextSize> searchContextSizeHigh level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
Optional<UserLocation> userLocationThe approximate location of the user.
The approximate location of the user.
Free text input for the city of the user, e.g. San Francisco.
The two-letter ISO country code of the user, e.g. US.
Free text input for the region of the user, e.g. California.
The IANA timezone of the user, e.g. America/Los_Angeles.
The type of location approximation. Always approximate.
Mcp
A label for this MCP server, used to identify it in tool calls.
The type of the MCP tool. Always mcp.
Optional<AllowedTools> allowedToolsList of allowed tool names or a filter object.
List of allowed tool names or a filter object.
class McpToolFilter:A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
Optional<ConnectorId> connectorIdIdentifier for service connectors, like those available in ChatGPT. One of
server_url or connector_id must be provided. Learn more about service
connectors here.
Currently supported connector_id values are:
- Dropbox:
connector_dropbox
- Gmail:
connector_gmail
- Google Calendar:
connector_googlecalendar
- Google Drive:
connector_googledrive
- Microsoft Teams:
connector_microsoftteams
- Outlook Calendar:
connector_outlookcalendar
- Outlook Email:
connector_outlookemail
- SharePoint:
connector_sharepoint
Identifier for service connectors, like those available in ChatGPT. One of
server_url or connector_id must be provided. Learn more about service
connectors here.
Currently supported connector_id values are:
- Dropbox:
connector_dropbox - Gmail:
connector_gmail - Google Calendar:
connector_googlecalendar - Google Drive:
connector_googledrive - Microsoft Teams:
connector_microsoftteams - Outlook Calendar:
connector_outlookcalendar - Outlook Email:
connector_outlookemail - SharePoint:
connector_sharepoint
Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
Optional<RequireApproval> requireApprovalSpecify which of the MCP server's tools require approval.
Specify which of the MCP server's tools require approval.
class McpToolApprovalFilter:Specify which of the MCP server's tools require approval. Can be
always, never, or a filter object associated with tools
that require approval.
Specify which of the MCP server's tools require approval. Can be
always, never, or a filter object associated with tools
that require approval.
Optional<Always> alwaysA filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
Optional<Never> neverA filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
enum McpToolApprovalSetting:Specify a single approval policy for all tools. One of always or
never. When set to always, all tools will require approval. When
set to never, all tools will not require approval.
Specify a single approval policy for all tools. One of always or
never. When set to always, all tools will require approval. When
set to never, all tools will not require approval.
Optional description of the MCP server, used to provide more context.
The URL for the MCP server. One of server_url or connector_id must be
provided.
CodeInterpreter
Container containerThe code interpreter container. Can be a container ID or an object that
specifies uploaded file IDs to make available to your code, along with an
optional memory_limit setting.
The code interpreter container. Can be a container ID or an object that
specifies uploaded file IDs to make available to your code, along with an
optional memory_limit setting.
class CodeInterpreterToolAuto:Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
Always auto.
An optional list of uploaded files to make available to your code.
Optional<MemoryLimit> memoryLimitThe memory limit for the code interpreter container.
The memory limit for the code interpreter container.
The type of the code interpreter tool. Always code_interpreter.
ImageGeneration
The type of the image generation tool. Always image_generation.
Optional<Action> actionWhether to generate a new image or edit an existing image. Default: auto.
Whether to generate a new image or edit an existing image. Default: auto.
Optional<Background> backgroundBackground type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Optional<InputFidelity> inputFidelityControl how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Optional<InputImageMask> inputImageMaskOptional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
File ID for the mask image.
Base64-encoded mask image.
Optional<Model> modelThe image generation model to use. Default: gpt-image-1.
The image generation model to use. Default: gpt-image-1.
Optional<Moderation> moderationModeration level for the generated image. Default: auto.
Moderation level for the generated image. Default: auto.
Compression level for the output image. Default: 100.
Optional<OutputFormat> outputFormatThe output format of the generated image. One of png, webp, or
jpeg. Default: png.
The output format of the generated image. One of png, webp, or
jpeg. Default: png.
Number of partial images to generate in streaming mode, from 0 (default value) to 3.
Optional<Quality> qualityThe quality of the generated image. One of low, medium, high,
or auto. Default: auto.
The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
Optional<Size> sizeThe size of the generated image. One of 1024x1024, 1024x1536,
1536x1024, or auto. Default: auto.
The size of the generated image. One of 1024x1024, 1024x1536,
1536x1024, or auto. Default: auto.
JsonValue;
The type of the local shell tool. Always local_shell.
class FunctionShellTool:A tool that allows the model to execute shell commands.
A tool that allows the model to execute shell commands.
The type of the shell tool. Always shell.
class CustomTool:A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
The name of the custom tool, used to identify it in tool calls.
The type of the custom tool. Always custom.
Optional description of the custom tool, used to provide more context.
The input format for the custom tool. Default is unconstrained text.
The input format for the custom tool. Default is unconstrained text.
JsonValue;
Unconstrained text format. Always text.
Grammar
The grammar definition.
Syntax syntaxThe syntax of the grammar definition. One of lark or regex.
The syntax of the grammar definition. One of lark or regex.
Grammar format. Always grammar.
class WebSearchPreviewTool:This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
Type typeThe type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
Optional<SearchContextSize> searchContextSizeHigh level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
Optional<UserLocation> userLocationThe user's location.
The user's location.
The type of location approximation. Always approximate.
Free text input for the city of the user, e.g. San Francisco.
The two-letter ISO country code of the user, e.g. US.
Free text input for the region of the user, e.g. California.
The IANA timezone of the user, e.g. America/Los_Angeles.
class ApplyPatchTool:Allows the assistant to create, delete, or update files using unified diffs.
Allows the assistant to create, delete, or update files using unified diffs.
The type of the tool. Always apply_patch.
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.
Whether to run the model response in the background. Learn more.
Unix timestamp (in seconds) of when this Response was completed.
Only present when the status is completed.
Optional<Conversation> conversationThe conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
The unique ID of the conversation that this response was associated with.
An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
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.
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.
Reference to a prompt template and its variables.
Learn more.
Reference to a prompt template and its variables. Learn more.
The unique identifier of the prompt template to use.
Optional<Variables> variablesOptional map of values to substitute in for variables in your
prompt. The substitution values can either be strings, or other
Response input types like images or files.
Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Optional version of the prompt template.
Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
Optional<PromptCacheRetention> promptCacheRetentionThe 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.
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.
gpt-5 and o-series models only
Configuration options for
reasoning models.
gpt-5 and o-series models only
Configuration options for reasoning models.
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1 default to medium reasoning effort, and do not support none.
- The
gpt-5-pro model defaults to (and only supports) high reasoning effort.
xhigh is supported for all models after gpt-5.1-codex-max.
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. - The
gpt-5-promodel defaults to (and only supports)highreasoning effort. xhighis supported for all models aftergpt-5.1-codex-max.
DeprecatedOptional<GenerateSummary> generateSummaryDeprecated: use summary instead.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
Deprecated: use summary instead.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
Optional<Summary> summaryA summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
concise is supported for computer-use-preview models and all reasoning models after gpt-5.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
concise is supported for computer-use-preview models and all reasoning models after gpt-5.
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. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
Optional<ServiceTier> serviceTierSpecifies 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' or 'priority', then the request will be processed with the corresponding service tier.
- 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.
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' or 'priority', then the request will be processed with the corresponding service tier.
- 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.
The status of the response generation. One of completed, failed,
in_progress, cancelled, queued, or incomplete.
The status of the response generation. One of completed, failed,
in_progress, cancelled, queued, or incomplete.
Configuration options for a text response from the model. Can be plain
text or structured JSON data. Learn more:
Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
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.
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.
class ResponseFormatText:Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatTextJsonSchemaConfig:JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
The type of response format being defined. Always json_schema.
A description of what the response format is for, used by the model to determine how to respond in the format.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
class ResponseFormatJsonObject:JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
Optional<Verbosity> verbosityConstrains the verbosity of the model's response. Lower values will result in
more concise responses, while higher values will result in more verbose responses.
Currently supported values are low, medium, and high.
Constrains the verbosity of the model's response. Lower values will result in
more concise responses, while higher values will result in more verbose responses.
Currently supported values are low, medium, and high.
An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.
Optional<Truncation> truncationThe 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.
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.
Represents token usage details including input tokens, output tokens,
a breakdown of output tokens, and the total tokens used.
Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
The number of input tokens.
InputTokensDetails inputTokensDetailsA detailed breakdown of the input tokens.
A detailed breakdown of the input tokens.
The number of tokens that were retrieved from the cache. More on prompt caching.
The number of output tokens.
OutputTokensDetails outputTokensDetailsA detailed breakdown of the output tokens.
A detailed breakdown of the output tokens.
The number of reasoning tokens.
The total number of tokens used.
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.
The sequence number of this event.
The type of the event. Always response.in_progress.
class ResponseFailedEvent:An event that is emitted when a response fails.
An event that is emitted when a response fails.
Response responseThe response that failed.
The response that failed.
Unique identifier for this Response.
Unix timestamp (in seconds) of when this Response was created.
An error object returned when the model fails to generate a Response.
An error object returned when the model fails to generate a Response.
Code codeThe error code for the response.
The error code for the response.
A human-readable description of the error.
Optional<IncompleteDetails> incompleteDetailsDetails about why the response is incomplete.
Details about why the response is incomplete.
Optional<Reason> reasonThe reason why the response is incomplete.
The reason why the response is incomplete.
Optional<Instructions> instructionsA 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.
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.
List<ResponseInputItem>
class EasyInputMessage:A message input to the model with a role indicating instruction following
hierarchy. Instructions given with the developer or system role take
precedence over instructions given with the user role. Messages with the
assistant role are presumed to have been generated by the model in previous
interactions.
A message input to the model with a role indicating instruction following
hierarchy. Instructions given with the developer or system role take
precedence over instructions given with the user role. Messages with the
assistant role are presumed to have been generated by the model in previous
interactions.
Content contentText, image, or audio input to the model, used to generate a response.
Can also contain previous assistant responses.
Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
List<ResponseInputContent>
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Role roleThe role of the message input. One of user, assistant, system, or
developer.
The role of the message input. One of user, assistant, system, or
developer.
The type of the message input. Always message.
Message
List<ResponseInputContent> contentA list of one or many input items to the model, containing different content
types.
A list of one or many input items to the model, containing different content types.
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Role roleThe role of the message input. One of user, system, or developer.
The role of the message input. One of user, system, or developer.
Optional<Status> statusThe status of item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the message input. Always set to message.
class ResponseOutputMessage:An output message from the model.
An output message from the model.
The unique ID of the output message.
List<Content> contentThe content of the output message.
The content of the output message.
class ResponseOutputText:A text output from the model.
A text output from the model.
List<Annotation> annotationsThe annotations of the text output.
The annotations of the text output.
class FileCitation:A citation to a file.
A citation to a file.
The ID of the file.
The filename of the file cited.
The index of the file in the list of files.
The type of the file citation. Always file_citation.
class UrlCitation:A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
The index of the last character of the URL citation in the message.
The index of the first character of the URL citation in the message.
The title of the web resource.
The type of the URL citation. Always url_citation.
The URL of the web resource.
class ContainerFileCitation:A citation for a container file used to generate a model response.
A citation for a container file used to generate a model response.
The ID of the container file.
The index of the last character of the container file citation in the message.
The ID of the file.
The filename of the container file cited.
The index of the first character of the container file citation in the message.
The type of the container file citation. Always container_file_citation.
class FilePath:A path to a file.
A path to a file.
The ID of the file.
The index of the file in the list of files.
The type of the file path. Always file_path.
The text output from the model.
The type of the output text. Always output_text.
Optional<List<Logprob>> logprobs
List<TopLogprob> topLogprobs
class ResponseOutputRefusal:A refusal from the model.
A refusal from the model.
The refusal explanation from the model.
The type of the refusal. Always refusal.
The role of the output message. Always assistant.
Status statusThe status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The type of the output message. Always message.
class ResponseFileSearchToolCall:The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
The unique ID of the file search tool call.
The queries used to search for files.
Status statusThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The type of the file search tool call. Always file_search_call.
Optional<List<Result>> resultsThe results of the file search tool call.
The results of the file search tool call.
Optional<Attributes> attributesSet 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, booleans, or numbers.
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, booleans, or numbers.
The unique ID of the file.
The name of the file.
The relevance score of the file - a value between 0 and 1.
The text that was retrieved from the file.
class ResponseComputerToolCall:A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
The unique ID of the computer call.
Action actionA click action.
A click action.
class Click:A click action.
A click action.
Button buttonIndicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Specifies the event type. For a click action, this property is always click.
The x-coordinate where the click occurred.
The y-coordinate where the click occurred.
class DoubleClick:A double click action.
A double click action.
Specifies the event type. For a double click action, this property is always set to double_click.
The x-coordinate where the double click occurred.
The y-coordinate where the double click occurred.
class Drag:A drag action.
A drag action.
List<Path> pathAn array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]
An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]The x-coordinate.
The y-coordinate.
Specifies the event type. For a drag action, this property is always set to drag.
class Keypress:A collection of keypresses the model would like to perform.
A collection of keypresses the model would like to perform.
The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
Specifies the event type. For a keypress action, this property is always set to keypress.
class Move:A mouse move action.
A mouse move action.
Specifies the event type. For a move action, this property is always set to move.
The x-coordinate to move to.
The y-coordinate to move to.
JsonValue;
Specifies the event type. For a screenshot action, this property is always set to screenshot.
class Scroll:A scroll action.
A scroll action.
The horizontal scroll distance.
The vertical scroll distance.
Specifies the event type. For a scroll action, this property is always set to scroll.
The x-coordinate where the scroll occurred.
The y-coordinate where the scroll occurred.
class Type:An action to type in text.
An action to type in text.
The text to type.
Specifies the event type. For a type action, this property is always set to type.
JsonValue;
Specifies the event type. For a wait action, this property is always set to wait.
An identifier used when responding to the tool call with output.
List<PendingSafetyCheck> pendingSafetyChecksThe pending safety checks for the computer call.
The pending safety checks for the computer call.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Status statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the computer call. Always computer_call.
ComputerCallOutput
The ID of the computer tool call that produced the output.
A computer screenshot image used with the computer use tool.
A computer screenshot image used with the computer use tool.
Specifies the event type. For a computer screenshot, this property is
always set to computer_screenshot.
The identifier of an uploaded file that contains the screenshot.
The URL of the screenshot image.
The type of the computer tool call output. Always computer_call_output.
The ID of the computer tool call output.
Optional<List<AcknowledgedSafetyCheck>> acknowledgedSafetyChecksThe safety checks reported by the API that have been acknowledged by the developer.
The safety checks reported by the API that have been acknowledged by the developer.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Optional<Status> statusThe status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
class ResponseFunctionWebSearch:The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
The unique ID of the web search tool call.
Action actionAn object describing the specific action taken in this web search call.
Includes details on how the model used the web (search, open_page, find_in_page).
An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
class Search:Action type "search" - Performs a web search query.
Action type "search" - Performs a web search query.
[DEPRECATED] The search query.
The action type.
The search queries.
Optional<List<Source>> sourcesThe sources used in the search.
The sources used in the search.
The type of source. Always url.
The URL of the source.
class OpenPage:Action type "open_page" - Opens a specific URL from search results.
Action type "open_page" - Opens a specific URL from search results.
The action type.
The URL opened by the model.
class FindInPage:Action type "find_in_page": Searches for a pattern within a loaded page.
Action type "find_in_page": Searches for a pattern within a loaded page.
The pattern or text to search for within the page.
The action type.
The URL of the page searched for the pattern.
Status statusThe status of the web search tool call.
The status of the web search tool call.
The type of the web search tool call. Always web_search_call.
class ResponseFunctionToolCall:A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
A JSON string of the arguments to pass to the function.
The unique ID of the function tool call generated by the model.
The name of the function to run.
The type of the function tool call. Always function_call.
The unique ID of the function tool call.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
FunctionCallOutput
The unique ID of the function tool call generated by the model.
Output outputText, image, or file output of the function tool call.
Text, image, or file output of the function tool call.
class ResponseInputTextContent:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImageContent:An image input to the model. Learn about image inputs
An image input to the model. Learn about image inputs
The type of the input item. Always input_image.
Optional<Detail> detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFileContent:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The base64-encoded data of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
The type of the function tool call output. Always function_call_output.
The unique ID of the function tool call output. Populated when this item is returned via API.
Optional<Status> statusThe status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
class ResponseReasoningItem:A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
The unique identifier of the reasoning content.
List<Summary> summaryReasoning summary content.
Reasoning summary content.
A summary of the reasoning output from the model so far.
The type of the object. Always summary_text.
The type of the object. Always reasoning.
Optional<List<Content>> contentReasoning text content.
Reasoning text content.
The reasoning text from the model.
The type of the reasoning text. Always reasoning_text.
The encrypted content of the reasoning item - populated when a response is
generated with reasoning.encrypted_content in the include parameter.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseCompactionItemParam:A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
The encrypted content of the compaction summary.
The type of the item. Always compaction.
The ID of the compaction item.
ImageGenerationCall
The unique ID of the image generation call.
The generated image encoded in base64.
Status statusThe status of the image generation call.
The status of the image generation call.
The type of the image generation call. Always image_generation_call.
class ResponseCodeInterpreterToolCall:A tool call to run code.
A tool call to run code.
The unique ID of the code interpreter tool call.
The code to run, or null if not available.
The ID of the container used to run the code.
Optional<List<Output>> outputsThe outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
class Logs:The logs output from the code interpreter.
The logs output from the code interpreter.
The logs output from the code interpreter.
The type of the output. Always logs.
class Image:The image output from the code interpreter.
The image output from the code interpreter.
The type of the output. Always image.
The URL of the image output from the code interpreter.
Status statusThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The type of the code interpreter tool call. Always code_interpreter_call.
LocalShellCall
The unique ID of the local shell call.
Action actionExecute a shell command on the server.
Execute a shell command on the server.
The command to run.
Environment variables to set for the command.
The type of the local shell action. Always exec.
Optional timeout in milliseconds for the command.
Optional user to run the command as.
Optional working directory to run the command in.
The unique ID of the local shell tool call generated by the model.
Status statusThe status of the local shell call.
The status of the local shell call.
The type of the local shell call. Always local_shell_call.
LocalShellCallOutput
The unique ID of the local shell tool call generated by the model.
A JSON string of the output of the local shell tool call.
The type of the local shell tool call output. Always local_shell_call_output.
Optional<Status> statusThe status of the item. One of in_progress, completed, or incomplete.
The status of the item. One of in_progress, completed, or incomplete.
ShellCall
Action actionThe shell commands and limits that describe how to run the tool call.
The shell commands and limits that describe how to run the tool call.
Ordered shell commands for the execution environment to run.
Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
Maximum wall-clock time in milliseconds to allow the shell commands to run.
The unique ID of the shell tool call generated by the model.
The type of the item. Always shell_call.
The unique ID of the shell tool call. Populated when this item is returned via API.
Optional<Status> statusThe status of the shell call. One of in_progress, completed, or incomplete.
The status of the shell call. One of in_progress, completed, or incomplete.
ShellCallOutput
The unique ID of the shell tool call generated by the model.
List<ResponseFunctionShellCallOutputContent> outputCaptured chunks of stdout and stderr output, along with their associated outcomes.
Captured chunks of stdout and stderr output, along with their associated outcomes.
Outcome outcomeThe exit or timeout outcome associated with this shell call.
The exit or timeout outcome associated with this shell call.
JsonValue;
The outcome type. Always timeout.
class Exit:Indicates that the shell commands finished and returned an exit code.
Indicates that the shell commands finished and returned an exit code.
The exit code returned by the shell process.
The outcome type. Always exit.
Captured stderr output for the shell call.
Captured stdout output for the shell call.
The type of the item. Always shell_call_output.
The unique ID of the shell tool call output. Populated when this item is returned via API.
The maximum number of UTF-8 characters captured for this shell call's combined output.
Optional<Status> statusThe status of the shell call output.
The status of the shell call output.
ApplyPatchCall
The unique ID of the apply patch tool call generated by the model.
Operation operationThe specific create, delete, or update instruction for the apply_patch tool call.
The specific create, delete, or update instruction for the apply_patch tool call.
class CreateFile:Instruction for creating a new file via the apply_patch tool.
Instruction for creating a new file via the apply_patch tool.
Unified diff content to apply when creating the file.
Path of the file to create relative to the workspace root.
The operation type. Always create_file.
class DeleteFile:Instruction for deleting an existing file via the apply_patch tool.
Instruction for deleting an existing file via the apply_patch tool.
Path of the file to delete relative to the workspace root.
The operation type. Always delete_file.
class UpdateFile:Instruction for updating an existing file via the apply_patch tool.
Instruction for updating an existing file via the apply_patch tool.
Unified diff content to apply to the existing file.
Path of the file to update relative to the workspace root.
The operation type. Always update_file.
Status statusThe status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
The type of the item. Always apply_patch_call.
The unique ID of the apply patch tool call. Populated when this item is returned via API.
ApplyPatchCallOutput
The unique ID of the apply patch tool call generated by the model.
Status statusThe status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
The type of the item. Always apply_patch_call_output.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
McpListTools
The unique ID of the list.
The label of the MCP server.
List<Tool> toolsThe tools available on the server.
The tools available on the server.
The JSON schema describing the tool's input.
The name of the tool.
Additional annotations about the tool.
The description of the tool.
The type of the item. Always mcp_list_tools.
Error message if the server could not list tools.
McpApprovalRequest
The unique ID of the approval request.
A JSON string of arguments for the tool.
The name of the tool to run.
The label of the MCP server making the request.
The type of the item. Always mcp_approval_request.
McpApprovalResponse
The ID of the approval request being answered.
Whether the request was approved.
The type of the item. Always mcp_approval_response.
The unique ID of the approval response
Optional reason for the decision.
McpCall
The unique ID of the tool call.
A JSON string of the arguments passed to the tool.
The name of the tool that was run.
The label of the MCP server running the tool.
The type of the item. Always mcp_call.
Unique identifier for the MCP tool call approval request.
Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
The error from the tool call, if any.
The output from the tool call.
Optional<Status> statusThe status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
class ResponseCustomToolCallOutput:The output of a custom tool call from your code, being sent back to the model.
The output of a custom tool call from your code, being sent back to the model.
The call ID, used to map this custom tool call output to a custom tool call.
Output outputThe output from the custom tool call generated by your code.
Can be a string or an list of output content.
The output from the custom tool call generated by your code. Can be a string or an list of output content.
List<FunctionAndCustomToolCallOutput>
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
The type of the custom tool call output. Always custom_tool_call_output.
The unique ID of the custom tool call output in the OpenAI platform.
class ResponseCustomToolCall:A call to a custom tool created by the model.
A call to a custom tool created by the model.
An identifier used to map this custom tool call to a tool call output.
The input for the custom tool call generated by the model.
The name of the custom tool being called.
The type of the custom tool call. Always custom_tool_call.
The unique ID of the custom tool call in the OpenAI platform.
ItemReference
The ID of the item to reference.
The type of item to reference. Always item_reference.
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.
ResponsesModel modelModel ID used to generate the response, like gpt-4o or o3. 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.
Model ID used to generate the response, like gpt-4o or o3. 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.
enum ChatModel:
ResponsesOnlyModel
The object type of this resource - always set to response.
List<ResponseOutputItem> outputAn 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.
An array of content items generated by the model.
- The length and order of items in the
outputarray is dependent on the model's response. - Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs.
class ResponseOutputMessage:An output message from the model.
An output message from the model.
The unique ID of the output message.
List<Content> contentThe content of the output message.
The content of the output message.
class ResponseOutputText:A text output from the model.
A text output from the model.
List<Annotation> annotationsThe annotations of the text output.
The annotations of the text output.
class FileCitation:A citation to a file.
A citation to a file.
The ID of the file.
The filename of the file cited.
The index of the file in the list of files.
The type of the file citation. Always file_citation.
class UrlCitation:A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
The index of the last character of the URL citation in the message.
The index of the first character of the URL citation in the message.
The title of the web resource.
The type of the URL citation. Always url_citation.
The URL of the web resource.
class ContainerFileCitation:A citation for a container file used to generate a model response.
A citation for a container file used to generate a model response.
The ID of the container file.
The index of the last character of the container file citation in the message.
The ID of the file.
The filename of the container file cited.
The index of the first character of the container file citation in the message.
The type of the container file citation. Always container_file_citation.
class FilePath:A path to a file.
A path to a file.
The ID of the file.
The index of the file in the list of files.
The type of the file path. Always file_path.
The text output from the model.
The type of the output text. Always output_text.
Optional<List<Logprob>> logprobs
List<TopLogprob> topLogprobs
class ResponseOutputRefusal:A refusal from the model.
A refusal from the model.
The refusal explanation from the model.
The type of the refusal. Always refusal.
The role of the output message. Always assistant.
Status statusThe status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The type of the output message. Always message.
class ResponseFileSearchToolCall:The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
The unique ID of the file search tool call.
The queries used to search for files.
Status statusThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The type of the file search tool call. Always file_search_call.
Optional<List<Result>> resultsThe results of the file search tool call.
The results of the file search tool call.
Optional<Attributes> attributesSet 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, booleans, or numbers.
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, booleans, or numbers.
The unique ID of the file.
The name of the file.
The relevance score of the file - a value between 0 and 1.
The text that was retrieved from the file.
class ResponseFunctionToolCall:A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
A JSON string of the arguments to pass to the function.
The unique ID of the function tool call generated by the model.
The name of the function to run.
The type of the function tool call. Always function_call.
The unique ID of the function tool call.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseFunctionWebSearch:The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
The unique ID of the web search tool call.
Action actionAn object describing the specific action taken in this web search call.
Includes details on how the model used the web (search, open_page, find_in_page).
An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
class Search:Action type "search" - Performs a web search query.
Action type "search" - Performs a web search query.
[DEPRECATED] The search query.
The action type.
The search queries.
Optional<List<Source>> sourcesThe sources used in the search.
The sources used in the search.
The type of source. Always url.
The URL of the source.
class OpenPage:Action type "open_page" - Opens a specific URL from search results.
Action type "open_page" - Opens a specific URL from search results.
The action type.
The URL opened by the model.
class FindInPage:Action type "find_in_page": Searches for a pattern within a loaded page.
Action type "find_in_page": Searches for a pattern within a loaded page.
The pattern or text to search for within the page.
The action type.
The URL of the page searched for the pattern.
Status statusThe status of the web search tool call.
The status of the web search tool call.
The type of the web search tool call. Always web_search_call.
class ResponseComputerToolCall:A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
The unique ID of the computer call.
Action actionA click action.
A click action.
class Click:A click action.
A click action.
Button buttonIndicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Specifies the event type. For a click action, this property is always click.
The x-coordinate where the click occurred.
The y-coordinate where the click occurred.
class DoubleClick:A double click action.
A double click action.
Specifies the event type. For a double click action, this property is always set to double_click.
The x-coordinate where the double click occurred.
The y-coordinate where the double click occurred.
class Drag:A drag action.
A drag action.
List<Path> pathAn array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]
An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]The x-coordinate.
The y-coordinate.
Specifies the event type. For a drag action, this property is always set to drag.
class Keypress:A collection of keypresses the model would like to perform.
A collection of keypresses the model would like to perform.
The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
Specifies the event type. For a keypress action, this property is always set to keypress.
class Move:A mouse move action.
A mouse move action.
Specifies the event type. For a move action, this property is always set to move.
The x-coordinate to move to.
The y-coordinate to move to.
JsonValue;
Specifies the event type. For a screenshot action, this property is always set to screenshot.
class Scroll:A scroll action.
A scroll action.
The horizontal scroll distance.
The vertical scroll distance.
Specifies the event type. For a scroll action, this property is always set to scroll.
The x-coordinate where the scroll occurred.
The y-coordinate where the scroll occurred.
class Type:An action to type in text.
An action to type in text.
The text to type.
Specifies the event type. For a type action, this property is always set to type.
JsonValue;
Specifies the event type. For a wait action, this property is always set to wait.
An identifier used when responding to the tool call with output.
List<PendingSafetyCheck> pendingSafetyChecksThe pending safety checks for the computer call.
The pending safety checks for the computer call.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Status statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the computer call. Always computer_call.
class ResponseReasoningItem:A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
The unique identifier of the reasoning content.
List<Summary> summaryReasoning summary content.
Reasoning summary content.
A summary of the reasoning output from the model so far.
The type of the object. Always summary_text.
The type of the object. Always reasoning.
Optional<List<Content>> contentReasoning text content.
Reasoning text content.
The reasoning text from the model.
The type of the reasoning text. Always reasoning_text.
The encrypted content of the reasoning item - populated when a response is
generated with reasoning.encrypted_content in the include parameter.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseCompactionItem:A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
The unique ID of the compaction item.
The encrypted content that was produced by compaction.
The type of the item. Always compaction.
The identifier of the actor that created the item.
ImageGenerationCall
The unique ID of the image generation call.
The generated image encoded in base64.
Status statusThe status of the image generation call.
The status of the image generation call.
The type of the image generation call. Always image_generation_call.
class ResponseCodeInterpreterToolCall:A tool call to run code.
A tool call to run code.
The unique ID of the code interpreter tool call.
The code to run, or null if not available.
The ID of the container used to run the code.
Optional<List<Output>> outputsThe outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
class Logs:The logs output from the code interpreter.
The logs output from the code interpreter.
The logs output from the code interpreter.
The type of the output. Always logs.
class Image:The image output from the code interpreter.
The image output from the code interpreter.
The type of the output. Always image.
The URL of the image output from the code interpreter.
Status statusThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The type of the code interpreter tool call. Always code_interpreter_call.
LocalShellCall
The unique ID of the local shell call.
Action actionExecute a shell command on the server.
Execute a shell command on the server.
The command to run.
Environment variables to set for the command.
The type of the local shell action. Always exec.
Optional timeout in milliseconds for the command.
Optional user to run the command as.
Optional working directory to run the command in.
The unique ID of the local shell tool call generated by the model.
Status statusThe status of the local shell call.
The status of the local shell call.
The type of the local shell call. Always local_shell_call.
class ResponseFunctionShellToolCall:A tool call that executes one or more shell commands in a managed environment.
A tool call that executes one or more shell commands in a managed environment.
The unique ID of the shell tool call. Populated when this item is returned via API.
Action actionThe shell commands and limits that describe how to run the tool call.
The shell commands and limits that describe how to run the tool call.
Optional maximum number of characters to return from each command.
Optional timeout in milliseconds for the commands.
The unique ID of the shell tool call generated by the model.
Status statusThe status of the shell call. One of in_progress, completed, or incomplete.
The status of the shell call. One of in_progress, completed, or incomplete.
The type of the item. Always shell_call.
The ID of the entity that created this tool call.
class ResponseFunctionShellToolCallOutput:The output of a shell tool call that was emitted.
The output of a shell tool call that was emitted.
The unique ID of the shell call output. Populated when this item is returned via API.
The unique ID of the shell tool call generated by the model.
The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
List<Output> outputAn array of shell call output contents
An array of shell call output contents
Outcome outcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
JsonValue;
The outcome type. Always timeout.
class Exit:Indicates that the shell commands finished and returned an exit code.
Indicates that the shell commands finished and returned an exit code.
Exit code from the shell process.
The outcome type. Always exit.
The standard error output that was captured.
The standard output that was captured.
The identifier of the actor that created the item.
Status statusThe status of the shell call output. One of in_progress, completed, or incomplete.
The status of the shell call output. One of in_progress, completed, or incomplete.
The type of the shell call output. Always shell_call_output.
The identifier of the actor that created the item.
class ResponseApplyPatchToolCall:A tool call that applies file diffs by creating, deleting, or updating files.
A tool call that applies file diffs by creating, deleting, or updating files.
The unique ID of the apply patch tool call. Populated when this item is returned via API.
The unique ID of the apply patch tool call generated by the model.
Operation operationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
One of the create_file, delete_file, or update_file operations applied via apply_patch.
class CreateFile:Instruction describing how to create a file via the apply_patch tool.
Instruction describing how to create a file via the apply_patch tool.
Diff to apply.
Path of the file to create.
Create a new file with the provided diff.
class DeleteFile:Instruction describing how to delete a file via the apply_patch tool.
Instruction describing how to delete a file via the apply_patch tool.
Path of the file to delete.
Delete the specified file.
class UpdateFile:Instruction describing how to update a file via the apply_patch tool.
Instruction describing how to update a file via the apply_patch tool.
Diff to apply.
Path of the file to update.
Update an existing file with the provided diff.
Status statusThe status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
The type of the item. Always apply_patch_call.
The ID of the entity that created this tool call.
class ResponseApplyPatchToolCallOutput:The output emitted by an apply patch tool call.
The output emitted by an apply patch tool call.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
The unique ID of the apply patch tool call generated by the model.
Status statusThe status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
The type of the item. Always apply_patch_call_output.
The ID of the entity that created this tool call output.
Optional textual output returned by the apply patch tool.
McpCall
The unique ID of the tool call.
A JSON string of the arguments passed to the tool.
The name of the tool that was run.
The label of the MCP server running the tool.
The type of the item. Always mcp_call.
Unique identifier for the MCP tool call approval request.
Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
The error from the tool call, if any.
The output from the tool call.
Optional<Status> statusThe status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
McpListTools
The unique ID of the list.
The label of the MCP server.
List<Tool> toolsThe tools available on the server.
The tools available on the server.
The JSON schema describing the tool's input.
The name of the tool.
Additional annotations about the tool.
The description of the tool.
The type of the item. Always mcp_list_tools.
Error message if the server could not list tools.
McpApprovalRequest
The unique ID of the approval request.
A JSON string of arguments for the tool.
The name of the tool to run.
The label of the MCP server making the request.
The type of the item. Always mcp_approval_request.
class ResponseCustomToolCall:A call to a custom tool created by the model.
A call to a custom tool created by the model.
An identifier used to map this custom tool call to a tool call output.
The input for the custom tool call generated by the model.
The name of the custom tool being called.
The type of the custom tool call. Always custom_tool_call.
The unique ID of the custom tool call in the OpenAI platform.
Whether to allow the model to run tool calls in parallel.
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.
ToolChoice toolChoiceHow 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.
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.
enum ToolChoiceOptions: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.
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.
class ToolChoiceAllowed:Constrains the tools available to the model to a pre-defined set.
Constrains the tools available to the model to a pre-defined set.
Mode modeConstrains the tools available to the model to a pre-defined set.
auto allows the model to pick from among the allowed tools and generate a
message.
required requires the model to call one or more of the allowed tools.
Constrains the tools available to the model to a pre-defined set.
auto allows the model to pick from among the allowed tools and generate a
message.
required requires the model to call one or more of the allowed tools.
A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[
{ "type": "function", "name": "get_weather" },
{ "type": "mcp", "server_label": "deepwiki" },
{ "type": "image_generation" }
]Allowed tool configuration type. Always allowed_tools.
class ToolChoiceTypes:Indicates that the model should use a built-in tool to generate a response.
Learn more about built-in tools.
Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
Type typeThe type of hosted tool the model should to use. Learn more about
built-in tools.
Allowed values are:
file_searchweb_search_previewcomputer_use_previewcode_interpreterimage_generation
The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
file_searchweb_search_previewcomputer_use_previewcode_interpreterimage_generation
class ToolChoiceFunction:Use this option to force the model to call a specific function.
Use this option to force the model to call a specific function.
The name of the function to call.
For function calling, the type is always function.
class ToolChoiceMcp:Use this option to force the model to call a specific tool on a remote MCP server.
Use this option to force the model to call a specific tool on a remote MCP server.
The label of the MCP server to use.
For MCP tools, the type is always mcp.
The name of the tool to call on the server.
class ToolChoiceCustom:Use this option to force the model to call a specific custom tool.
Use this option to force the model to call a specific custom tool.
The name of the custom tool to call.
For custom tool calling, the type is always custom.
class ToolChoiceApplyPatch:Forces the model to call the apply_patch tool when executing a tool call.
Forces the model to call the apply_patch tool when executing a tool call.
The tool to call. Always apply_patch.
class ToolChoiceShell:Forces the model to call the shell tool when a tool call is required.
Forces the model to call the shell tool when a tool call is required.
The tool to call. Always shell.
List<Tool> toolsAn 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
or file search. Learn more about
built-in 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.
- 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. You can also use
custom tools to call your own code.
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 or file search. Learn more about built-in 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.
- 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. You can also use custom tools to call your own code.
class FunctionTool:Defines a function in your own code the model can choose to call. Learn more about function calling.
Defines a function in your own code the model can choose to call. Learn more about function calling.
The name of the function to call.
A JSON schema object describing the parameters of the function.
Whether to enforce strict parameter validation. Default true.
The type of the function tool. Always function.
A description of the function. Used by the model to determine whether or not to call the function.
class FileSearchTool:A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
The type of the file search tool. Always file_search.
The IDs of the vector stores to search.
Optional<Filters> filtersA filter to apply.
A filter to apply.
class ComparisonFilter:A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
The key to compare against the value.
Type typeSpecifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Value valueThe value to compare against the attribute key; supports string, number, or boolean types.
The value to compare against the attribute key; supports string, number, or boolean types.
List<ComparisonFilterValueItem>
class CompoundFilter:Combine multiple filters using and or or.
Combine multiple filters using and or or.
List<Filter> filtersArray of filters to combine. Items can be ComparisonFilter or CompoundFilter.
Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
class ComparisonFilter:A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
The key to compare against the value.
Type typeSpecifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Value valueThe value to compare against the attribute key; supports string, number, or boolean types.
The value to compare against the attribute key; supports string, number, or boolean types.
List<ComparisonFilterValueItem>
Type typeType of operation: and or or.
Type of operation: and or or.
The maximum number of results to return. This number should be between 1 and 50 inclusive.
Optional<RankingOptions> rankingOptionsRanking options for search.
Ranking options for search.
Optional<HybridSearch> hybridSearchWeights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
The weight of the embedding in the reciprocal ranking fusion.
The weight of the text in the reciprocal ranking fusion.
Optional<Ranker> rankerThe ranker to use for the file search.
The ranker to use for the file search.
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.
class ComputerTool:A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
The height of the computer display.
The width of the computer display.
Environment environmentThe type of computer environment to control.
The type of computer environment to control.
The type of the computer use tool. Always computer_use_preview.
class WebSearchTool:Search the Internet for sources related to the prompt. Learn more about the
web search tool.
Search the Internet for sources related to the prompt. Learn more about the web search tool.
Type typeThe type of the web search tool. One of web_search or web_search_2025_08_26.
The type of the web search tool. One of web_search or web_search_2025_08_26.
Optional<Filters> filtersFilters for the search.
Filters for the search.
Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example: ["pubmed.ncbi.nlm.nih.gov"]
Optional<SearchContextSize> searchContextSizeHigh level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
Optional<UserLocation> userLocationThe approximate location of the user.
The approximate location of the user.
Free text input for the city of the user, e.g. San Francisco.
The two-letter ISO country code of the user, e.g. US.
Free text input for the region of the user, e.g. California.
The IANA timezone of the user, e.g. America/Los_Angeles.
The type of location approximation. Always approximate.
Mcp
A label for this MCP server, used to identify it in tool calls.
The type of the MCP tool. Always mcp.
Optional<AllowedTools> allowedToolsList of allowed tool names or a filter object.
List of allowed tool names or a filter object.
class McpToolFilter:A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
Optional<ConnectorId> connectorIdIdentifier for service connectors, like those available in ChatGPT. One of
server_url or connector_id must be provided. Learn more about service
connectors here.
Currently supported connector_id values are:
- Dropbox:
connector_dropbox
- Gmail:
connector_gmail
- Google Calendar:
connector_googlecalendar
- Google Drive:
connector_googledrive
- Microsoft Teams:
connector_microsoftteams
- Outlook Calendar:
connector_outlookcalendar
- Outlook Email:
connector_outlookemail
- SharePoint:
connector_sharepoint
Identifier for service connectors, like those available in ChatGPT. One of
server_url or connector_id must be provided. Learn more about service
connectors here.
Currently supported connector_id values are:
- Dropbox:
connector_dropbox - Gmail:
connector_gmail - Google Calendar:
connector_googlecalendar - Google Drive:
connector_googledrive - Microsoft Teams:
connector_microsoftteams - Outlook Calendar:
connector_outlookcalendar - Outlook Email:
connector_outlookemail - SharePoint:
connector_sharepoint
Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
Optional<RequireApproval> requireApprovalSpecify which of the MCP server's tools require approval.
Specify which of the MCP server's tools require approval.
class McpToolApprovalFilter:Specify which of the MCP server's tools require approval. Can be
always, never, or a filter object associated with tools
that require approval.
Specify which of the MCP server's tools require approval. Can be
always, never, or a filter object associated with tools
that require approval.
Optional<Always> alwaysA filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
Optional<Never> neverA filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
enum McpToolApprovalSetting:Specify a single approval policy for all tools. One of always or
never. When set to always, all tools will require approval. When
set to never, all tools will not require approval.
Specify a single approval policy for all tools. One of always or
never. When set to always, all tools will require approval. When
set to never, all tools will not require approval.
Optional description of the MCP server, used to provide more context.
The URL for the MCP server. One of server_url or connector_id must be
provided.
CodeInterpreter
Container containerThe code interpreter container. Can be a container ID or an object that
specifies uploaded file IDs to make available to your code, along with an
optional memory_limit setting.
The code interpreter container. Can be a container ID or an object that
specifies uploaded file IDs to make available to your code, along with an
optional memory_limit setting.
class CodeInterpreterToolAuto:Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
Always auto.
An optional list of uploaded files to make available to your code.
Optional<MemoryLimit> memoryLimitThe memory limit for the code interpreter container.
The memory limit for the code interpreter container.
The type of the code interpreter tool. Always code_interpreter.
ImageGeneration
The type of the image generation tool. Always image_generation.
Optional<Action> actionWhether to generate a new image or edit an existing image. Default: auto.
Whether to generate a new image or edit an existing image. Default: auto.
Optional<Background> backgroundBackground type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Optional<InputFidelity> inputFidelityControl how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Optional<InputImageMask> inputImageMaskOptional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
File ID for the mask image.
Base64-encoded mask image.
Optional<Model> modelThe image generation model to use. Default: gpt-image-1.
The image generation model to use. Default: gpt-image-1.
Optional<Moderation> moderationModeration level for the generated image. Default: auto.
Moderation level for the generated image. Default: auto.
Compression level for the output image. Default: 100.
Optional<OutputFormat> outputFormatThe output format of the generated image. One of png, webp, or
jpeg. Default: png.
The output format of the generated image. One of png, webp, or
jpeg. Default: png.
Number of partial images to generate in streaming mode, from 0 (default value) to 3.
Optional<Quality> qualityThe quality of the generated image. One of low, medium, high,
or auto. Default: auto.
The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
Optional<Size> sizeThe size of the generated image. One of 1024x1024, 1024x1536,
1536x1024, or auto. Default: auto.
The size of the generated image. One of 1024x1024, 1024x1536,
1536x1024, or auto. Default: auto.
JsonValue;
The type of the local shell tool. Always local_shell.
class FunctionShellTool:A tool that allows the model to execute shell commands.
A tool that allows the model to execute shell commands.
The type of the shell tool. Always shell.
class CustomTool:A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
The name of the custom tool, used to identify it in tool calls.
The type of the custom tool. Always custom.
Optional description of the custom tool, used to provide more context.
The input format for the custom tool. Default is unconstrained text.
The input format for the custom tool. Default is unconstrained text.
JsonValue;
Unconstrained text format. Always text.
Grammar
The grammar definition.
Syntax syntaxThe syntax of the grammar definition. One of lark or regex.
The syntax of the grammar definition. One of lark or regex.
Grammar format. Always grammar.
class WebSearchPreviewTool:This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
Type typeThe type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
Optional<SearchContextSize> searchContextSizeHigh level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
Optional<UserLocation> userLocationThe user's location.
The user's location.
The type of location approximation. Always approximate.
Free text input for the city of the user, e.g. San Francisco.
The two-letter ISO country code of the user, e.g. US.
Free text input for the region of the user, e.g. California.
The IANA timezone of the user, e.g. America/Los_Angeles.
class ApplyPatchTool:Allows the assistant to create, delete, or update files using unified diffs.
Allows the assistant to create, delete, or update files using unified diffs.
The type of the tool. Always apply_patch.
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.
Whether to run the model response in the background. Learn more.
Unix timestamp (in seconds) of when this Response was completed.
Only present when the status is completed.
Optional<Conversation> conversationThe conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
The unique ID of the conversation that this response was associated with.
An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
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.
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.
Reference to a prompt template and its variables.
Learn more.
Reference to a prompt template and its variables. Learn more.
The unique identifier of the prompt template to use.
Optional<Variables> variablesOptional map of values to substitute in for variables in your
prompt. The substitution values can either be strings, or other
Response input types like images or files.
Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Optional version of the prompt template.
Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
Optional<PromptCacheRetention> promptCacheRetentionThe 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.
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.
gpt-5 and o-series models only
Configuration options for
reasoning models.
gpt-5 and o-series models only
Configuration options for reasoning models.
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1 default to medium reasoning effort, and do not support none.
- The
gpt-5-pro model defaults to (and only supports) high reasoning effort.
xhigh is supported for all models after gpt-5.1-codex-max.
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. - The
gpt-5-promodel defaults to (and only supports)highreasoning effort. xhighis supported for all models aftergpt-5.1-codex-max.
DeprecatedOptional<GenerateSummary> generateSummaryDeprecated: use summary instead.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
Deprecated: use summary instead.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
Optional<Summary> summaryA summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
concise is supported for computer-use-preview models and all reasoning models after gpt-5.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
concise is supported for computer-use-preview models and all reasoning models after gpt-5.
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. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
Optional<ServiceTier> serviceTierSpecifies 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' or 'priority', then the request will be processed with the corresponding service tier.
- 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.
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' or 'priority', then the request will be processed with the corresponding service tier.
- 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.
The status of the response generation. One of completed, failed,
in_progress, cancelled, queued, or incomplete.
The status of the response generation. One of completed, failed,
in_progress, cancelled, queued, or incomplete.
Configuration options for a text response from the model. Can be plain
text or structured JSON data. Learn more:
Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
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.
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.
class ResponseFormatText:Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatTextJsonSchemaConfig:JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
The type of response format being defined. Always json_schema.
A description of what the response format is for, used by the model to determine how to respond in the format.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
class ResponseFormatJsonObject:JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
Optional<Verbosity> verbosityConstrains the verbosity of the model's response. Lower values will result in
more concise responses, while higher values will result in more verbose responses.
Currently supported values are low, medium, and high.
Constrains the verbosity of the model's response. Lower values will result in
more concise responses, while higher values will result in more verbose responses.
Currently supported values are low, medium, and high.
An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.
Optional<Truncation> truncationThe 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.
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.
Represents token usage details including input tokens, output tokens,
a breakdown of output tokens, and the total tokens used.
Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
The number of input tokens.
InputTokensDetails inputTokensDetailsA detailed breakdown of the input tokens.
A detailed breakdown of the input tokens.
The number of tokens that were retrieved from the cache. More on prompt caching.
The number of output tokens.
OutputTokensDetails outputTokensDetailsA detailed breakdown of the output tokens.
A detailed breakdown of the output tokens.
The number of reasoning tokens.
The total number of tokens used.
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.
The sequence number of this event.
The type of the event. Always response.failed.
class ResponseIncompleteEvent:An event that is emitted when a response finishes as incomplete.
An event that is emitted when a response finishes as incomplete.
Response responseThe response that was incomplete.
The response that was incomplete.
Unique identifier for this Response.
Unix timestamp (in seconds) of when this Response was created.
An error object returned when the model fails to generate a Response.
An error object returned when the model fails to generate a Response.
Code codeThe error code for the response.
The error code for the response.
A human-readable description of the error.
Optional<IncompleteDetails> incompleteDetailsDetails about why the response is incomplete.
Details about why the response is incomplete.
Optional<Reason> reasonThe reason why the response is incomplete.
The reason why the response is incomplete.
Optional<Instructions> instructionsA 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.
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.
List<ResponseInputItem>
class EasyInputMessage:A message input to the model with a role indicating instruction following
hierarchy. Instructions given with the developer or system role take
precedence over instructions given with the user role. Messages with the
assistant role are presumed to have been generated by the model in previous
interactions.
A message input to the model with a role indicating instruction following
hierarchy. Instructions given with the developer or system role take
precedence over instructions given with the user role. Messages with the
assistant role are presumed to have been generated by the model in previous
interactions.
Content contentText, image, or audio input to the model, used to generate a response.
Can also contain previous assistant responses.
Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
List<ResponseInputContent>
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Role roleThe role of the message input. One of user, assistant, system, or
developer.
The role of the message input. One of user, assistant, system, or
developer.
The type of the message input. Always message.
Message
List<ResponseInputContent> contentA list of one or many input items to the model, containing different content
types.
A list of one or many input items to the model, containing different content types.
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Role roleThe role of the message input. One of user, system, or developer.
The role of the message input. One of user, system, or developer.
Optional<Status> statusThe status of item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the message input. Always set to message.
class ResponseOutputMessage:An output message from the model.
An output message from the model.
The unique ID of the output message.
List<Content> contentThe content of the output message.
The content of the output message.
class ResponseOutputText:A text output from the model.
A text output from the model.
List<Annotation> annotationsThe annotations of the text output.
The annotations of the text output.
class FileCitation:A citation to a file.
A citation to a file.
The ID of the file.
The filename of the file cited.
The index of the file in the list of files.
The type of the file citation. Always file_citation.
class UrlCitation:A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
The index of the last character of the URL citation in the message.
The index of the first character of the URL citation in the message.
The title of the web resource.
The type of the URL citation. Always url_citation.
The URL of the web resource.
class ContainerFileCitation:A citation for a container file used to generate a model response.
A citation for a container file used to generate a model response.
The ID of the container file.
The index of the last character of the container file citation in the message.
The ID of the file.
The filename of the container file cited.
The index of the first character of the container file citation in the message.
The type of the container file citation. Always container_file_citation.
class FilePath:A path to a file.
A path to a file.
The ID of the file.
The index of the file in the list of files.
The type of the file path. Always file_path.
The text output from the model.
The type of the output text. Always output_text.
Optional<List<Logprob>> logprobs
List<TopLogprob> topLogprobs
class ResponseOutputRefusal:A refusal from the model.
A refusal from the model.
The refusal explanation from the model.
The type of the refusal. Always refusal.
The role of the output message. Always assistant.
Status statusThe status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The type of the output message. Always message.
class ResponseFileSearchToolCall:The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
The unique ID of the file search tool call.
The queries used to search for files.
Status statusThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The type of the file search tool call. Always file_search_call.
Optional<List<Result>> resultsThe results of the file search tool call.
The results of the file search tool call.
Optional<Attributes> attributesSet 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, booleans, or numbers.
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, booleans, or numbers.
The unique ID of the file.
The name of the file.
The relevance score of the file - a value between 0 and 1.
The text that was retrieved from the file.
class ResponseComputerToolCall:A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
The unique ID of the computer call.
Action actionA click action.
A click action.
class Click:A click action.
A click action.
Button buttonIndicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Specifies the event type. For a click action, this property is always click.
The x-coordinate where the click occurred.
The y-coordinate where the click occurred.
class DoubleClick:A double click action.
A double click action.
Specifies the event type. For a double click action, this property is always set to double_click.
The x-coordinate where the double click occurred.
The y-coordinate where the double click occurred.
class Drag:A drag action.
A drag action.
List<Path> pathAn array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]
An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]The x-coordinate.
The y-coordinate.
Specifies the event type. For a drag action, this property is always set to drag.
class Keypress:A collection of keypresses the model would like to perform.
A collection of keypresses the model would like to perform.
The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
Specifies the event type. For a keypress action, this property is always set to keypress.
class Move:A mouse move action.
A mouse move action.
Specifies the event type. For a move action, this property is always set to move.
The x-coordinate to move to.
The y-coordinate to move to.
JsonValue;
Specifies the event type. For a screenshot action, this property is always set to screenshot.
class Scroll:A scroll action.
A scroll action.
The horizontal scroll distance.
The vertical scroll distance.
Specifies the event type. For a scroll action, this property is always set to scroll.
The x-coordinate where the scroll occurred.
The y-coordinate where the scroll occurred.
class Type:An action to type in text.
An action to type in text.
The text to type.
Specifies the event type. For a type action, this property is always set to type.
JsonValue;
Specifies the event type. For a wait action, this property is always set to wait.
An identifier used when responding to the tool call with output.
List<PendingSafetyCheck> pendingSafetyChecksThe pending safety checks for the computer call.
The pending safety checks for the computer call.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Status statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the computer call. Always computer_call.
ComputerCallOutput
The ID of the computer tool call that produced the output.
A computer screenshot image used with the computer use tool.
A computer screenshot image used with the computer use tool.
Specifies the event type. For a computer screenshot, this property is
always set to computer_screenshot.
The identifier of an uploaded file that contains the screenshot.
The URL of the screenshot image.
The type of the computer tool call output. Always computer_call_output.
The ID of the computer tool call output.
Optional<List<AcknowledgedSafetyCheck>> acknowledgedSafetyChecksThe safety checks reported by the API that have been acknowledged by the developer.
The safety checks reported by the API that have been acknowledged by the developer.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Optional<Status> statusThe status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
class ResponseFunctionWebSearch:The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
The unique ID of the web search tool call.
Action actionAn object describing the specific action taken in this web search call.
Includes details on how the model used the web (search, open_page, find_in_page).
An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
class Search:Action type "search" - Performs a web search query.
Action type "search" - Performs a web search query.
[DEPRECATED] The search query.
The action type.
The search queries.
Optional<List<Source>> sourcesThe sources used in the search.
The sources used in the search.
The type of source. Always url.
The URL of the source.
class OpenPage:Action type "open_page" - Opens a specific URL from search results.
Action type "open_page" - Opens a specific URL from search results.
The action type.
The URL opened by the model.
class FindInPage:Action type "find_in_page": Searches for a pattern within a loaded page.
Action type "find_in_page": Searches for a pattern within a loaded page.
The pattern or text to search for within the page.
The action type.
The URL of the page searched for the pattern.
Status statusThe status of the web search tool call.
The status of the web search tool call.
The type of the web search tool call. Always web_search_call.
class ResponseFunctionToolCall:A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
A JSON string of the arguments to pass to the function.
The unique ID of the function tool call generated by the model.
The name of the function to run.
The type of the function tool call. Always function_call.
The unique ID of the function tool call.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
FunctionCallOutput
The unique ID of the function tool call generated by the model.
Output outputText, image, or file output of the function tool call.
Text, image, or file output of the function tool call.
class ResponseInputTextContent:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImageContent:An image input to the model. Learn about image inputs
An image input to the model. Learn about image inputs
The type of the input item. Always input_image.
Optional<Detail> detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFileContent:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The base64-encoded data of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
The type of the function tool call output. Always function_call_output.
The unique ID of the function tool call output. Populated when this item is returned via API.
Optional<Status> statusThe status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
class ResponseReasoningItem:A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
The unique identifier of the reasoning content.
List<Summary> summaryReasoning summary content.
Reasoning summary content.
A summary of the reasoning output from the model so far.
The type of the object. Always summary_text.
The type of the object. Always reasoning.
Optional<List<Content>> contentReasoning text content.
Reasoning text content.
The reasoning text from the model.
The type of the reasoning text. Always reasoning_text.
The encrypted content of the reasoning item - populated when a response is
generated with reasoning.encrypted_content in the include parameter.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseCompactionItemParam:A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
The encrypted content of the compaction summary.
The type of the item. Always compaction.
The ID of the compaction item.
ImageGenerationCall
The unique ID of the image generation call.
The generated image encoded in base64.
Status statusThe status of the image generation call.
The status of the image generation call.
The type of the image generation call. Always image_generation_call.
class ResponseCodeInterpreterToolCall:A tool call to run code.
A tool call to run code.
The unique ID of the code interpreter tool call.
The code to run, or null if not available.
The ID of the container used to run the code.
Optional<List<Output>> outputsThe outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
class Logs:The logs output from the code interpreter.
The logs output from the code interpreter.
The logs output from the code interpreter.
The type of the output. Always logs.
class Image:The image output from the code interpreter.
The image output from the code interpreter.
The type of the output. Always image.
The URL of the image output from the code interpreter.
Status statusThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The type of the code interpreter tool call. Always code_interpreter_call.
LocalShellCall
The unique ID of the local shell call.
Action actionExecute a shell command on the server.
Execute a shell command on the server.
The command to run.
Environment variables to set for the command.
The type of the local shell action. Always exec.
Optional timeout in milliseconds for the command.
Optional user to run the command as.
Optional working directory to run the command in.
The unique ID of the local shell tool call generated by the model.
Status statusThe status of the local shell call.
The status of the local shell call.
The type of the local shell call. Always local_shell_call.
LocalShellCallOutput
The unique ID of the local shell tool call generated by the model.
A JSON string of the output of the local shell tool call.
The type of the local shell tool call output. Always local_shell_call_output.
Optional<Status> statusThe status of the item. One of in_progress, completed, or incomplete.
The status of the item. One of in_progress, completed, or incomplete.
ShellCall
Action actionThe shell commands and limits that describe how to run the tool call.
The shell commands and limits that describe how to run the tool call.
Ordered shell commands for the execution environment to run.
Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
Maximum wall-clock time in milliseconds to allow the shell commands to run.
The unique ID of the shell tool call generated by the model.
The type of the item. Always shell_call.
The unique ID of the shell tool call. Populated when this item is returned via API.
Optional<Status> statusThe status of the shell call. One of in_progress, completed, or incomplete.
The status of the shell call. One of in_progress, completed, or incomplete.
ShellCallOutput
The unique ID of the shell tool call generated by the model.
List<ResponseFunctionShellCallOutputContent> outputCaptured chunks of stdout and stderr output, along with their associated outcomes.
Captured chunks of stdout and stderr output, along with their associated outcomes.
Outcome outcomeThe exit or timeout outcome associated with this shell call.
The exit or timeout outcome associated with this shell call.
JsonValue;
The outcome type. Always timeout.
class Exit:Indicates that the shell commands finished and returned an exit code.
Indicates that the shell commands finished and returned an exit code.
The exit code returned by the shell process.
The outcome type. Always exit.
Captured stderr output for the shell call.
Captured stdout output for the shell call.
The type of the item. Always shell_call_output.
The unique ID of the shell tool call output. Populated when this item is returned via API.
The maximum number of UTF-8 characters captured for this shell call's combined output.
Optional<Status> statusThe status of the shell call output.
The status of the shell call output.
ApplyPatchCall
The unique ID of the apply patch tool call generated by the model.
Operation operationThe specific create, delete, or update instruction for the apply_patch tool call.
The specific create, delete, or update instruction for the apply_patch tool call.
class CreateFile:Instruction for creating a new file via the apply_patch tool.
Instruction for creating a new file via the apply_patch tool.
Unified diff content to apply when creating the file.
Path of the file to create relative to the workspace root.
The operation type. Always create_file.
class DeleteFile:Instruction for deleting an existing file via the apply_patch tool.
Instruction for deleting an existing file via the apply_patch tool.
Path of the file to delete relative to the workspace root.
The operation type. Always delete_file.
class UpdateFile:Instruction for updating an existing file via the apply_patch tool.
Instruction for updating an existing file via the apply_patch tool.
Unified diff content to apply to the existing file.
Path of the file to update relative to the workspace root.
The operation type. Always update_file.
Status statusThe status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
The type of the item. Always apply_patch_call.
The unique ID of the apply patch tool call. Populated when this item is returned via API.
ApplyPatchCallOutput
The unique ID of the apply patch tool call generated by the model.
Status statusThe status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
The type of the item. Always apply_patch_call_output.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
McpListTools
The unique ID of the list.
The label of the MCP server.
List<Tool> toolsThe tools available on the server.
The tools available on the server.
The JSON schema describing the tool's input.
The name of the tool.
Additional annotations about the tool.
The description of the tool.
The type of the item. Always mcp_list_tools.
Error message if the server could not list tools.
McpApprovalRequest
The unique ID of the approval request.
A JSON string of arguments for the tool.
The name of the tool to run.
The label of the MCP server making the request.
The type of the item. Always mcp_approval_request.
McpApprovalResponse
The ID of the approval request being answered.
Whether the request was approved.
The type of the item. Always mcp_approval_response.
The unique ID of the approval response
Optional reason for the decision.
McpCall
The unique ID of the tool call.
A JSON string of the arguments passed to the tool.
The name of the tool that was run.
The label of the MCP server running the tool.
The type of the item. Always mcp_call.
Unique identifier for the MCP tool call approval request.
Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
The error from the tool call, if any.
The output from the tool call.
Optional<Status> statusThe status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
class ResponseCustomToolCallOutput:The output of a custom tool call from your code, being sent back to the model.
The output of a custom tool call from your code, being sent back to the model.
The call ID, used to map this custom tool call output to a custom tool call.
Output outputThe output from the custom tool call generated by your code.
Can be a string or an list of output content.
The output from the custom tool call generated by your code. Can be a string or an list of output content.
List<FunctionAndCustomToolCallOutput>
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
The type of the custom tool call output. Always custom_tool_call_output.
The unique ID of the custom tool call output in the OpenAI platform.
class ResponseCustomToolCall:A call to a custom tool created by the model.
A call to a custom tool created by the model.
An identifier used to map this custom tool call to a tool call output.
The input for the custom tool call generated by the model.
The name of the custom tool being called.
The type of the custom tool call. Always custom_tool_call.
The unique ID of the custom tool call in the OpenAI platform.
ItemReference
The ID of the item to reference.
The type of item to reference. Always item_reference.
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.
ResponsesModel modelModel ID used to generate the response, like gpt-4o or o3. 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.
Model ID used to generate the response, like gpt-4o or o3. 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.
enum ChatModel:
ResponsesOnlyModel
The object type of this resource - always set to response.
List<ResponseOutputItem> outputAn 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.
An array of content items generated by the model.
- The length and order of items in the
outputarray is dependent on the model's response. - Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs.
class ResponseOutputMessage:An output message from the model.
An output message from the model.
The unique ID of the output message.
List<Content> contentThe content of the output message.
The content of the output message.
class ResponseOutputText:A text output from the model.
A text output from the model.
List<Annotation> annotationsThe annotations of the text output.
The annotations of the text output.
class FileCitation:A citation to a file.
A citation to a file.
The ID of the file.
The filename of the file cited.
The index of the file in the list of files.
The type of the file citation. Always file_citation.
class UrlCitation:A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
The index of the last character of the URL citation in the message.
The index of the first character of the URL citation in the message.
The title of the web resource.
The type of the URL citation. Always url_citation.
The URL of the web resource.
class ContainerFileCitation:A citation for a container file used to generate a model response.
A citation for a container file used to generate a model response.
The ID of the container file.
The index of the last character of the container file citation in the message.
The ID of the file.
The filename of the container file cited.
The index of the first character of the container file citation in the message.
The type of the container file citation. Always container_file_citation.
class FilePath:A path to a file.
A path to a file.
The ID of the file.
The index of the file in the list of files.
The type of the file path. Always file_path.
The text output from the model.
The type of the output text. Always output_text.
Optional<List<Logprob>> logprobs
List<TopLogprob> topLogprobs
class ResponseOutputRefusal:A refusal from the model.
A refusal from the model.
The refusal explanation from the model.
The type of the refusal. Always refusal.
The role of the output message. Always assistant.
Status statusThe status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The type of the output message. Always message.
class ResponseFileSearchToolCall:The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
The unique ID of the file search tool call.
The queries used to search for files.
Status statusThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The type of the file search tool call. Always file_search_call.
Optional<List<Result>> resultsThe results of the file search tool call.
The results of the file search tool call.
Optional<Attributes> attributesSet 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, booleans, or numbers.
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, booleans, or numbers.
The unique ID of the file.
The name of the file.
The relevance score of the file - a value between 0 and 1.
The text that was retrieved from the file.
class ResponseFunctionToolCall:A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
A JSON string of the arguments to pass to the function.
The unique ID of the function tool call generated by the model.
The name of the function to run.
The type of the function tool call. Always function_call.
The unique ID of the function tool call.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseFunctionWebSearch:The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
The unique ID of the web search tool call.
Action actionAn object describing the specific action taken in this web search call.
Includes details on how the model used the web (search, open_page, find_in_page).
An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
class Search:Action type "search" - Performs a web search query.
Action type "search" - Performs a web search query.
[DEPRECATED] The search query.
The action type.
The search queries.
Optional<List<Source>> sourcesThe sources used in the search.
The sources used in the search.
The type of source. Always url.
The URL of the source.
class OpenPage:Action type "open_page" - Opens a specific URL from search results.
Action type "open_page" - Opens a specific URL from search results.
The action type.
The URL opened by the model.
class FindInPage:Action type "find_in_page": Searches for a pattern within a loaded page.
Action type "find_in_page": Searches for a pattern within a loaded page.
The pattern or text to search for within the page.
The action type.
The URL of the page searched for the pattern.
Status statusThe status of the web search tool call.
The status of the web search tool call.
The type of the web search tool call. Always web_search_call.
class ResponseComputerToolCall:A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
The unique ID of the computer call.
Action actionA click action.
A click action.
class Click:A click action.
A click action.
Button buttonIndicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Specifies the event type. For a click action, this property is always click.
The x-coordinate where the click occurred.
The y-coordinate where the click occurred.
class DoubleClick:A double click action.
A double click action.
Specifies the event type. For a double click action, this property is always set to double_click.
The x-coordinate where the double click occurred.
The y-coordinate where the double click occurred.
class Drag:A drag action.
A drag action.
List<Path> pathAn array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]
An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]The x-coordinate.
The y-coordinate.
Specifies the event type. For a drag action, this property is always set to drag.
class Keypress:A collection of keypresses the model would like to perform.
A collection of keypresses the model would like to perform.
The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
Specifies the event type. For a keypress action, this property is always set to keypress.
class Move:A mouse move action.
A mouse move action.
Specifies the event type. For a move action, this property is always set to move.
The x-coordinate to move to.
The y-coordinate to move to.
JsonValue;
Specifies the event type. For a screenshot action, this property is always set to screenshot.
class Scroll:A scroll action.
A scroll action.
The horizontal scroll distance.
The vertical scroll distance.
Specifies the event type. For a scroll action, this property is always set to scroll.
The x-coordinate where the scroll occurred.
The y-coordinate where the scroll occurred.
class Type:An action to type in text.
An action to type in text.
The text to type.
Specifies the event type. For a type action, this property is always set to type.
JsonValue;
Specifies the event type. For a wait action, this property is always set to wait.
An identifier used when responding to the tool call with output.
List<PendingSafetyCheck> pendingSafetyChecksThe pending safety checks for the computer call.
The pending safety checks for the computer call.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Status statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the computer call. Always computer_call.
class ResponseReasoningItem:A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
The unique identifier of the reasoning content.
List<Summary> summaryReasoning summary content.
Reasoning summary content.
A summary of the reasoning output from the model so far.
The type of the object. Always summary_text.
The type of the object. Always reasoning.
Optional<List<Content>> contentReasoning text content.
Reasoning text content.
The reasoning text from the model.
The type of the reasoning text. Always reasoning_text.
The encrypted content of the reasoning item - populated when a response is
generated with reasoning.encrypted_content in the include parameter.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseCompactionItem:A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
The unique ID of the compaction item.
The encrypted content that was produced by compaction.
The type of the item. Always compaction.
The identifier of the actor that created the item.
ImageGenerationCall
The unique ID of the image generation call.
The generated image encoded in base64.
Status statusThe status of the image generation call.
The status of the image generation call.
The type of the image generation call. Always image_generation_call.
class ResponseCodeInterpreterToolCall:A tool call to run code.
A tool call to run code.
The unique ID of the code interpreter tool call.
The code to run, or null if not available.
The ID of the container used to run the code.
Optional<List<Output>> outputsThe outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
class Logs:The logs output from the code interpreter.
The logs output from the code interpreter.
The logs output from the code interpreter.
The type of the output. Always logs.
class Image:The image output from the code interpreter.
The image output from the code interpreter.
The type of the output. Always image.
The URL of the image output from the code interpreter.
Status statusThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The type of the code interpreter tool call. Always code_interpreter_call.
LocalShellCall
The unique ID of the local shell call.
Action actionExecute a shell command on the server.
Execute a shell command on the server.
The command to run.
Environment variables to set for the command.
The type of the local shell action. Always exec.
Optional timeout in milliseconds for the command.
Optional user to run the command as.
Optional working directory to run the command in.
The unique ID of the local shell tool call generated by the model.
Status statusThe status of the local shell call.
The status of the local shell call.
The type of the local shell call. Always local_shell_call.
class ResponseFunctionShellToolCall:A tool call that executes one or more shell commands in a managed environment.
A tool call that executes one or more shell commands in a managed environment.
The unique ID of the shell tool call. Populated when this item is returned via API.
Action actionThe shell commands and limits that describe how to run the tool call.
The shell commands and limits that describe how to run the tool call.
Optional maximum number of characters to return from each command.
Optional timeout in milliseconds for the commands.
The unique ID of the shell tool call generated by the model.
Status statusThe status of the shell call. One of in_progress, completed, or incomplete.
The status of the shell call. One of in_progress, completed, or incomplete.
The type of the item. Always shell_call.
The ID of the entity that created this tool call.
class ResponseFunctionShellToolCallOutput:The output of a shell tool call that was emitted.
The output of a shell tool call that was emitted.
The unique ID of the shell call output. Populated when this item is returned via API.
The unique ID of the shell tool call generated by the model.
The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
List<Output> outputAn array of shell call output contents
An array of shell call output contents
Outcome outcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
JsonValue;
The outcome type. Always timeout.
class Exit:Indicates that the shell commands finished and returned an exit code.
Indicates that the shell commands finished and returned an exit code.
Exit code from the shell process.
The outcome type. Always exit.
The standard error output that was captured.
The standard output that was captured.
The identifier of the actor that created the item.
Status statusThe status of the shell call output. One of in_progress, completed, or incomplete.
The status of the shell call output. One of in_progress, completed, or incomplete.
The type of the shell call output. Always shell_call_output.
The identifier of the actor that created the item.
class ResponseApplyPatchToolCall:A tool call that applies file diffs by creating, deleting, or updating files.
A tool call that applies file diffs by creating, deleting, or updating files.
The unique ID of the apply patch tool call. Populated when this item is returned via API.
The unique ID of the apply patch tool call generated by the model.
Operation operationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
One of the create_file, delete_file, or update_file operations applied via apply_patch.
class CreateFile:Instruction describing how to create a file via the apply_patch tool.
Instruction describing how to create a file via the apply_patch tool.
Diff to apply.
Path of the file to create.
Create a new file with the provided diff.
class DeleteFile:Instruction describing how to delete a file via the apply_patch tool.
Instruction describing how to delete a file via the apply_patch tool.
Path of the file to delete.
Delete the specified file.
class UpdateFile:Instruction describing how to update a file via the apply_patch tool.
Instruction describing how to update a file via the apply_patch tool.
Diff to apply.
Path of the file to update.
Update an existing file with the provided diff.
Status statusThe status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
The type of the item. Always apply_patch_call.
The ID of the entity that created this tool call.
class ResponseApplyPatchToolCallOutput:The output emitted by an apply patch tool call.
The output emitted by an apply patch tool call.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
The unique ID of the apply patch tool call generated by the model.
Status statusThe status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
The type of the item. Always apply_patch_call_output.
The ID of the entity that created this tool call output.
Optional textual output returned by the apply patch tool.
McpCall
The unique ID of the tool call.
A JSON string of the arguments passed to the tool.
The name of the tool that was run.
The label of the MCP server running the tool.
The type of the item. Always mcp_call.
Unique identifier for the MCP tool call approval request.
Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
The error from the tool call, if any.
The output from the tool call.
Optional<Status> statusThe status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
McpListTools
The unique ID of the list.
The label of the MCP server.
List<Tool> toolsThe tools available on the server.
The tools available on the server.
The JSON schema describing the tool's input.
The name of the tool.
Additional annotations about the tool.
The description of the tool.
The type of the item. Always mcp_list_tools.
Error message if the server could not list tools.
McpApprovalRequest
The unique ID of the approval request.
A JSON string of arguments for the tool.
The name of the tool to run.
The label of the MCP server making the request.
The type of the item. Always mcp_approval_request.
class ResponseCustomToolCall:A call to a custom tool created by the model.
A call to a custom tool created by the model.
An identifier used to map this custom tool call to a tool call output.
The input for the custom tool call generated by the model.
The name of the custom tool being called.
The type of the custom tool call. Always custom_tool_call.
The unique ID of the custom tool call in the OpenAI platform.
Whether to allow the model to run tool calls in parallel.
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.
ToolChoice toolChoiceHow 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.
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.
enum ToolChoiceOptions: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.
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.
class ToolChoiceAllowed:Constrains the tools available to the model to a pre-defined set.
Constrains the tools available to the model to a pre-defined set.
Mode modeConstrains the tools available to the model to a pre-defined set.
auto allows the model to pick from among the allowed tools and generate a
message.
required requires the model to call one or more of the allowed tools.
Constrains the tools available to the model to a pre-defined set.
auto allows the model to pick from among the allowed tools and generate a
message.
required requires the model to call one or more of the allowed tools.
A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[
{ "type": "function", "name": "get_weather" },
{ "type": "mcp", "server_label": "deepwiki" },
{ "type": "image_generation" }
]Allowed tool configuration type. Always allowed_tools.
class ToolChoiceTypes:Indicates that the model should use a built-in tool to generate a response.
Learn more about built-in tools.
Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
Type typeThe type of hosted tool the model should to use. Learn more about
built-in tools.
Allowed values are:
file_searchweb_search_previewcomputer_use_previewcode_interpreterimage_generation
The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
file_searchweb_search_previewcomputer_use_previewcode_interpreterimage_generation
class ToolChoiceFunction:Use this option to force the model to call a specific function.
Use this option to force the model to call a specific function.
The name of the function to call.
For function calling, the type is always function.
class ToolChoiceMcp:Use this option to force the model to call a specific tool on a remote MCP server.
Use this option to force the model to call a specific tool on a remote MCP server.
The label of the MCP server to use.
For MCP tools, the type is always mcp.
The name of the tool to call on the server.
class ToolChoiceCustom:Use this option to force the model to call a specific custom tool.
Use this option to force the model to call a specific custom tool.
The name of the custom tool to call.
For custom tool calling, the type is always custom.
class ToolChoiceApplyPatch:Forces the model to call the apply_patch tool when executing a tool call.
Forces the model to call the apply_patch tool when executing a tool call.
The tool to call. Always apply_patch.
class ToolChoiceShell:Forces the model to call the shell tool when a tool call is required.
Forces the model to call the shell tool when a tool call is required.
The tool to call. Always shell.
List<Tool> toolsAn 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
or file search. Learn more about
built-in 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.
- 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. You can also use
custom tools to call your own code.
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 or file search. Learn more about built-in 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.
- 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. You can also use custom tools to call your own code.
class FunctionTool:Defines a function in your own code the model can choose to call. Learn more about function calling.
Defines a function in your own code the model can choose to call. Learn more about function calling.
The name of the function to call.
A JSON schema object describing the parameters of the function.
Whether to enforce strict parameter validation. Default true.
The type of the function tool. Always function.
A description of the function. Used by the model to determine whether or not to call the function.
class FileSearchTool:A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
The type of the file search tool. Always file_search.
The IDs of the vector stores to search.
Optional<Filters> filtersA filter to apply.
A filter to apply.
class ComparisonFilter:A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
The key to compare against the value.
Type typeSpecifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Value valueThe value to compare against the attribute key; supports string, number, or boolean types.
The value to compare against the attribute key; supports string, number, or boolean types.
List<ComparisonFilterValueItem>
class CompoundFilter:Combine multiple filters using and or or.
Combine multiple filters using and or or.
List<Filter> filtersArray of filters to combine. Items can be ComparisonFilter or CompoundFilter.
Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
class ComparisonFilter:A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
The key to compare against the value.
Type typeSpecifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Value valueThe value to compare against the attribute key; supports string, number, or boolean types.
The value to compare against the attribute key; supports string, number, or boolean types.
List<ComparisonFilterValueItem>
Type typeType of operation: and or or.
Type of operation: and or or.
The maximum number of results to return. This number should be between 1 and 50 inclusive.
Optional<RankingOptions> rankingOptionsRanking options for search.
Ranking options for search.
Optional<HybridSearch> hybridSearchWeights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
The weight of the embedding in the reciprocal ranking fusion.
The weight of the text in the reciprocal ranking fusion.
Optional<Ranker> rankerThe ranker to use for the file search.
The ranker to use for the file search.
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.
class ComputerTool:A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
The height of the computer display.
The width of the computer display.
Environment environmentThe type of computer environment to control.
The type of computer environment to control.
The type of the computer use tool. Always computer_use_preview.
class WebSearchTool:Search the Internet for sources related to the prompt. Learn more about the
web search tool.
Search the Internet for sources related to the prompt. Learn more about the web search tool.
Type typeThe type of the web search tool. One of web_search or web_search_2025_08_26.
The type of the web search tool. One of web_search or web_search_2025_08_26.
Optional<Filters> filtersFilters for the search.
Filters for the search.
Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example: ["pubmed.ncbi.nlm.nih.gov"]
Optional<SearchContextSize> searchContextSizeHigh level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
Optional<UserLocation> userLocationThe approximate location of the user.
The approximate location of the user.
Free text input for the city of the user, e.g. San Francisco.
The two-letter ISO country code of the user, e.g. US.
Free text input for the region of the user, e.g. California.
The IANA timezone of the user, e.g. America/Los_Angeles.
The type of location approximation. Always approximate.
Mcp
A label for this MCP server, used to identify it in tool calls.
The type of the MCP tool. Always mcp.
Optional<AllowedTools> allowedToolsList of allowed tool names or a filter object.
List of allowed tool names or a filter object.
class McpToolFilter:A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
Optional<ConnectorId> connectorIdIdentifier for service connectors, like those available in ChatGPT. One of
server_url or connector_id must be provided. Learn more about service
connectors here.
Currently supported connector_id values are:
- Dropbox:
connector_dropbox
- Gmail:
connector_gmail
- Google Calendar:
connector_googlecalendar
- Google Drive:
connector_googledrive
- Microsoft Teams:
connector_microsoftteams
- Outlook Calendar:
connector_outlookcalendar
- Outlook Email:
connector_outlookemail
- SharePoint:
connector_sharepoint
Identifier for service connectors, like those available in ChatGPT. One of
server_url or connector_id must be provided. Learn more about service
connectors here.
Currently supported connector_id values are:
- Dropbox:
connector_dropbox - Gmail:
connector_gmail - Google Calendar:
connector_googlecalendar - Google Drive:
connector_googledrive - Microsoft Teams:
connector_microsoftteams - Outlook Calendar:
connector_outlookcalendar - Outlook Email:
connector_outlookemail - SharePoint:
connector_sharepoint
Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
Optional<RequireApproval> requireApprovalSpecify which of the MCP server's tools require approval.
Specify which of the MCP server's tools require approval.
class McpToolApprovalFilter:Specify which of the MCP server's tools require approval. Can be
always, never, or a filter object associated with tools
that require approval.
Specify which of the MCP server's tools require approval. Can be
always, never, or a filter object associated with tools
that require approval.
Optional<Always> alwaysA filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
Optional<Never> neverA filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
enum McpToolApprovalSetting:Specify a single approval policy for all tools. One of always or
never. When set to always, all tools will require approval. When
set to never, all tools will not require approval.
Specify a single approval policy for all tools. One of always or
never. When set to always, all tools will require approval. When
set to never, all tools will not require approval.
Optional description of the MCP server, used to provide more context.
The URL for the MCP server. One of server_url or connector_id must be
provided.
CodeInterpreter
Container containerThe code interpreter container. Can be a container ID or an object that
specifies uploaded file IDs to make available to your code, along with an
optional memory_limit setting.
The code interpreter container. Can be a container ID or an object that
specifies uploaded file IDs to make available to your code, along with an
optional memory_limit setting.
class CodeInterpreterToolAuto:Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
Always auto.
An optional list of uploaded files to make available to your code.
Optional<MemoryLimit> memoryLimitThe memory limit for the code interpreter container.
The memory limit for the code interpreter container.
The type of the code interpreter tool. Always code_interpreter.
ImageGeneration
The type of the image generation tool. Always image_generation.
Optional<Action> actionWhether to generate a new image or edit an existing image. Default: auto.
Whether to generate a new image or edit an existing image. Default: auto.
Optional<Background> backgroundBackground type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Optional<InputFidelity> inputFidelityControl how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Optional<InputImageMask> inputImageMaskOptional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
File ID for the mask image.
Base64-encoded mask image.
Optional<Model> modelThe image generation model to use. Default: gpt-image-1.
The image generation model to use. Default: gpt-image-1.
Optional<Moderation> moderationModeration level for the generated image. Default: auto.
Moderation level for the generated image. Default: auto.
Compression level for the output image. Default: 100.
Optional<OutputFormat> outputFormatThe output format of the generated image. One of png, webp, or
jpeg. Default: png.
The output format of the generated image. One of png, webp, or
jpeg. Default: png.
Number of partial images to generate in streaming mode, from 0 (default value) to 3.
Optional<Quality> qualityThe quality of the generated image. One of low, medium, high,
or auto. Default: auto.
The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
Optional<Size> sizeThe size of the generated image. One of 1024x1024, 1024x1536,
1536x1024, or auto. Default: auto.
The size of the generated image. One of 1024x1024, 1024x1536,
1536x1024, or auto. Default: auto.
JsonValue;
The type of the local shell tool. Always local_shell.
class FunctionShellTool:A tool that allows the model to execute shell commands.
A tool that allows the model to execute shell commands.
The type of the shell tool. Always shell.
class CustomTool:A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
The name of the custom tool, used to identify it in tool calls.
The type of the custom tool. Always custom.
Optional description of the custom tool, used to provide more context.
The input format for the custom tool. Default is unconstrained text.
The input format for the custom tool. Default is unconstrained text.
JsonValue;
Unconstrained text format. Always text.
Grammar
The grammar definition.
Syntax syntaxThe syntax of the grammar definition. One of lark or regex.
The syntax of the grammar definition. One of lark or regex.
Grammar format. Always grammar.
class WebSearchPreviewTool:This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
Type typeThe type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
Optional<SearchContextSize> searchContextSizeHigh level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
Optional<UserLocation> userLocationThe user's location.
The user's location.
The type of location approximation. Always approximate.
Free text input for the city of the user, e.g. San Francisco.
The two-letter ISO country code of the user, e.g. US.
Free text input for the region of the user, e.g. California.
The IANA timezone of the user, e.g. America/Los_Angeles.
class ApplyPatchTool:Allows the assistant to create, delete, or update files using unified diffs.
Allows the assistant to create, delete, or update files using unified diffs.
The type of the tool. Always apply_patch.
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.
Whether to run the model response in the background. Learn more.
Unix timestamp (in seconds) of when this Response was completed.
Only present when the status is completed.
Optional<Conversation> conversationThe conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
The unique ID of the conversation that this response was associated with.
An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
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.
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.
Reference to a prompt template and its variables.
Learn more.
Reference to a prompt template and its variables. Learn more.
The unique identifier of the prompt template to use.
Optional<Variables> variablesOptional map of values to substitute in for variables in your
prompt. The substitution values can either be strings, or other
Response input types like images or files.
Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Optional version of the prompt template.
Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
Optional<PromptCacheRetention> promptCacheRetentionThe 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.
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.
gpt-5 and o-series models only
Configuration options for
reasoning models.
gpt-5 and o-series models only
Configuration options for reasoning models.
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1 default to medium reasoning effort, and do not support none.
- The
gpt-5-pro model defaults to (and only supports) high reasoning effort.
xhigh is supported for all models after gpt-5.1-codex-max.
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. - The
gpt-5-promodel defaults to (and only supports)highreasoning effort. xhighis supported for all models aftergpt-5.1-codex-max.
DeprecatedOptional<GenerateSummary> generateSummaryDeprecated: use summary instead.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
Deprecated: use summary instead.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
Optional<Summary> summaryA summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
concise is supported for computer-use-preview models and all reasoning models after gpt-5.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
concise is supported for computer-use-preview models and all reasoning models after gpt-5.
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. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
Optional<ServiceTier> serviceTierSpecifies 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' or 'priority', then the request will be processed with the corresponding service tier.
- 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.
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' or 'priority', then the request will be processed with the corresponding service tier.
- 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.
The status of the response generation. One of completed, failed,
in_progress, cancelled, queued, or incomplete.
The status of the response generation. One of completed, failed,
in_progress, cancelled, queued, or incomplete.
Configuration options for a text response from the model. Can be plain
text or structured JSON data. Learn more:
Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
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.
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.
class ResponseFormatText:Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatTextJsonSchemaConfig:JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
The type of response format being defined. Always json_schema.
A description of what the response format is for, used by the model to determine how to respond in the format.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
class ResponseFormatJsonObject:JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
Optional<Verbosity> verbosityConstrains the verbosity of the model's response. Lower values will result in
more concise responses, while higher values will result in more verbose responses.
Currently supported values are low, medium, and high.
Constrains the verbosity of the model's response. Lower values will result in
more concise responses, while higher values will result in more verbose responses.
Currently supported values are low, medium, and high.
An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.
Optional<Truncation> truncationThe 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.
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.
Represents token usage details including input tokens, output tokens,
a breakdown of output tokens, and the total tokens used.
Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
The number of input tokens.
InputTokensDetails inputTokensDetailsA detailed breakdown of the input tokens.
A detailed breakdown of the input tokens.
The number of tokens that were retrieved from the cache. More on prompt caching.
The number of output tokens.
OutputTokensDetails outputTokensDetailsA detailed breakdown of the output tokens.
A detailed breakdown of the output tokens.
The number of reasoning tokens.
The total number of tokens used.
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.
The sequence number of this event.
The type of the event. Always response.incomplete.
class ResponseOutputItemAddedEvent:Emitted when a new output item is added.
Emitted when a new output item is added.
ResponseOutputItem itemThe output item that was added.
The output item that was added.
class ResponseOutputMessage:An output message from the model.
An output message from the model.
The unique ID of the output message.
List<Content> contentThe content of the output message.
The content of the output message.
class ResponseOutputText:A text output from the model.
A text output from the model.
List<Annotation> annotationsThe annotations of the text output.
The annotations of the text output.
class FileCitation:A citation to a file.
A citation to a file.
The ID of the file.
The filename of the file cited.
The index of the file in the list of files.
The type of the file citation. Always file_citation.
class UrlCitation:A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
The index of the last character of the URL citation in the message.
The index of the first character of the URL citation in the message.
The title of the web resource.
The type of the URL citation. Always url_citation.
The URL of the web resource.
class ContainerFileCitation:A citation for a container file used to generate a model response.
A citation for a container file used to generate a model response.
The ID of the container file.
The index of the last character of the container file citation in the message.
The ID of the file.
The filename of the container file cited.
The index of the first character of the container file citation in the message.
The type of the container file citation. Always container_file_citation.
class FilePath:A path to a file.
A path to a file.
The ID of the file.
The index of the file in the list of files.
The type of the file path. Always file_path.
The text output from the model.
The type of the output text. Always output_text.
Optional<List<Logprob>> logprobs
List<TopLogprob> topLogprobs
class ResponseOutputRefusal:A refusal from the model.
A refusal from the model.
The refusal explanation from the model.
The type of the refusal. Always refusal.
The role of the output message. Always assistant.
Status statusThe status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The type of the output message. Always message.
class ResponseFileSearchToolCall:The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
The unique ID of the file search tool call.
The queries used to search for files.
Status statusThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The type of the file search tool call. Always file_search_call.
Optional<List<Result>> resultsThe results of the file search tool call.
The results of the file search tool call.
Optional<Attributes> attributesSet 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, booleans, or numbers.
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, booleans, or numbers.
The unique ID of the file.
The name of the file.
The relevance score of the file - a value between 0 and 1.
The text that was retrieved from the file.
class ResponseFunctionToolCall:A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
A JSON string of the arguments to pass to the function.
The unique ID of the function tool call generated by the model.
The name of the function to run.
The type of the function tool call. Always function_call.
The unique ID of the function tool call.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseFunctionWebSearch:The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
The unique ID of the web search tool call.
Action actionAn object describing the specific action taken in this web search call.
Includes details on how the model used the web (search, open_page, find_in_page).
An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
class Search:Action type "search" - Performs a web search query.
Action type "search" - Performs a web search query.
[DEPRECATED] The search query.
The action type.
The search queries.
Optional<List<Source>> sourcesThe sources used in the search.
The sources used in the search.
The type of source. Always url.
The URL of the source.
class OpenPage:Action type "open_page" - Opens a specific URL from search results.
Action type "open_page" - Opens a specific URL from search results.
The action type.
The URL opened by the model.
class FindInPage:Action type "find_in_page": Searches for a pattern within a loaded page.
Action type "find_in_page": Searches for a pattern within a loaded page.
The pattern or text to search for within the page.
The action type.
The URL of the page searched for the pattern.
Status statusThe status of the web search tool call.
The status of the web search tool call.
The type of the web search tool call. Always web_search_call.
class ResponseComputerToolCall:A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
The unique ID of the computer call.
Action actionA click action.
A click action.
class Click:A click action.
A click action.
Button buttonIndicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Specifies the event type. For a click action, this property is always click.
The x-coordinate where the click occurred.
The y-coordinate where the click occurred.
class DoubleClick:A double click action.
A double click action.
Specifies the event type. For a double click action, this property is always set to double_click.
The x-coordinate where the double click occurred.
The y-coordinate where the double click occurred.
class Drag:A drag action.
A drag action.
List<Path> pathAn array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]
An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]The x-coordinate.
The y-coordinate.
Specifies the event type. For a drag action, this property is always set to drag.
class Keypress:A collection of keypresses the model would like to perform.
A collection of keypresses the model would like to perform.
The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
Specifies the event type. For a keypress action, this property is always set to keypress.
class Move:A mouse move action.
A mouse move action.
Specifies the event type. For a move action, this property is always set to move.
The x-coordinate to move to.
The y-coordinate to move to.
JsonValue;
Specifies the event type. For a screenshot action, this property is always set to screenshot.
class Scroll:A scroll action.
A scroll action.
The horizontal scroll distance.
The vertical scroll distance.
Specifies the event type. For a scroll action, this property is always set to scroll.
The x-coordinate where the scroll occurred.
The y-coordinate where the scroll occurred.
class Type:An action to type in text.
An action to type in text.
The text to type.
Specifies the event type. For a type action, this property is always set to type.
JsonValue;
Specifies the event type. For a wait action, this property is always set to wait.
An identifier used when responding to the tool call with output.
List<PendingSafetyCheck> pendingSafetyChecksThe pending safety checks for the computer call.
The pending safety checks for the computer call.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Status statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the computer call. Always computer_call.
class ResponseReasoningItem:A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
The unique identifier of the reasoning content.
List<Summary> summaryReasoning summary content.
Reasoning summary content.
A summary of the reasoning output from the model so far.
The type of the object. Always summary_text.
The type of the object. Always reasoning.
Optional<List<Content>> contentReasoning text content.
Reasoning text content.
The reasoning text from the model.
The type of the reasoning text. Always reasoning_text.
The encrypted content of the reasoning item - populated when a response is
generated with reasoning.encrypted_content in the include parameter.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseCompactionItem:A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
The unique ID of the compaction item.
The encrypted content that was produced by compaction.
The type of the item. Always compaction.
The identifier of the actor that created the item.
ImageGenerationCall
The unique ID of the image generation call.
The generated image encoded in base64.
Status statusThe status of the image generation call.
The status of the image generation call.
The type of the image generation call. Always image_generation_call.
class ResponseCodeInterpreterToolCall:A tool call to run code.
A tool call to run code.
The unique ID of the code interpreter tool call.
The code to run, or null if not available.
The ID of the container used to run the code.
Optional<List<Output>> outputsThe outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
class Logs:The logs output from the code interpreter.
The logs output from the code interpreter.
The logs output from the code interpreter.
The type of the output. Always logs.
class Image:The image output from the code interpreter.
The image output from the code interpreter.
The type of the output. Always image.
The URL of the image output from the code interpreter.
Status statusThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The type of the code interpreter tool call. Always code_interpreter_call.
LocalShellCall
The unique ID of the local shell call.
Action actionExecute a shell command on the server.
Execute a shell command on the server.
The command to run.
Environment variables to set for the command.
The type of the local shell action. Always exec.
Optional timeout in milliseconds for the command.
Optional user to run the command as.
Optional working directory to run the command in.
The unique ID of the local shell tool call generated by the model.
Status statusThe status of the local shell call.
The status of the local shell call.
The type of the local shell call. Always local_shell_call.
class ResponseFunctionShellToolCall:A tool call that executes one or more shell commands in a managed environment.
A tool call that executes one or more shell commands in a managed environment.
The unique ID of the shell tool call. Populated when this item is returned via API.
Action actionThe shell commands and limits that describe how to run the tool call.
The shell commands and limits that describe how to run the tool call.
Optional maximum number of characters to return from each command.
Optional timeout in milliseconds for the commands.
The unique ID of the shell tool call generated by the model.
Status statusThe status of the shell call. One of in_progress, completed, or incomplete.
The status of the shell call. One of in_progress, completed, or incomplete.
The type of the item. Always shell_call.
The ID of the entity that created this tool call.
class ResponseFunctionShellToolCallOutput:The output of a shell tool call that was emitted.
The output of a shell tool call that was emitted.
The unique ID of the shell call output. Populated when this item is returned via API.
The unique ID of the shell tool call generated by the model.
The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
List<Output> outputAn array of shell call output contents
An array of shell call output contents
Outcome outcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
JsonValue;
The outcome type. Always timeout.
class Exit:Indicates that the shell commands finished and returned an exit code.
Indicates that the shell commands finished and returned an exit code.
Exit code from the shell process.
The outcome type. Always exit.
The standard error output that was captured.
The standard output that was captured.
The identifier of the actor that created the item.
Status statusThe status of the shell call output. One of in_progress, completed, or incomplete.
The status of the shell call output. One of in_progress, completed, or incomplete.
The type of the shell call output. Always shell_call_output.
The identifier of the actor that created the item.
class ResponseApplyPatchToolCall:A tool call that applies file diffs by creating, deleting, or updating files.
A tool call that applies file diffs by creating, deleting, or updating files.
The unique ID of the apply patch tool call. Populated when this item is returned via API.
The unique ID of the apply patch tool call generated by the model.
Operation operationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
One of the create_file, delete_file, or update_file operations applied via apply_patch.
class CreateFile:Instruction describing how to create a file via the apply_patch tool.
Instruction describing how to create a file via the apply_patch tool.
Diff to apply.
Path of the file to create.
Create a new file with the provided diff.
class DeleteFile:Instruction describing how to delete a file via the apply_patch tool.
Instruction describing how to delete a file via the apply_patch tool.
Path of the file to delete.
Delete the specified file.
class UpdateFile:Instruction describing how to update a file via the apply_patch tool.
Instruction describing how to update a file via the apply_patch tool.
Diff to apply.
Path of the file to update.
Update an existing file with the provided diff.
Status statusThe status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
The type of the item. Always apply_patch_call.
The ID of the entity that created this tool call.
class ResponseApplyPatchToolCallOutput:The output emitted by an apply patch tool call.
The output emitted by an apply patch tool call.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
The unique ID of the apply patch tool call generated by the model.
Status statusThe status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
The type of the item. Always apply_patch_call_output.
The ID of the entity that created this tool call output.
Optional textual output returned by the apply patch tool.
McpCall
The unique ID of the tool call.
A JSON string of the arguments passed to the tool.
The name of the tool that was run.
The label of the MCP server running the tool.
The type of the item. Always mcp_call.
Unique identifier for the MCP tool call approval request.
Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
The error from the tool call, if any.
The output from the tool call.
Optional<Status> statusThe status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
McpListTools
The unique ID of the list.
The label of the MCP server.
List<Tool> toolsThe tools available on the server.
The tools available on the server.
The JSON schema describing the tool's input.
The name of the tool.
Additional annotations about the tool.
The description of the tool.
The type of the item. Always mcp_list_tools.
Error message if the server could not list tools.
McpApprovalRequest
The unique ID of the approval request.
A JSON string of arguments for the tool.
The name of the tool to run.
The label of the MCP server making the request.
The type of the item. Always mcp_approval_request.
class ResponseCustomToolCall:A call to a custom tool created by the model.
A call to a custom tool created by the model.
An identifier used to map this custom tool call to a tool call output.
The input for the custom tool call generated by the model.
The name of the custom tool being called.
The type of the custom tool call. Always custom_tool_call.
The unique ID of the custom tool call in the OpenAI platform.
The index of the output item that was added.
The sequence number of this event.
The type of the event. Always response.output_item.added.
class ResponseOutputItemDoneEvent:Emitted when an output item is marked done.
Emitted when an output item is marked done.
ResponseOutputItem itemThe output item that was marked done.
The output item that was marked done.
class ResponseOutputMessage:An output message from the model.
An output message from the model.
The unique ID of the output message.
List<Content> contentThe content of the output message.
The content of the output message.
class ResponseOutputText:A text output from the model.
A text output from the model.
List<Annotation> annotationsThe annotations of the text output.
The annotations of the text output.
class FileCitation:A citation to a file.
A citation to a file.
The ID of the file.
The filename of the file cited.
The index of the file in the list of files.
The type of the file citation. Always file_citation.
class UrlCitation:A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
The index of the last character of the URL citation in the message.
The index of the first character of the URL citation in the message.
The title of the web resource.
The type of the URL citation. Always url_citation.
The URL of the web resource.
class ContainerFileCitation:A citation for a container file used to generate a model response.
A citation for a container file used to generate a model response.
The ID of the container file.
The index of the last character of the container file citation in the message.
The ID of the file.
The filename of the container file cited.
The index of the first character of the container file citation in the message.
The type of the container file citation. Always container_file_citation.
class FilePath:A path to a file.
A path to a file.
The ID of the file.
The index of the file in the list of files.
The type of the file path. Always file_path.
The text output from the model.
The type of the output text. Always output_text.
Optional<List<Logprob>> logprobs
List<TopLogprob> topLogprobs
class ResponseOutputRefusal:A refusal from the model.
A refusal from the model.
The refusal explanation from the model.
The type of the refusal. Always refusal.
The role of the output message. Always assistant.
Status statusThe status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The type of the output message. Always message.
class ResponseFileSearchToolCall:The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
The unique ID of the file search tool call.
The queries used to search for files.
Status statusThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The type of the file search tool call. Always file_search_call.
Optional<List<Result>> resultsThe results of the file search tool call.
The results of the file search tool call.
Optional<Attributes> attributesSet 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, booleans, or numbers.
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, booleans, or numbers.
The unique ID of the file.
The name of the file.
The relevance score of the file - a value between 0 and 1.
The text that was retrieved from the file.
class ResponseFunctionToolCall:A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
A JSON string of the arguments to pass to the function.
The unique ID of the function tool call generated by the model.
The name of the function to run.
The type of the function tool call. Always function_call.
The unique ID of the function tool call.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseFunctionWebSearch:The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
The unique ID of the web search tool call.
Action actionAn object describing the specific action taken in this web search call.
Includes details on how the model used the web (search, open_page, find_in_page).
An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
class Search:Action type "search" - Performs a web search query.
Action type "search" - Performs a web search query.
[DEPRECATED] The search query.
The action type.
The search queries.
Optional<List<Source>> sourcesThe sources used in the search.
The sources used in the search.
The type of source. Always url.
The URL of the source.
class OpenPage:Action type "open_page" - Opens a specific URL from search results.
Action type "open_page" - Opens a specific URL from search results.
The action type.
The URL opened by the model.
class FindInPage:Action type "find_in_page": Searches for a pattern within a loaded page.
Action type "find_in_page": Searches for a pattern within a loaded page.
The pattern or text to search for within the page.
The action type.
The URL of the page searched for the pattern.
Status statusThe status of the web search tool call.
The status of the web search tool call.
The type of the web search tool call. Always web_search_call.
class ResponseComputerToolCall:A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
The unique ID of the computer call.
Action actionA click action.
A click action.
class Click:A click action.
A click action.
Button buttonIndicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Specifies the event type. For a click action, this property is always click.
The x-coordinate where the click occurred.
The y-coordinate where the click occurred.
class DoubleClick:A double click action.
A double click action.
Specifies the event type. For a double click action, this property is always set to double_click.
The x-coordinate where the double click occurred.
The y-coordinate where the double click occurred.
class Drag:A drag action.
A drag action.
List<Path> pathAn array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]
An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]The x-coordinate.
The y-coordinate.
Specifies the event type. For a drag action, this property is always set to drag.
class Keypress:A collection of keypresses the model would like to perform.
A collection of keypresses the model would like to perform.
The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
Specifies the event type. For a keypress action, this property is always set to keypress.
class Move:A mouse move action.
A mouse move action.
Specifies the event type. For a move action, this property is always set to move.
The x-coordinate to move to.
The y-coordinate to move to.
JsonValue;
Specifies the event type. For a screenshot action, this property is always set to screenshot.
class Scroll:A scroll action.
A scroll action.
The horizontal scroll distance.
The vertical scroll distance.
Specifies the event type. For a scroll action, this property is always set to scroll.
The x-coordinate where the scroll occurred.
The y-coordinate where the scroll occurred.
class Type:An action to type in text.
An action to type in text.
The text to type.
Specifies the event type. For a type action, this property is always set to type.
JsonValue;
Specifies the event type. For a wait action, this property is always set to wait.
An identifier used when responding to the tool call with output.
List<PendingSafetyCheck> pendingSafetyChecksThe pending safety checks for the computer call.
The pending safety checks for the computer call.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Status statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the computer call. Always computer_call.
class ResponseReasoningItem:A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
The unique identifier of the reasoning content.
List<Summary> summaryReasoning summary content.
Reasoning summary content.
A summary of the reasoning output from the model so far.
The type of the object. Always summary_text.
The type of the object. Always reasoning.
Optional<List<Content>> contentReasoning text content.
Reasoning text content.
The reasoning text from the model.
The type of the reasoning text. Always reasoning_text.
The encrypted content of the reasoning item - populated when a response is
generated with reasoning.encrypted_content in the include parameter.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseCompactionItem:A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
The unique ID of the compaction item.
The encrypted content that was produced by compaction.
The type of the item. Always compaction.
The identifier of the actor that created the item.
ImageGenerationCall
The unique ID of the image generation call.
The generated image encoded in base64.
Status statusThe status of the image generation call.
The status of the image generation call.
The type of the image generation call. Always image_generation_call.
class ResponseCodeInterpreterToolCall:A tool call to run code.
A tool call to run code.
The unique ID of the code interpreter tool call.
The code to run, or null if not available.
The ID of the container used to run the code.
Optional<List<Output>> outputsThe outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
class Logs:The logs output from the code interpreter.
The logs output from the code interpreter.
The logs output from the code interpreter.
The type of the output. Always logs.
class Image:The image output from the code interpreter.
The image output from the code interpreter.
The type of the output. Always image.
The URL of the image output from the code interpreter.
Status statusThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The type of the code interpreter tool call. Always code_interpreter_call.
LocalShellCall
The unique ID of the local shell call.
Action actionExecute a shell command on the server.
Execute a shell command on the server.
The command to run.
Environment variables to set for the command.
The type of the local shell action. Always exec.
Optional timeout in milliseconds for the command.
Optional user to run the command as.
Optional working directory to run the command in.
The unique ID of the local shell tool call generated by the model.
Status statusThe status of the local shell call.
The status of the local shell call.
The type of the local shell call. Always local_shell_call.
class ResponseFunctionShellToolCall:A tool call that executes one or more shell commands in a managed environment.
A tool call that executes one or more shell commands in a managed environment.
The unique ID of the shell tool call. Populated when this item is returned via API.
Action actionThe shell commands and limits that describe how to run the tool call.
The shell commands and limits that describe how to run the tool call.
Optional maximum number of characters to return from each command.
Optional timeout in milliseconds for the commands.
The unique ID of the shell tool call generated by the model.
Status statusThe status of the shell call. One of in_progress, completed, or incomplete.
The status of the shell call. One of in_progress, completed, or incomplete.
The type of the item. Always shell_call.
The ID of the entity that created this tool call.
class ResponseFunctionShellToolCallOutput:The output of a shell tool call that was emitted.
The output of a shell tool call that was emitted.
The unique ID of the shell call output. Populated when this item is returned via API.
The unique ID of the shell tool call generated by the model.
The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
List<Output> outputAn array of shell call output contents
An array of shell call output contents
Outcome outcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
JsonValue;
The outcome type. Always timeout.
class Exit:Indicates that the shell commands finished and returned an exit code.
Indicates that the shell commands finished and returned an exit code.
Exit code from the shell process.
The outcome type. Always exit.
The standard error output that was captured.
The standard output that was captured.
The identifier of the actor that created the item.
Status statusThe status of the shell call output. One of in_progress, completed, or incomplete.
The status of the shell call output. One of in_progress, completed, or incomplete.
The type of the shell call output. Always shell_call_output.
The identifier of the actor that created the item.
class ResponseApplyPatchToolCall:A tool call that applies file diffs by creating, deleting, or updating files.
A tool call that applies file diffs by creating, deleting, or updating files.
The unique ID of the apply patch tool call. Populated when this item is returned via API.
The unique ID of the apply patch tool call generated by the model.
Operation operationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
One of the create_file, delete_file, or update_file operations applied via apply_patch.
class CreateFile:Instruction describing how to create a file via the apply_patch tool.
Instruction describing how to create a file via the apply_patch tool.
Diff to apply.
Path of the file to create.
Create a new file with the provided diff.
class DeleteFile:Instruction describing how to delete a file via the apply_patch tool.
Instruction describing how to delete a file via the apply_patch tool.
Path of the file to delete.
Delete the specified file.
class UpdateFile:Instruction describing how to update a file via the apply_patch tool.
Instruction describing how to update a file via the apply_patch tool.
Diff to apply.
Path of the file to update.
Update an existing file with the provided diff.
Status statusThe status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
The type of the item. Always apply_patch_call.
The ID of the entity that created this tool call.
class ResponseApplyPatchToolCallOutput:The output emitted by an apply patch tool call.
The output emitted by an apply patch tool call.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
The unique ID of the apply patch tool call generated by the model.
Status statusThe status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
The type of the item. Always apply_patch_call_output.
The ID of the entity that created this tool call output.
Optional textual output returned by the apply patch tool.
McpCall
The unique ID of the tool call.
A JSON string of the arguments passed to the tool.
The name of the tool that was run.
The label of the MCP server running the tool.
The type of the item. Always mcp_call.
Unique identifier for the MCP tool call approval request.
Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
The error from the tool call, if any.
The output from the tool call.
Optional<Status> statusThe status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
McpListTools
The unique ID of the list.
The label of the MCP server.
List<Tool> toolsThe tools available on the server.
The tools available on the server.
The JSON schema describing the tool's input.
The name of the tool.
Additional annotations about the tool.
The description of the tool.
The type of the item. Always mcp_list_tools.
Error message if the server could not list tools.
McpApprovalRequest
The unique ID of the approval request.
A JSON string of arguments for the tool.
The name of the tool to run.
The label of the MCP server making the request.
The type of the item. Always mcp_approval_request.
class ResponseCustomToolCall:A call to a custom tool created by the model.
A call to a custom tool created by the model.
An identifier used to map this custom tool call to a tool call output.
The input for the custom tool call generated by the model.
The name of the custom tool being called.
The type of the custom tool call. Always custom_tool_call.
The unique ID of the custom tool call in the OpenAI platform.
The index of the output item that was marked done.
The sequence number of this event.
The type of the event. Always response.output_item.done.
class ResponseReasoningSummaryPartAddedEvent:Emitted when a new reasoning summary part is added.
Emitted when a new reasoning summary part is added.
The ID of the item this summary part is associated with.
The index of the output item this summary part is associated with.
Part partThe summary part that was added.
The summary part that was added.
The text of the summary part.
The type of the summary part. Always summary_text.
The sequence number of this event.
The index of the summary part within the reasoning summary.
The type of the event. Always response.reasoning_summary_part.added.
class ResponseReasoningSummaryPartDoneEvent:Emitted when a reasoning summary part is completed.
Emitted when a reasoning summary part is completed.
The ID of the item this summary part is associated with.
The index of the output item this summary part is associated with.
Part partThe completed summary part.
The completed summary part.
The text of the summary part.
The type of the summary part. Always summary_text.
The sequence number of this event.
The index of the summary part within the reasoning summary.
The type of the event. Always response.reasoning_summary_part.done.
class ResponseReasoningSummaryTextDeltaEvent:Emitted when a delta is added to a reasoning summary text.
Emitted when a delta is added to a reasoning summary text.
The text delta that was added to the summary.
The ID of the item this summary text delta is associated with.
The index of the output item this summary text delta is associated with.
The sequence number of this event.
The index of the summary part within the reasoning summary.
The type of the event. Always response.reasoning_summary_text.delta.
class ResponseReasoningSummaryTextDoneEvent:Emitted when a reasoning summary text is completed.
Emitted when a reasoning summary text is completed.
The ID of the item this summary text is associated with.
The index of the output item this summary text is associated with.
The sequence number of this event.
The index of the summary part within the reasoning summary.
The full text of the completed reasoning summary.
The type of the event. Always response.reasoning_summary_text.done.
class ResponseReasoningTextDeltaEvent:Emitted when a delta is added to a reasoning text.
Emitted when a delta is added to a reasoning text.
The index of the reasoning content part this delta is associated with.
The text delta that was added to the reasoning content.
The ID of the item this reasoning text delta is associated with.
The index of the output item this reasoning text delta is associated with.
The sequence number of this event.
The type of the event. Always response.reasoning_text.delta.
class ResponseReasoningTextDoneEvent:Emitted when a reasoning text is completed.
Emitted when a reasoning text is completed.
The index of the reasoning content part.
The ID of the item this reasoning text is associated with.
The index of the output item this reasoning text is associated with.
The sequence number of this event.
The full text of the completed reasoning content.
The type of the event. Always response.reasoning_text.done.
class ResponseRefusalDeltaEvent:Emitted when there is a partial refusal text.
Emitted when there is a partial refusal text.
The index of the content part that the refusal text is added to.
The refusal text that is added.
The ID of the output item that the refusal text is added to.
The index of the output item that the refusal text is added to.
The sequence number of this event.
The type of the event. Always response.refusal.delta.
class ResponseRefusalDoneEvent:Emitted when refusal text is finalized.
Emitted when refusal text is finalized.
The index of the content part that the refusal text is finalized.
The ID of the output item that the refusal text is finalized.
The index of the output item that the refusal text is finalized.
The refusal text that is finalized.
The sequence number of this event.
The type of the event. Always response.refusal.done.
class ResponseTextDeltaEvent:Emitted when there is an additional text delta.
Emitted when there is an additional text delta.
The index of the content part that the text delta was added to.
The text delta that was added.
The ID of the output item that the text delta was added to.
List<Logprob> logprobsThe log probabilities of the tokens in the delta.
The log probabilities of the tokens in the delta.
A possible text token.
The log probability of this token.
Optional<List<TopLogprob>> topLogprobsThe log probability of the top 20 most likely tokens.
The log probability of the top 20 most likely tokens.
A possible text token.
The log probability of this token.
The index of the output item that the text delta was added to.
The sequence number for this event.
The type of the event. Always response.output_text.delta.
class ResponseTextDoneEvent:Emitted when text content is finalized.
Emitted when text content is finalized.
The index of the content part that the text content is finalized.
The ID of the output item that the text content is finalized.
List<Logprob> logprobsThe log probabilities of the tokens in the delta.
The log probabilities of the tokens in the delta.
A possible text token.
The log probability of this token.
Optional<List<TopLogprob>> topLogprobsThe log probability of the top 20 most likely tokens.
The log probability of the top 20 most likely tokens.
A possible text token.
The log probability of this token.
The index of the output item that the text content is finalized.
The sequence number for this event.
The text content that is finalized.
The type of the event. Always response.output_text.done.
class ResponseWebSearchCallCompletedEvent:Emitted when a web search call is completed.
Emitted when a web search call is completed.
Unique ID for the output item associated with the web search call.
The index of the output item that the web search call is associated with.
The sequence number of the web search call being processed.
The type of the event. Always response.web_search_call.completed.
class ResponseWebSearchCallInProgressEvent:Emitted when a web search call is initiated.
Emitted when a web search call is initiated.
Unique ID for the output item associated with the web search call.
The index of the output item that the web search call is associated with.
The sequence number of the web search call being processed.
The type of the event. Always response.web_search_call.in_progress.
class ResponseWebSearchCallSearchingEvent:Emitted when a web search call is executing.
Emitted when a web search call is executing.
Unique ID for the output item associated with the web search call.
The index of the output item that the web search call is associated with.
The sequence number of the web search call being processed.
The type of the event. Always response.web_search_call.searching.
class ResponseImageGenCallCompletedEvent:Emitted when an image generation tool call has completed and the final image is available.
Emitted when an image generation tool call has completed and the final image is available.
The unique identifier of the image generation item being processed.
The index of the output item in the response's output array.
The sequence number of this event.
The type of the event. Always 'response.image_generation_call.completed'.
class ResponseImageGenCallGeneratingEvent:Emitted when an image generation tool call is actively generating an image (intermediate state).
Emitted when an image generation tool call is actively generating an image (intermediate state).
The unique identifier of the image generation item being processed.
The index of the output item in the response's output array.
The sequence number of the image generation item being processed.
The type of the event. Always 'response.image_generation_call.generating'.
class ResponseImageGenCallInProgressEvent:Emitted when an image generation tool call is in progress.
Emitted when an image generation tool call is in progress.
The unique identifier of the image generation item being processed.
The index of the output item in the response's output array.
The sequence number of the image generation item being processed.
The type of the event. Always 'response.image_generation_call.in_progress'.
class ResponseImageGenCallPartialImageEvent:Emitted when a partial image is available during image generation streaming.
Emitted when a partial image is available during image generation streaming.
The unique identifier of the image generation item being processed.
The index of the output item in the response's output array.
Base64-encoded partial image data, suitable for rendering as an image.
0-based index for the partial image (backend is 1-based, but this is 0-based for the user).
The sequence number of the image generation item being processed.
The type of the event. Always 'response.image_generation_call.partial_image'.
class ResponseMcpCallArgumentsDeltaEvent:Emitted when there is a delta (partial update) to the arguments of an MCP tool call.
Emitted when there is a delta (partial update) to the arguments of an MCP tool call.
A JSON string containing the partial update to the arguments for the MCP tool call.
The unique identifier of the MCP tool call item being processed.
The index of the output item in the response's output array.
The sequence number of this event.
The type of the event. Always 'response.mcp_call_arguments.delta'.
class ResponseMcpCallArgumentsDoneEvent:Emitted when the arguments for an MCP tool call are finalized.
Emitted when the arguments for an MCP tool call are finalized.
A JSON string containing the finalized arguments for the MCP tool call.
The unique identifier of the MCP tool call item being processed.
The index of the output item in the response's output array.
The sequence number of this event.
The type of the event. Always 'response.mcp_call_arguments.done'.
class ResponseMcpCallCompletedEvent:Emitted when an MCP tool call has completed successfully.
Emitted when an MCP tool call has completed successfully.
The ID of the MCP tool call item that completed.
The index of the output item that completed.
The sequence number of this event.
The type of the event. Always 'response.mcp_call.completed'.
class ResponseMcpCallFailedEvent:Emitted when an MCP tool call has failed.
Emitted when an MCP tool call has failed.
The ID of the MCP tool call item that failed.
The index of the output item that failed.
The sequence number of this event.
The type of the event. Always 'response.mcp_call.failed'.
class ResponseMcpCallInProgressEvent:Emitted when an MCP tool call is in progress.
Emitted when an MCP tool call is in progress.
The unique identifier of the MCP tool call item being processed.
The index of the output item in the response's output array.
The sequence number of this event.
The type of the event. Always 'response.mcp_call.in_progress'.
class ResponseMcpListToolsCompletedEvent:Emitted when the list of available MCP tools has been successfully retrieved.
Emitted when the list of available MCP tools has been successfully retrieved.
The ID of the MCP tool call item that produced this output.
The index of the output item that was processed.
The sequence number of this event.
The type of the event. Always 'response.mcp_list_tools.completed'.
class ResponseMcpListToolsFailedEvent:Emitted when the attempt to list available MCP tools has failed.
Emitted when the attempt to list available MCP tools has failed.
The ID of the MCP tool call item that failed.
The index of the output item that failed.
The sequence number of this event.
The type of the event. Always 'response.mcp_list_tools.failed'.
class ResponseMcpListToolsInProgressEvent:Emitted when the system is in the process of retrieving the list of available MCP tools.
Emitted when the system is in the process of retrieving the list of available MCP tools.
The ID of the MCP tool call item that is being processed.
The index of the output item that is being processed.
The sequence number of this event.
The type of the event. Always 'response.mcp_list_tools.in_progress'.
class ResponseOutputTextAnnotationAddedEvent:Emitted when an annotation is added to output text content.
Emitted when an annotation is added to output text content.
The annotation object being added. (See annotation schema for details.)
The index of the annotation within the content part.
The index of the content part within the output item.
The unique identifier of the item to which the annotation is being added.
The index of the output item in the response's output array.
The sequence number of this event.
The type of the event. Always 'response.output_text.annotation.added'.
class ResponseQueuedEvent:Emitted when a response is queued and waiting to be processed.
Emitted when a response is queued and waiting to be processed.
Response responseThe full response object that is queued.
The full response object that is queued.
Unique identifier for this Response.
Unix timestamp (in seconds) of when this Response was created.
An error object returned when the model fails to generate a Response.
An error object returned when the model fails to generate a Response.
Code codeThe error code for the response.
The error code for the response.
A human-readable description of the error.
Optional<IncompleteDetails> incompleteDetailsDetails about why the response is incomplete.
Details about why the response is incomplete.
Optional<Reason> reasonThe reason why the response is incomplete.
The reason why the response is incomplete.
Optional<Instructions> instructionsA 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.
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.
List<ResponseInputItem>
class EasyInputMessage:A message input to the model with a role indicating instruction following
hierarchy. Instructions given with the developer or system role take
precedence over instructions given with the user role. Messages with the
assistant role are presumed to have been generated by the model in previous
interactions.
A message input to the model with a role indicating instruction following
hierarchy. Instructions given with the developer or system role take
precedence over instructions given with the user role. Messages with the
assistant role are presumed to have been generated by the model in previous
interactions.
Content contentText, image, or audio input to the model, used to generate a response.
Can also contain previous assistant responses.
Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
List<ResponseInputContent>
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Role roleThe role of the message input. One of user, assistant, system, or
developer.
The role of the message input. One of user, assistant, system, or
developer.
The type of the message input. Always message.
Message
List<ResponseInputContent> contentA list of one or many input items to the model, containing different content
types.
A list of one or many input items to the model, containing different content types.
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Role roleThe role of the message input. One of user, system, or developer.
The role of the message input. One of user, system, or developer.
Optional<Status> statusThe status of item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the message input. Always set to message.
class ResponseOutputMessage:An output message from the model.
An output message from the model.
The unique ID of the output message.
List<Content> contentThe content of the output message.
The content of the output message.
class ResponseOutputText:A text output from the model.
A text output from the model.
List<Annotation> annotationsThe annotations of the text output.
The annotations of the text output.
class FileCitation:A citation to a file.
A citation to a file.
The ID of the file.
The filename of the file cited.
The index of the file in the list of files.
The type of the file citation. Always file_citation.
class UrlCitation:A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
The index of the last character of the URL citation in the message.
The index of the first character of the URL citation in the message.
The title of the web resource.
The type of the URL citation. Always url_citation.
The URL of the web resource.
class ContainerFileCitation:A citation for a container file used to generate a model response.
A citation for a container file used to generate a model response.
The ID of the container file.
The index of the last character of the container file citation in the message.
The ID of the file.
The filename of the container file cited.
The index of the first character of the container file citation in the message.
The type of the container file citation. Always container_file_citation.
class FilePath:A path to a file.
A path to a file.
The ID of the file.
The index of the file in the list of files.
The type of the file path. Always file_path.
The text output from the model.
The type of the output text. Always output_text.
Optional<List<Logprob>> logprobs
List<TopLogprob> topLogprobs
class ResponseOutputRefusal:A refusal from the model.
A refusal from the model.
The refusal explanation from the model.
The type of the refusal. Always refusal.
The role of the output message. Always assistant.
Status statusThe status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The type of the output message. Always message.
class ResponseFileSearchToolCall:The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
The unique ID of the file search tool call.
The queries used to search for files.
Status statusThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The type of the file search tool call. Always file_search_call.
Optional<List<Result>> resultsThe results of the file search tool call.
The results of the file search tool call.
Optional<Attributes> attributesSet 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, booleans, or numbers.
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, booleans, or numbers.
The unique ID of the file.
The name of the file.
The relevance score of the file - a value between 0 and 1.
The text that was retrieved from the file.
class ResponseComputerToolCall:A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
The unique ID of the computer call.
Action actionA click action.
A click action.
class Click:A click action.
A click action.
Button buttonIndicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Specifies the event type. For a click action, this property is always click.
The x-coordinate where the click occurred.
The y-coordinate where the click occurred.
class DoubleClick:A double click action.
A double click action.
Specifies the event type. For a double click action, this property is always set to double_click.
The x-coordinate where the double click occurred.
The y-coordinate where the double click occurred.
class Drag:A drag action.
A drag action.
List<Path> pathAn array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]
An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]The x-coordinate.
The y-coordinate.
Specifies the event type. For a drag action, this property is always set to drag.
class Keypress:A collection of keypresses the model would like to perform.
A collection of keypresses the model would like to perform.
The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
Specifies the event type. For a keypress action, this property is always set to keypress.
class Move:A mouse move action.
A mouse move action.
Specifies the event type. For a move action, this property is always set to move.
The x-coordinate to move to.
The y-coordinate to move to.
JsonValue;
Specifies the event type. For a screenshot action, this property is always set to screenshot.
class Scroll:A scroll action.
A scroll action.
The horizontal scroll distance.
The vertical scroll distance.
Specifies the event type. For a scroll action, this property is always set to scroll.
The x-coordinate where the scroll occurred.
The y-coordinate where the scroll occurred.
class Type:An action to type in text.
An action to type in text.
The text to type.
Specifies the event type. For a type action, this property is always set to type.
JsonValue;
Specifies the event type. For a wait action, this property is always set to wait.
An identifier used when responding to the tool call with output.
List<PendingSafetyCheck> pendingSafetyChecksThe pending safety checks for the computer call.
The pending safety checks for the computer call.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Status statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the computer call. Always computer_call.
ComputerCallOutput
The ID of the computer tool call that produced the output.
A computer screenshot image used with the computer use tool.
A computer screenshot image used with the computer use tool.
Specifies the event type. For a computer screenshot, this property is
always set to computer_screenshot.
The identifier of an uploaded file that contains the screenshot.
The URL of the screenshot image.
The type of the computer tool call output. Always computer_call_output.
The ID of the computer tool call output.
Optional<List<AcknowledgedSafetyCheck>> acknowledgedSafetyChecksThe safety checks reported by the API that have been acknowledged by the developer.
The safety checks reported by the API that have been acknowledged by the developer.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Optional<Status> statusThe status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.
class ResponseFunctionWebSearch:The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
The unique ID of the web search tool call.
Action actionAn object describing the specific action taken in this web search call.
Includes details on how the model used the web (search, open_page, find_in_page).
An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
class Search:Action type "search" - Performs a web search query.
Action type "search" - Performs a web search query.
[DEPRECATED] The search query.
The action type.
The search queries.
Optional<List<Source>> sourcesThe sources used in the search.
The sources used in the search.
The type of source. Always url.
The URL of the source.
class OpenPage:Action type "open_page" - Opens a specific URL from search results.
Action type "open_page" - Opens a specific URL from search results.
The action type.
The URL opened by the model.
class FindInPage:Action type "find_in_page": Searches for a pattern within a loaded page.
Action type "find_in_page": Searches for a pattern within a loaded page.
The pattern or text to search for within the page.
The action type.
The URL of the page searched for the pattern.
Status statusThe status of the web search tool call.
The status of the web search tool call.
The type of the web search tool call. Always web_search_call.
class ResponseFunctionToolCall:A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
A JSON string of the arguments to pass to the function.
The unique ID of the function tool call generated by the model.
The name of the function to run.
The type of the function tool call. Always function_call.
The unique ID of the function tool call.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
FunctionCallOutput
The unique ID of the function tool call generated by the model.
Output outputText, image, or file output of the function tool call.
Text, image, or file output of the function tool call.
class ResponseInputTextContent:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImageContent:An image input to the model. Learn about image inputs
An image input to the model. Learn about image inputs
The type of the input item. Always input_image.
Optional<Detail> detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFileContent:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The base64-encoded data of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
The type of the function tool call output. Always function_call_output.
The unique ID of the function tool call output. Populated when this item is returned via API.
Optional<Status> statusThe status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.
class ResponseReasoningItem:A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
The unique identifier of the reasoning content.
List<Summary> summaryReasoning summary content.
Reasoning summary content.
A summary of the reasoning output from the model so far.
The type of the object. Always summary_text.
The type of the object. Always reasoning.
Optional<List<Content>> contentReasoning text content.
Reasoning text content.
The reasoning text from the model.
The type of the reasoning text. Always reasoning_text.
The encrypted content of the reasoning item - populated when a response is
generated with reasoning.encrypted_content in the include parameter.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseCompactionItemParam:A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
The encrypted content of the compaction summary.
The type of the item. Always compaction.
The ID of the compaction item.
ImageGenerationCall
The unique ID of the image generation call.
The generated image encoded in base64.
Status statusThe status of the image generation call.
The status of the image generation call.
The type of the image generation call. Always image_generation_call.
class ResponseCodeInterpreterToolCall:A tool call to run code.
A tool call to run code.
The unique ID of the code interpreter tool call.
The code to run, or null if not available.
The ID of the container used to run the code.
Optional<List<Output>> outputsThe outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
class Logs:The logs output from the code interpreter.
The logs output from the code interpreter.
The logs output from the code interpreter.
The type of the output. Always logs.
class Image:The image output from the code interpreter.
The image output from the code interpreter.
The type of the output. Always image.
The URL of the image output from the code interpreter.
Status statusThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The type of the code interpreter tool call. Always code_interpreter_call.
LocalShellCall
The unique ID of the local shell call.
Action actionExecute a shell command on the server.
Execute a shell command on the server.
The command to run.
Environment variables to set for the command.
The type of the local shell action. Always exec.
Optional timeout in milliseconds for the command.
Optional user to run the command as.
Optional working directory to run the command in.
The unique ID of the local shell tool call generated by the model.
Status statusThe status of the local shell call.
The status of the local shell call.
The type of the local shell call. Always local_shell_call.
LocalShellCallOutput
The unique ID of the local shell tool call generated by the model.
A JSON string of the output of the local shell tool call.
The type of the local shell tool call output. Always local_shell_call_output.
Optional<Status> statusThe status of the item. One of in_progress, completed, or incomplete.
The status of the item. One of in_progress, completed, or incomplete.
ShellCall
Action actionThe shell commands and limits that describe how to run the tool call.
The shell commands and limits that describe how to run the tool call.
Ordered shell commands for the execution environment to run.
Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
Maximum wall-clock time in milliseconds to allow the shell commands to run.
The unique ID of the shell tool call generated by the model.
The type of the item. Always shell_call.
The unique ID of the shell tool call. Populated when this item is returned via API.
Optional<Status> statusThe status of the shell call. One of in_progress, completed, or incomplete.
The status of the shell call. One of in_progress, completed, or incomplete.
ShellCallOutput
The unique ID of the shell tool call generated by the model.
List<ResponseFunctionShellCallOutputContent> outputCaptured chunks of stdout and stderr output, along with their associated outcomes.
Captured chunks of stdout and stderr output, along with their associated outcomes.
Outcome outcomeThe exit or timeout outcome associated with this shell call.
The exit or timeout outcome associated with this shell call.
JsonValue;
The outcome type. Always timeout.
class Exit:Indicates that the shell commands finished and returned an exit code.
Indicates that the shell commands finished and returned an exit code.
The exit code returned by the shell process.
The outcome type. Always exit.
Captured stderr output for the shell call.
Captured stdout output for the shell call.
The type of the item. Always shell_call_output.
The unique ID of the shell tool call output. Populated when this item is returned via API.
The maximum number of UTF-8 characters captured for this shell call's combined output.
Optional<Status> statusThe status of the shell call output.
The status of the shell call output.
ApplyPatchCall
The unique ID of the apply patch tool call generated by the model.
Operation operationThe specific create, delete, or update instruction for the apply_patch tool call.
The specific create, delete, or update instruction for the apply_patch tool call.
class CreateFile:Instruction for creating a new file via the apply_patch tool.
Instruction for creating a new file via the apply_patch tool.
Unified diff content to apply when creating the file.
Path of the file to create relative to the workspace root.
The operation type. Always create_file.
class DeleteFile:Instruction for deleting an existing file via the apply_patch tool.
Instruction for deleting an existing file via the apply_patch tool.
Path of the file to delete relative to the workspace root.
The operation type. Always delete_file.
class UpdateFile:Instruction for updating an existing file via the apply_patch tool.
Instruction for updating an existing file via the apply_patch tool.
Unified diff content to apply to the existing file.
Path of the file to update relative to the workspace root.
The operation type. Always update_file.
Status statusThe status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
The type of the item. Always apply_patch_call.
The unique ID of the apply patch tool call. Populated when this item is returned via API.
ApplyPatchCallOutput
The unique ID of the apply patch tool call generated by the model.
Status statusThe status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
The type of the item. Always apply_patch_call_output.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
McpListTools
The unique ID of the list.
The label of the MCP server.
List<Tool> toolsThe tools available on the server.
The tools available on the server.
The JSON schema describing the tool's input.
The name of the tool.
Additional annotations about the tool.
The description of the tool.
The type of the item. Always mcp_list_tools.
Error message if the server could not list tools.
McpApprovalRequest
The unique ID of the approval request.
A JSON string of arguments for the tool.
The name of the tool to run.
The label of the MCP server making the request.
The type of the item. Always mcp_approval_request.
McpApprovalResponse
The ID of the approval request being answered.
Whether the request was approved.
The type of the item. Always mcp_approval_response.
The unique ID of the approval response
Optional reason for the decision.
McpCall
The unique ID of the tool call.
A JSON string of the arguments passed to the tool.
The name of the tool that was run.
The label of the MCP server running the tool.
The type of the item. Always mcp_call.
Unique identifier for the MCP tool call approval request.
Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
The error from the tool call, if any.
The output from the tool call.
Optional<Status> statusThe status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
class ResponseCustomToolCallOutput:The output of a custom tool call from your code, being sent back to the model.
The output of a custom tool call from your code, being sent back to the model.
The call ID, used to map this custom tool call output to a custom tool call.
Output outputThe output from the custom tool call generated by your code.
Can be a string or an list of output content.
The output from the custom tool call generated by your code. Can be a string or an list of output content.
List<FunctionAndCustomToolCallOutput>
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
The type of the custom tool call output. Always custom_tool_call_output.
The unique ID of the custom tool call output in the OpenAI platform.
class ResponseCustomToolCall:A call to a custom tool created by the model.
A call to a custom tool created by the model.
An identifier used to map this custom tool call to a tool call output.
The input for the custom tool call generated by the model.
The name of the custom tool being called.
The type of the custom tool call. Always custom_tool_call.
The unique ID of the custom tool call in the OpenAI platform.
ItemReference
The ID of the item to reference.
The type of item to reference. Always item_reference.
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.
ResponsesModel modelModel ID used to generate the response, like gpt-4o or o3. 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.
Model ID used to generate the response, like gpt-4o or o3. 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.
enum ChatModel:
ResponsesOnlyModel
The object type of this resource - always set to response.
List<ResponseOutputItem> outputAn 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.
An array of content items generated by the model.
- The length and order of items in the
outputarray is dependent on the model's response. - Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs.
class ResponseOutputMessage:An output message from the model.
An output message from the model.
The unique ID of the output message.
List<Content> contentThe content of the output message.
The content of the output message.
class ResponseOutputText:A text output from the model.
A text output from the model.
List<Annotation> annotationsThe annotations of the text output.
The annotations of the text output.
class FileCitation:A citation to a file.
A citation to a file.
The ID of the file.
The filename of the file cited.
The index of the file in the list of files.
The type of the file citation. Always file_citation.
class UrlCitation:A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
The index of the last character of the URL citation in the message.
The index of the first character of the URL citation in the message.
The title of the web resource.
The type of the URL citation. Always url_citation.
The URL of the web resource.
class ContainerFileCitation:A citation for a container file used to generate a model response.
A citation for a container file used to generate a model response.
The ID of the container file.
The index of the last character of the container file citation in the message.
The ID of the file.
The filename of the container file cited.
The index of the first character of the container file citation in the message.
The type of the container file citation. Always container_file_citation.
class FilePath:A path to a file.
A path to a file.
The ID of the file.
The index of the file in the list of files.
The type of the file path. Always file_path.
The text output from the model.
The type of the output text. Always output_text.
Optional<List<Logprob>> logprobs
List<TopLogprob> topLogprobs
class ResponseOutputRefusal:A refusal from the model.
A refusal from the model.
The refusal explanation from the model.
The type of the refusal. Always refusal.
The role of the output message. Always assistant.
Status statusThe status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The type of the output message. Always message.
class ResponseFileSearchToolCall:The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
The unique ID of the file search tool call.
The queries used to search for files.
Status statusThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The type of the file search tool call. Always file_search_call.
Optional<List<Result>> resultsThe results of the file search tool call.
The results of the file search tool call.
Optional<Attributes> attributesSet 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, booleans, or numbers.
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, booleans, or numbers.
The unique ID of the file.
The name of the file.
The relevance score of the file - a value between 0 and 1.
The text that was retrieved from the file.
class ResponseFunctionToolCall:A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
A JSON string of the arguments to pass to the function.
The unique ID of the function tool call generated by the model.
The name of the function to run.
The type of the function tool call. Always function_call.
The unique ID of the function tool call.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseFunctionWebSearch:The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
The unique ID of the web search tool call.
Action actionAn object describing the specific action taken in this web search call.
Includes details on how the model used the web (search, open_page, find_in_page).
An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
class Search:Action type "search" - Performs a web search query.
Action type "search" - Performs a web search query.
[DEPRECATED] The search query.
The action type.
The search queries.
Optional<List<Source>> sourcesThe sources used in the search.
The sources used in the search.
The type of source. Always url.
The URL of the source.
class OpenPage:Action type "open_page" - Opens a specific URL from search results.
Action type "open_page" - Opens a specific URL from search results.
The action type.
The URL opened by the model.
class FindInPage:Action type "find_in_page": Searches for a pattern within a loaded page.
Action type "find_in_page": Searches for a pattern within a loaded page.
The pattern or text to search for within the page.
The action type.
The URL of the page searched for the pattern.
Status statusThe status of the web search tool call.
The status of the web search tool call.
The type of the web search tool call. Always web_search_call.
class ResponseComputerToolCall:A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
The unique ID of the computer call.
Action actionA click action.
A click action.
class Click:A click action.
A click action.
Button buttonIndicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.
Specifies the event type. For a click action, this property is always click.
The x-coordinate where the click occurred.
The y-coordinate where the click occurred.
class DoubleClick:A double click action.
A double click action.
Specifies the event type. For a double click action, this property is always set to double_click.
The x-coordinate where the double click occurred.
The y-coordinate where the double click occurred.
class Drag:A drag action.
A drag action.
List<Path> pathAn array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]
An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[
{ x: 100, y: 200 },
{ x: 200, y: 300 }
]The x-coordinate.
The y-coordinate.
Specifies the event type. For a drag action, this property is always set to drag.
class Keypress:A collection of keypresses the model would like to perform.
A collection of keypresses the model would like to perform.
The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
Specifies the event type. For a keypress action, this property is always set to keypress.
class Move:A mouse move action.
A mouse move action.
Specifies the event type. For a move action, this property is always set to move.
The x-coordinate to move to.
The y-coordinate to move to.
JsonValue;
Specifies the event type. For a screenshot action, this property is always set to screenshot.
class Scroll:A scroll action.
A scroll action.
The horizontal scroll distance.
The vertical scroll distance.
Specifies the event type. For a scroll action, this property is always set to scroll.
The x-coordinate where the scroll occurred.
The y-coordinate where the scroll occurred.
class Type:An action to type in text.
An action to type in text.
The text to type.
Specifies the event type. For a type action, this property is always set to type.
JsonValue;
Specifies the event type. For a wait action, this property is always set to wait.
An identifier used when responding to the tool call with output.
List<PendingSafetyCheck> pendingSafetyChecksThe pending safety checks for the computer call.
The pending safety checks for the computer call.
The ID of the pending safety check.
The type of the pending safety check.
Details about the pending safety check.
Status statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the computer call. Always computer_call.
class ResponseReasoningItem:A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
The unique identifier of the reasoning content.
List<Summary> summaryReasoning summary content.
Reasoning summary content.
A summary of the reasoning output from the model so far.
The type of the object. Always summary_text.
The type of the object. Always reasoning.
Optional<List<Content>> contentReasoning text content.
Reasoning text content.
The reasoning text from the model.
The type of the reasoning text. Always reasoning_text.
The encrypted content of the reasoning item - populated when a response is
generated with reasoning.encrypted_content in the include parameter.
Optional<Status> statusThe status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
class ResponseCompactionItem:A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
The unique ID of the compaction item.
The encrypted content that was produced by compaction.
The type of the item. Always compaction.
The identifier of the actor that created the item.
ImageGenerationCall
The unique ID of the image generation call.
The generated image encoded in base64.
Status statusThe status of the image generation call.
The status of the image generation call.
The type of the image generation call. Always image_generation_call.
class ResponseCodeInterpreterToolCall:A tool call to run code.
A tool call to run code.
The unique ID of the code interpreter tool call.
The code to run, or null if not available.
The ID of the container used to run the code.
Optional<List<Output>> outputsThe outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
class Logs:The logs output from the code interpreter.
The logs output from the code interpreter.
The logs output from the code interpreter.
The type of the output. Always logs.
class Image:The image output from the code interpreter.
The image output from the code interpreter.
The type of the output. Always image.
The URL of the image output from the code interpreter.
Status statusThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The type of the code interpreter tool call. Always code_interpreter_call.
LocalShellCall
The unique ID of the local shell call.
Action actionExecute a shell command on the server.
Execute a shell command on the server.
The command to run.
Environment variables to set for the command.
The type of the local shell action. Always exec.
Optional timeout in milliseconds for the command.
Optional user to run the command as.
Optional working directory to run the command in.
The unique ID of the local shell tool call generated by the model.
Status statusThe status of the local shell call.
The status of the local shell call.
The type of the local shell call. Always local_shell_call.
class ResponseFunctionShellToolCall:A tool call that executes one or more shell commands in a managed environment.
A tool call that executes one or more shell commands in a managed environment.
The unique ID of the shell tool call. Populated when this item is returned via API.
Action actionThe shell commands and limits that describe how to run the tool call.
The shell commands and limits that describe how to run the tool call.
Optional maximum number of characters to return from each command.
Optional timeout in milliseconds for the commands.
The unique ID of the shell tool call generated by the model.
Status statusThe status of the shell call. One of in_progress, completed, or incomplete.
The status of the shell call. One of in_progress, completed, or incomplete.
The type of the item. Always shell_call.
The ID of the entity that created this tool call.
class ResponseFunctionShellToolCallOutput:The output of a shell tool call that was emitted.
The output of a shell tool call that was emitted.
The unique ID of the shell call output. Populated when this item is returned via API.
The unique ID of the shell tool call generated by the model.
The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
List<Output> outputAn array of shell call output contents
An array of shell call output contents
Outcome outcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
JsonValue;
The outcome type. Always timeout.
class Exit:Indicates that the shell commands finished and returned an exit code.
Indicates that the shell commands finished and returned an exit code.
Exit code from the shell process.
The outcome type. Always exit.
The standard error output that was captured.
The standard output that was captured.
The identifier of the actor that created the item.
Status statusThe status of the shell call output. One of in_progress, completed, or incomplete.
The status of the shell call output. One of in_progress, completed, or incomplete.
The type of the shell call output. Always shell_call_output.
The identifier of the actor that created the item.
class ResponseApplyPatchToolCall:A tool call that applies file diffs by creating, deleting, or updating files.
A tool call that applies file diffs by creating, deleting, or updating files.
The unique ID of the apply patch tool call. Populated when this item is returned via API.
The unique ID of the apply patch tool call generated by the model.
Operation operationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
One of the create_file, delete_file, or update_file operations applied via apply_patch.
class CreateFile:Instruction describing how to create a file via the apply_patch tool.
Instruction describing how to create a file via the apply_patch tool.
Diff to apply.
Path of the file to create.
Create a new file with the provided diff.
class DeleteFile:Instruction describing how to delete a file via the apply_patch tool.
Instruction describing how to delete a file via the apply_patch tool.
Path of the file to delete.
Delete the specified file.
class UpdateFile:Instruction describing how to update a file via the apply_patch tool.
Instruction describing how to update a file via the apply_patch tool.
Diff to apply.
Path of the file to update.
Update an existing file with the provided diff.
Status statusThe status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
The type of the item. Always apply_patch_call.
The ID of the entity that created this tool call.
class ResponseApplyPatchToolCallOutput:The output emitted by an apply patch tool call.
The output emitted by an apply patch tool call.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
The unique ID of the apply patch tool call generated by the model.
Status statusThe status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
The type of the item. Always apply_patch_call_output.
The ID of the entity that created this tool call output.
Optional textual output returned by the apply patch tool.
McpCall
The unique ID of the tool call.
A JSON string of the arguments passed to the tool.
The name of the tool that was run.
The label of the MCP server running the tool.
The type of the item. Always mcp_call.
Unique identifier for the MCP tool call approval request.
Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.
The error from the tool call, if any.
The output from the tool call.
Optional<Status> statusThe status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.
McpListTools
The unique ID of the list.
The label of the MCP server.
List<Tool> toolsThe tools available on the server.
The tools available on the server.
The JSON schema describing the tool's input.
The name of the tool.
Additional annotations about the tool.
The description of the tool.
The type of the item. Always mcp_list_tools.
Error message if the server could not list tools.
McpApprovalRequest
The unique ID of the approval request.
A JSON string of arguments for the tool.
The name of the tool to run.
The label of the MCP server making the request.
The type of the item. Always mcp_approval_request.
class ResponseCustomToolCall:A call to a custom tool created by the model.
A call to a custom tool created by the model.
An identifier used to map this custom tool call to a tool call output.
The input for the custom tool call generated by the model.
The name of the custom tool being called.
The type of the custom tool call. Always custom_tool_call.
The unique ID of the custom tool call in the OpenAI platform.
Whether to allow the model to run tool calls in parallel.
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.
ToolChoice toolChoiceHow 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.
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.
enum ToolChoiceOptions: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.
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.
class ToolChoiceAllowed:Constrains the tools available to the model to a pre-defined set.
Constrains the tools available to the model to a pre-defined set.
Mode modeConstrains the tools available to the model to a pre-defined set.
auto allows the model to pick from among the allowed tools and generate a
message.
required requires the model to call one or more of the allowed tools.
Constrains the tools available to the model to a pre-defined set.
auto allows the model to pick from among the allowed tools and generate a
message.
required requires the model to call one or more of the allowed tools.
A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[
{ "type": "function", "name": "get_weather" },
{ "type": "mcp", "server_label": "deepwiki" },
{ "type": "image_generation" }
]Allowed tool configuration type. Always allowed_tools.
class ToolChoiceTypes:Indicates that the model should use a built-in tool to generate a response.
Learn more about built-in tools.
Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
Type typeThe type of hosted tool the model should to use. Learn more about
built-in tools.
Allowed values are:
file_searchweb_search_previewcomputer_use_previewcode_interpreterimage_generation
The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
file_searchweb_search_previewcomputer_use_previewcode_interpreterimage_generation
class ToolChoiceFunction:Use this option to force the model to call a specific function.
Use this option to force the model to call a specific function.
The name of the function to call.
For function calling, the type is always function.
class ToolChoiceMcp:Use this option to force the model to call a specific tool on a remote MCP server.
Use this option to force the model to call a specific tool on a remote MCP server.
The label of the MCP server to use.
For MCP tools, the type is always mcp.
The name of the tool to call on the server.
class ToolChoiceCustom:Use this option to force the model to call a specific custom tool.
Use this option to force the model to call a specific custom tool.
The name of the custom tool to call.
For custom tool calling, the type is always custom.
class ToolChoiceApplyPatch:Forces the model to call the apply_patch tool when executing a tool call.
Forces the model to call the apply_patch tool when executing a tool call.
The tool to call. Always apply_patch.
class ToolChoiceShell:Forces the model to call the shell tool when a tool call is required.
Forces the model to call the shell tool when a tool call is required.
The tool to call. Always shell.
List<Tool> toolsAn 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
or file search. Learn more about
built-in 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.
- 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. You can also use
custom tools to call your own code.
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 or file search. Learn more about built-in 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.
- 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. You can also use custom tools to call your own code.
class FunctionTool:Defines a function in your own code the model can choose to call. Learn more about function calling.
Defines a function in your own code the model can choose to call. Learn more about function calling.
The name of the function to call.
A JSON schema object describing the parameters of the function.
Whether to enforce strict parameter validation. Default true.
The type of the function tool. Always function.
A description of the function. Used by the model to determine whether or not to call the function.
class FileSearchTool:A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
The type of the file search tool. Always file_search.
The IDs of the vector stores to search.
Optional<Filters> filtersA filter to apply.
A filter to apply.
class ComparisonFilter:A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
The key to compare against the value.
Type typeSpecifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Value valueThe value to compare against the attribute key; supports string, number, or boolean types.
The value to compare against the attribute key; supports string, number, or boolean types.
List<ComparisonFilterValueItem>
class CompoundFilter:Combine multiple filters using and or or.
Combine multiple filters using and or or.
List<Filter> filtersArray of filters to combine. Items can be ComparisonFilter or CompoundFilter.
Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
class ComparisonFilter:A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
The key to compare against the value.
Type typeSpecifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
eq: equalsne: not equalgt: greater thangte: greater than or equallt: less thanlte: less than or equalin: innin: not in
Value valueThe value to compare against the attribute key; supports string, number, or boolean types.
The value to compare against the attribute key; supports string, number, or boolean types.
List<ComparisonFilterValueItem>
Type typeType of operation: and or or.
Type of operation: and or or.
The maximum number of results to return. This number should be between 1 and 50 inclusive.
Optional<RankingOptions> rankingOptionsRanking options for search.
Ranking options for search.
Optional<HybridSearch> hybridSearchWeights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
The weight of the embedding in the reciprocal ranking fusion.
The weight of the text in the reciprocal ranking fusion.
Optional<Ranker> rankerThe ranker to use for the file search.
The ranker to use for the file search.
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.
class ComputerTool:A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
The height of the computer display.
The width of the computer display.
Environment environmentThe type of computer environment to control.
The type of computer environment to control.
The type of the computer use tool. Always computer_use_preview.
class WebSearchTool:Search the Internet for sources related to the prompt. Learn more about the
web search tool.
Search the Internet for sources related to the prompt. Learn more about the web search tool.
Type typeThe type of the web search tool. One of web_search or web_search_2025_08_26.
The type of the web search tool. One of web_search or web_search_2025_08_26.
Optional<Filters> filtersFilters for the search.
Filters for the search.
Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example: ["pubmed.ncbi.nlm.nih.gov"]
Optional<SearchContextSize> searchContextSizeHigh level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
Optional<UserLocation> userLocationThe approximate location of the user.
The approximate location of the user.
Free text input for the city of the user, e.g. San Francisco.
The two-letter ISO country code of the user, e.g. US.
Free text input for the region of the user, e.g. California.
The IANA timezone of the user, e.g. America/Los_Angeles.
The type of location approximation. Always approximate.
Mcp
A label for this MCP server, used to identify it in tool calls.
The type of the MCP tool. Always mcp.
Optional<AllowedTools> allowedToolsList of allowed tool names or a filter object.
List of allowed tool names or a filter object.
class McpToolFilter:A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
Optional<ConnectorId> connectorIdIdentifier for service connectors, like those available in ChatGPT. One of
server_url or connector_id must be provided. Learn more about service
connectors here.
Currently supported connector_id values are:
- Dropbox:
connector_dropbox
- Gmail:
connector_gmail
- Google Calendar:
connector_googlecalendar
- Google Drive:
connector_googledrive
- Microsoft Teams:
connector_microsoftteams
- Outlook Calendar:
connector_outlookcalendar
- Outlook Email:
connector_outlookemail
- SharePoint:
connector_sharepoint
Identifier for service connectors, like those available in ChatGPT. One of
server_url or connector_id must be provided. Learn more about service
connectors here.
Currently supported connector_id values are:
- Dropbox:
connector_dropbox - Gmail:
connector_gmail - Google Calendar:
connector_googlecalendar - Google Drive:
connector_googledrive - Microsoft Teams:
connector_microsoftteams - Outlook Calendar:
connector_outlookcalendar - Outlook Email:
connector_outlookemail - SharePoint:
connector_sharepoint
Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
Optional<RequireApproval> requireApprovalSpecify which of the MCP server's tools require approval.
Specify which of the MCP server's tools require approval.
class McpToolApprovalFilter:Specify which of the MCP server's tools require approval. Can be
always, never, or a filter object associated with tools
that require approval.
Specify which of the MCP server's tools require approval. Can be
always, never, or a filter object associated with tools
that require approval.
Optional<Always> alwaysA filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
Optional<Never> neverA filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
Indicates whether or not a tool modifies data or is read-only. If an
MCP server is annotated with readOnlyHint,
it will match this filter.
List of allowed tool names.
enum McpToolApprovalSetting:Specify a single approval policy for all tools. One of always or
never. When set to always, all tools will require approval. When
set to never, all tools will not require approval.
Specify a single approval policy for all tools. One of always or
never. When set to always, all tools will require approval. When
set to never, all tools will not require approval.
Optional description of the MCP server, used to provide more context.
The URL for the MCP server. One of server_url or connector_id must be
provided.
CodeInterpreter
Container containerThe code interpreter container. Can be a container ID or an object that
specifies uploaded file IDs to make available to your code, along with an
optional memory_limit setting.
The code interpreter container. Can be a container ID or an object that
specifies uploaded file IDs to make available to your code, along with an
optional memory_limit setting.
class CodeInterpreterToolAuto:Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
Always auto.
An optional list of uploaded files to make available to your code.
Optional<MemoryLimit> memoryLimitThe memory limit for the code interpreter container.
The memory limit for the code interpreter container.
The type of the code interpreter tool. Always code_interpreter.
ImageGeneration
The type of the image generation tool. Always image_generation.
Optional<Action> actionWhether to generate a new image or edit an existing image. Default: auto.
Whether to generate a new image or edit an existing image. Default: auto.
Optional<Background> backgroundBackground type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Optional<InputFidelity> inputFidelityControl how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Optional<InputImageMask> inputImageMaskOptional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
File ID for the mask image.
Base64-encoded mask image.
Optional<Model> modelThe image generation model to use. Default: gpt-image-1.
The image generation model to use. Default: gpt-image-1.
Optional<Moderation> moderationModeration level for the generated image. Default: auto.
Moderation level for the generated image. Default: auto.
Compression level for the output image. Default: 100.
Optional<OutputFormat> outputFormatThe output format of the generated image. One of png, webp, or
jpeg. Default: png.
The output format of the generated image. One of png, webp, or
jpeg. Default: png.
Number of partial images to generate in streaming mode, from 0 (default value) to 3.
Optional<Quality> qualityThe quality of the generated image. One of low, medium, high,
or auto. Default: auto.
The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
Optional<Size> sizeThe size of the generated image. One of 1024x1024, 1024x1536,
1536x1024, or auto. Default: auto.
The size of the generated image. One of 1024x1024, 1024x1536,
1536x1024, or auto. Default: auto.
JsonValue;
The type of the local shell tool. Always local_shell.
class FunctionShellTool:A tool that allows the model to execute shell commands.
A tool that allows the model to execute shell commands.
The type of the shell tool. Always shell.
class CustomTool:A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
The name of the custom tool, used to identify it in tool calls.
The type of the custom tool. Always custom.
Optional description of the custom tool, used to provide more context.
The input format for the custom tool. Default is unconstrained text.
The input format for the custom tool. Default is unconstrained text.
JsonValue;
Unconstrained text format. Always text.
Grammar
The grammar definition.
Syntax syntaxThe syntax of the grammar definition. One of lark or regex.
The syntax of the grammar definition. One of lark or regex.
Grammar format. Always grammar.
class WebSearchPreviewTool:This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
Type typeThe type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
Optional<SearchContextSize> searchContextSizeHigh level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
Optional<UserLocation> userLocationThe user's location.
The user's location.
The type of location approximation. Always approximate.
Free text input for the city of the user, e.g. San Francisco.
The two-letter ISO country code of the user, e.g. US.
Free text input for the region of the user, e.g. California.
The IANA timezone of the user, e.g. America/Los_Angeles.
class ApplyPatchTool:Allows the assistant to create, delete, or update files using unified diffs.
Allows the assistant to create, delete, or update files using unified diffs.
The type of the tool. Always apply_patch.
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.
Whether to run the model response in the background. Learn more.
Unix timestamp (in seconds) of when this Response was completed.
Only present when the status is completed.
Optional<Conversation> conversationThe conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
The unique ID of the conversation that this response was associated with.
An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
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.
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.
Reference to a prompt template and its variables.
Learn more.
Reference to a prompt template and its variables. Learn more.
The unique identifier of the prompt template to use.
Optional<Variables> variablesOptional map of values to substitute in for variables in your
prompt. The substitution values can either be strings, or other
Response input types like images or files.
Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
class ResponseInputText:A text input to the model.
A text input to the model.
The text input to the model.
The type of the input item. Always input_text.
class ResponseInputImage:An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
Detail detailThe detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, or auto. Defaults to auto.
The type of the input item. Always input_image.
The ID of the file to be sent to the model.
The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
class ResponseInputFile:A file input to the model.
A file input to the model.
The type of the input item. Always input_file.
The content of the file to be sent to the model.
The ID of the file to be sent to the model.
The URL of the file to be sent to the model.
The name of the file to be sent to the model.
Optional version of the prompt template.
Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
Optional<PromptCacheRetention> promptCacheRetentionThe 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.
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.
gpt-5 and o-series models only
Configuration options for
reasoning models.
gpt-5 and o-series models only
Configuration options for reasoning models.
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1 default to medium reasoning effort, and do not support none.
- The
gpt-5-pro model defaults to (and only supports) high reasoning effort.
xhigh is supported for all models after gpt-5.1-codex-max.
Constrains effort on reasoning for
reasoning models.
Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1.- All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. - The
gpt-5-promodel defaults to (and only supports)highreasoning effort. xhighis supported for all models aftergpt-5.1-codex-max.
DeprecatedOptional<GenerateSummary> generateSummaryDeprecated: use summary instead.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
Deprecated: use summary instead.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
Optional<Summary> summaryA summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
concise is supported for computer-use-preview models and all reasoning models after gpt-5.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model's reasoning process.
One of auto, concise, or detailed.
concise is supported for computer-use-preview models and all reasoning models after gpt-5.
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. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
Optional<ServiceTier> serviceTierSpecifies 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' or 'priority', then the request will be processed with the corresponding service tier.
- 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.
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' or 'priority', then the request will be processed with the corresponding service tier.
- 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.
The status of the response generation. One of completed, failed,
in_progress, cancelled, queued, or incomplete.
The status of the response generation. One of completed, failed,
in_progress, cancelled, queued, or incomplete.
Configuration options for a text response from the model. Can be plain
text or structured JSON data. Learn more:
Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
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.
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.
class ResponseFormatText:Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatTextJsonSchemaConfig:JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
The type of response format being defined. Always json_schema.
A description of what the response format is for, used by the model to determine how to respond in the format.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
class ResponseFormatJsonObject:JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
Optional<Verbosity> verbosityConstrains the verbosity of the model's response. Lower values will result in
more concise responses, while higher values will result in more verbose responses.
Currently supported values are low, medium, and high.
Constrains the verbosity of the model's response. Lower values will result in
more concise responses, while higher values will result in more verbose responses.
Currently supported values are low, medium, and high.
An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.
Optional<Truncation> truncationThe 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.
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.
Represents token usage details including input tokens, output tokens,
a breakdown of output tokens, and the total tokens used.
Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
The number of input tokens.
InputTokensDetails inputTokensDetailsA detailed breakdown of the input tokens.
A detailed breakdown of the input tokens.
The number of tokens that were retrieved from the cache. More on prompt caching.
The number of output tokens.
OutputTokensDetails outputTokensDetailsA detailed breakdown of the output tokens.
A detailed breakdown of the output tokens.
The number of reasoning tokens.
The total number of tokens used.
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.
The sequence number for this event.
The type of the event. Always 'response.queued'.
class ResponseCustomToolCallInputDeltaEvent:Event representing a delta (partial update) to the input of a custom tool call.
Event representing a delta (partial update) to the input of a custom tool call.
The incremental input data (delta) for the custom tool call.
Unique identifier for the API item associated with this event.
The index of the output this delta applies to.
The sequence number of this event.
The event type identifier.
class ResponseCustomToolCallInputDoneEvent:Event indicating that input for a custom tool call is complete.
Event indicating that input for a custom tool call is complete.
The complete input data for the custom tool call.
Unique identifier for the API item associated with this event.
The index of the output this event applies to.
The sequence number of this event.
The event type identifier.
Get a model response
package com.openai.example;
import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.responses.Response;
import com.openai.models.responses.ResponseRetrieveParams;
public final class Main {
private Main() {}
public static void main(String[] args) {
OpenAIClient client = OpenAIOkHttpClient.fromEnv();
Response response = client.responses().retrieve("resp_677efb5139a88190b512bc3fef8e535d");
}
}{
"id": "id",
"created_at": 0,
"error": {
"code": "server_error",
"message": "message"
},
"incomplete_details": {
"reason": "max_output_tokens"
},
"instructions": "string",
"metadata": {
"foo": "string"
},
"model": "gpt-5.1",
"object": "response",
"output": [
{
"id": "id",
"content": [
{
"annotations": [
{
"file_id": "file_id",
"filename": "filename",
"index": 0,
"type": "file_citation"
}
],
"text": "text",
"type": "output_text",
"logprobs": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0,
"top_logprobs": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0
}
]
}
]
}
],
"role": "assistant",
"status": "in_progress",
"type": "message"
}
],
"parallel_tool_calls": true,
"temperature": 1,
"tool_choice": "none",
"tools": [
{
"name": "name",
"parameters": {
"foo": "bar"
},
"strict": true,
"type": "function",
"description": "description"
}
],
"top_p": 1,
"background": true,
"completed_at": 0,
"conversation": {
"id": "id"
},
"max_output_tokens": 0,
"max_tool_calls": 0,
"output_text": "output_text",
"previous_response_id": "previous_response_id",
"prompt": {
"id": "id",
"variables": {
"foo": "string"
},
"version": "version"
},
"prompt_cache_key": "prompt-cache-key-1234",
"prompt_cache_retention": "in-memory",
"reasoning": {
"effort": "none",
"generate_summary": "auto",
"summary": "auto"
},
"safety_identifier": "safety-identifier-1234",
"service_tier": "auto",
"status": "completed",
"text": {
"format": {
"type": "text"
},
"verbosity": "low"
},
"top_logprobs": 0,
"truncation": "auto",
"usage": {
"input_tokens": 0,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 0,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 0
},
"user": "user-1234"
}Returns Examples
{
"id": "id",
"created_at": 0,
"error": {
"code": "server_error",
"message": "message"
},
"incomplete_details": {
"reason": "max_output_tokens"
},
"instructions": "string",
"metadata": {
"foo": "string"
},
"model": "gpt-5.1",
"object": "response",
"output": [
{
"id": "id",
"content": [
{
"annotations": [
{
"file_id": "file_id",
"filename": "filename",
"index": 0,
"type": "file_citation"
}
],
"text": "text",
"type": "output_text",
"logprobs": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0,
"top_logprobs": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0
}
]
}
]
}
],
"role": "assistant",
"status": "in_progress",
"type": "message"
}
],
"parallel_tool_calls": true,
"temperature": 1,
"tool_choice": "none",
"tools": [
{
"name": "name",
"parameters": {
"foo": "bar"
},
"strict": true,
"type": "function",
"description": "description"
}
],
"top_p": 1,
"background": true,
"completed_at": 0,
"conversation": {
"id": "id"
},
"max_output_tokens": 0,
"max_tool_calls": 0,
"output_text": "output_text",
"previous_response_id": "previous_response_id",
"prompt": {
"id": "id",
"variables": {
"foo": "string"
},
"version": "version"
},
"prompt_cache_key": "prompt-cache-key-1234",
"prompt_cache_retention": "in-memory",
"reasoning": {
"effort": "none",
"generate_summary": "auto",
"summary": "auto"
},
"safety_identifier": "safety-identifier-1234",
"service_tier": "auto",
"status": "completed",
"text": {
"format": {
"type": "text"
},
"verbosity": "low"
},
"top_logprobs": 0,
"truncation": "auto",
"usage": {
"input_tokens": 0,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 0,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 0
},
"user": "user-1234"
}