Module openai.responses

ballerinax/openai.responses Ballerina library

1.0.0

Overview

OpenAI, an AI research organization focused on creating friendly AI for humanity, offers the OpenAI API to access its powerful AI models for tasks like natural language processing and image generation.

The ballerinax/openai.responses package offers functionality to connect and interact with the Responses API of the OpenAI REST API. The Responses API is OpenAI's most advanced interface for generating model responses — an evolution of Chat Completions that brings added simplicity and powerful agentic primitives such as built-in tools for web search and file search.

The package currently exposes the create model response operation (POST /responses), which covers text and image inputs, text and JSON outputs, function calling, and the built-in tools.

Setup guide

To use the OpenAI Connector, you must have access to the OpenAI API through an OpenAI Platform account and a project under it. If you do not have a OpenAI Platform account, you can sign up for one here.

Create an OpenAI API Key

Open the OpenAI Platform Dashboard.
Navigate to Dashboard -> API keys.
Click on the "Create new secret key" button.
Fill the details and click on Create secret key.
Store the API key securely to use in your application.

Quickstart

To use the OpenAI Responses connector in your Ballerina application, update the .bal file as follows:

Step 1: Import the module

Import the ballerinax/openai.responses module.


import ballerinax/openai.responses;

Step 2: Create a new connector instance

Create a responses:Client with the obtained API Key and initialize the connector.


configurable string token = ?;

final responses:Client openAIResponses = check new ({
    auth: {
        token
    }
});

Step 3: Invoke the connector operation

Now, you can utilize the available connector operation.

Create a model response


public function main() returns error? {
    responses:CreateResponse request = {
        model: "gpt-4o-mini",
        input: "What is Ballerina programming language?"
    };

    responses:Response response =
        check openAIResponses->/responses.post(request);
}

Step 4: Run the Ballerina application


bal run

Examples

The OpenAI Responses connector provides practical examples illustrating usage in various scenarios. Explore these examples, covering the following use cases:

CLI assistant - Execute the user's task description by generating and running the appropriate command in the command line interface of their selected operating system.
Image to markdown document converter - Generate detailed markdown documentation based on the image content.

Clients

openai.responses: Client

Isolated

The OpenAI REST API. Please see https://platform.openai.com/docs/api-reference for more details.

Constructor

Gets invoked to initialize the connector.

init (ConnectionConfig config, string serviceUrl)

config ConnectionConfig - The configurations to be used when initializing the connector

serviceUrl string "https://api.openai.com/v1" - URL of the target service

post responses

Isolated FunctionResource Function

function post responses(CreateResponse payload, map<string|string[]> headers) returns Response|error

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

Parameters

payload CreateResponse -

headers map<string|string[]> (default {}) - Headers to be sent with the request

Return Type

Response|error - OK

Records

openai.responses: ApplyPatchCreateFileOperation

Instruction describing how to create a file via the apply_patch tool.

Fields

'type "create_file" (default "create_file") - Create a new file with the provided diff.

path string - Path of the file to create.

diff string - Diff to apply.

openai.responses: ApplyPatchCreateFileOperationParam

Instruction for creating a new file via the apply_patch tool.

Fields

'type "create_file" (default "create_file") - The operation type. Always create_file.

path string - Path of the file to create relative to the workspace root.

diff string - Unified diff content to apply when creating the file.

openai.responses: ApplyPatchDeleteFileOperation

Instruction describing how to delete a file via the apply_patch tool.

Fields

'type "delete_file" (default "delete_file") - Delete the specified file.

path string - Path of the file to delete.

openai.responses: ApplyPatchDeleteFileOperationParam

Instruction for deleting an existing file via the apply_patch tool.

Fields

'type "delete_file" (default "delete_file") - The operation type. Always delete_file.

path string - Path of the file to delete relative to the workspace root.

openai.responses: ApplyPatchToolCall

A tool call that applies file diffs by creating, deleting, or updating files.

Fields

'type "apply_patch_call" (default "apply_patch_call") - The type of the item. Always apply_patch_call.

id string - The unique ID of the apply patch tool call. Populated when this item is returned via API.

call_id string - The unique ID of the apply patch tool call generated by the model.

status ApplyPatchCallStatus -

operation ApplyPatchCreateFileOperation|ApplyPatchDeleteFileOperation|ApplyPatchUpdateFileOperation - One of the create_file, delete_file, or update_file operations applied via apply_patch.

created_by? string - The ID of the entity that created this tool call.

openai.responses: ApplyPatchToolCallItemParam

A tool call representing a request to create, delete, or update files using diff patches.

Fields

'type "apply_patch_call" (default "apply_patch_call") - The type of the item. Always apply_patch_call.

id? string? - The unique ID of the apply patch tool call. Populated when this item is returned via API.

call_id string - The unique ID of the apply patch tool call generated by the model.

status ApplyPatchCallStatusParam - Status values reported for apply_patch tool calls.

operation ApplyPatchOperationParam - One of the create_file, delete_file, or update_file operations supplied to the apply_patch tool.

openai.responses: ApplyPatchToolCallOutput

The output emitted by an apply patch tool call.

Fields

'type "apply_patch_call_output" (default "apply_patch_call_output") - The type of the item. Always apply_patch_call_output.

id string - The unique ID of the apply patch tool call output. Populated when this item is returned via API.

call_id string - The unique ID of the apply patch tool call generated by the model.

status ApplyPatchCallOutputStatus -

output? string? - Optional textual output returned by the apply patch tool.

created_by? string - The ID of the entity that created this tool call output.

openai.responses: ApplyPatchToolCallOutputItemParam

The streamed output emitted by an apply patch tool call.

Fields

'type "apply_patch_call_output" (default "apply_patch_call_output") - The type of the item. Always apply_patch_call_output.

id? string? - The unique ID of the apply patch tool call output. Populated when this item is returned via API.

call_id string - The unique ID of the apply patch tool call generated by the model.

status ApplyPatchCallOutputStatusParam - Outcome values reported for apply_patch tool call outputs.

output? string? - Optional human-readable log text from the apply patch tool (e.g., patch results or errors).

openai.responses: ApplyPatchToolParam

Allows the assistant to create, delete, or update files using unified diffs.

Fields

'type "apply_patch" (default "apply_patch") - The type of the tool. Always apply_patch.

openai.responses: ApplyPatchUpdateFileOperation

Instruction describing how to update a file via the apply_patch tool.

Fields

'type "update_file" (default "update_file") - Update an existing file with the provided diff.

path string - Path of the file to update.

diff string - Diff to apply.

openai.responses: ApplyPatchUpdateFileOperationParam

Instruction for updating an existing file via the apply_patch tool.

Fields

'type "update_file" (default "update_file") - The operation type. Always update_file.

path string - Path of the file to update relative to the workspace root.

diff string - Unified diff content to apply to the existing file.

openai.responses: ApproximateLocation

Fields

'type "approximate" (default "approximate") - The type of location approximation. Always approximate.

country? string? - The two-letter ISO country code of the user, e.g. US.

region? string? - Free text input for the region of the user, e.g. California.

city? string? - Free text input for the city of the user, e.g. San Francisco.

timezone? string? - The IANA timezone of the user, e.g. America/Los_Angeles.

openai.responses: AutoCodeInterpreterToolParam

Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.

Fields

'type "auto" (default "auto") - Always auto.

file_ids? string[] - An optional list of uploaded files to make available to your code.

memory_limit? ContainerMemoryLimit - The memory limit for the code interpreter container.

network_policy? ContainerNetworkPolicyDisabledParam|ContainerNetworkPolicyAllowlistParam - Network access policy for the container.

openai.responses: ClickParam

A click action.

Fields

'type "click" (default "click") - Specifies the event type. For a click action, this property is always click.

button ClickButtonType -

x int - The x-coordinate where the click occurred.

y int - The y-coordinate where the click occurred.

keys? string[]? - The keys being held while clicking.

openai.responses: CodeInterpreterOutputImage

The image output from the code interpreter.

Fields

'type "image" (default "image") - The type of the output. Always image.

url string - The URL of the image output from the code interpreter.

openai.responses: CodeInterpreterOutputLogs

The logs output from the code interpreter.

Fields

'type "logs" (default "logs") - The type of the output. Always logs.

logs string - The logs output from the code interpreter.

openai.responses: CodeInterpreterTool

A tool that runs Python code to help generate a response to a prompt.

Fields

'type "code_interpreter" - The type of the code interpreter tool. Always code_interpreter.

container string|AutoCodeInterpreterToolParam - 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.

openai.responses: CodeInterpreterToolCall

A tool call to run code.

Fields

'type "code_interpreter_call" (default "code_interpreter_call") - The type of the code interpreter tool call. Always code_interpreter_call.

id string - The unique ID of the code interpreter tool call.

status "in_progress"|"completed"|"incomplete"|"interpreting"|"failed" - The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.

container_id string - The ID of the container used to run the code.

code string? - The code to run, or null if not available.

outputs (CodeInterpreterOutputLogs|CodeInterpreterOutputImage)[]? - The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.

openai.responses: CompactionBody

A compaction item generated by the v1/responses/compact API.

Fields

'type "compaction" (default "compaction") - The type of the item. Always compaction.

id string - The unique ID of the compaction item.

encrypted_content string - The encrypted content that was produced by compaction.

created_by? string - The identifier of the actor that created the item.

openai.responses: CompactionSummaryItemParam

A compaction item generated by the v1/responses/compact API.

Fields

id? string? - The ID of the compaction item.

'type "compaction" (default "compaction") - The type of the item. Always compaction.

encrypted_content string - The encrypted content of the compaction summary.

openai.responses: ComparisonFilter

Closed record

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

Fields

'type "eq"|"ne"|"gt"|"gte"|"lt"|"lte"|"in"|"nin" (default "eq") - Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.
- eq: equals
- ne: not equal
- gt: greater than
- gte: greater than or equal
- lt: less than
- lte: less than or equal
- in: in
- nin: not in

'key string - The key to compare against the value.

value string|decimal|boolean|(string|decimal)[] - The value to compare against the attribute key; supports string, number, or boolean types.

openai.responses: CompoundFilter

Closed record

Combine multiple filters using and or or.

Fields

'type "and"|"or" - Type of operation: and or or.

filters (ComparisonFilter|CompoundFilter)[] - Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.

openai.responses: ComputerCallOutputItemParam

The output of a computer tool call.

Fields

id? string? - The ID of the computer tool call output.

call_id string - The ID of the computer tool call that produced the output.

'type "computer_call_output" (default "computer_call_output") - The type of the computer tool call output. Always computer_call_output.

output ComputerScreenshotImage - A computer screenshot image used with the computer use tool.

acknowledged_safety_checks? ComputerCallSafetyCheckParam[]? - The safety checks reported by the API that have been acknowledged by the developer.

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

openai.responses: ComputerCallSafetyCheckParam

A pending safety check for the computer call.

Fields

id string - The ID of the pending safety check.

code? string? - The type of the pending safety check.

message? string? - Details about the pending safety check.

openai.responses: ComputerScreenshotImage

A computer screenshot image used with the computer use tool.

Fields

'type "computer_screenshot" (default "computer_screenshot") - Specifies the event type. For a computer screenshot, this property is always set to computer_screenshot.

image_url? string - The URL of the screenshot image.

file_id? string - The identifier of an uploaded file that contains the screenshot.

openai.responses: ComputerTool

A tool that controls a virtual computer. Learn more about the computer tool.

Fields

'type "computer" (default "computer") - The type of the computer tool. Always computer.

openai.responses: ComputerToolCall

A tool call to a computer use tool. See the computer use guide for more information.

Fields

'type "computer_call" (default "computer_call") - The type of the computer call. Always computer_call.

id string - The unique ID of the computer call.

call_id string - An identifier used when responding to the tool call with output.

action? ComputerAction -

actions? ComputerActionList - Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.

pending_safety_checks ComputerCallSafetyCheckParam[] - The pending safety checks for the computer call.

status "in_progress"|"completed"|"incomplete" - The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.

openai.responses: ComputerToolCallOutput

The output of a computer tool call.

Fields

'type "computer_call_output" (default "computer_call_output") - The type of the computer tool call output. Always computer_call_output.

id? string - The ID of the computer tool call output.

call_id string - The ID of the computer tool call that produced the output.

acknowledged_safety_checks? ComputerCallSafetyCheckParam[] - The safety checks reported by the API that have been acknowledged by the developer.

output ComputerScreenshotImage - A computer screenshot image used with the computer use tool.

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

openai.responses: ComputerToolCallOutputResource

Fields

Fields Included from *ComputerToolCallOutput

type "computer_call_output"
id string
call_id string
acknowledged_safety_checks ComputerCallSafetyCheckParam[]
output ComputerScreenshotImage
status "in_progress"|"completed"|"incomplete"|"failed"
anydata...

id string - The unique ID of the computer call tool output.

status? ComputerCallOutputStatus -

created_by? string - The identifier of the actor that created the item.

openai.responses: ComputerUsePreviewTool

A tool that controls a virtual computer. Learn more about the computer tool.

Fields

'type "computer_use_preview" (default "computer_use_preview") - The type of the computer use tool. Always computer_use_preview.

environment ComputerEnvironment -

display_width int - The width of the computer display.

display_height int - The height of the computer display.

openai.responses: ConnectionConfig

Closed record

Provides a set of configurations for controlling the behaviours when communicating with a remote HTTP endpoint.

Fields

auth BearerTokenConfig - Configurations related to client authentication

httpVersion HttpVersion(default http:HTTP_2_0) - The HTTP version understood by the client

http1Settings ClientHttp1Settings(default {}) - Configurations related to HTTP/1.x protocol

http2Settings ClientHttp2Settings(default {}) - Configurations related to HTTP/2 protocol

timeout decimal(default 30) - The maximum time to wait (in seconds) for a response before closing the connection

forwarded string(default "disable") - The choice of setting forwarded/x-forwarded header

followRedirects? FollowRedirects - Configurations associated with Redirection

poolConfig? PoolConfiguration - Configurations associated with request pooling

cache CacheConfig(default {}) - HTTP caching related configurations

compression Compression(default http:COMPRESSION_AUTO) - Specifies the way of handling compression (accept-encoding) header

circuitBreaker? CircuitBreakerConfig - Configurations associated with the behaviour of the Circuit Breaker

retryConfig? RetryConfig - Configurations associated with retrying

cookieConfig? CookieConfig - Configurations associated with cookies

responseLimits ResponseLimitConfigs(default {}) - Configurations associated with inbound response size limits

secureSocket? ClientSecureSocket - SSL/TLS-related options

proxy? ProxyConfig - Proxy server related options

socketConfig ClientSocketConfig(default {}) - Provides settings related to client socket configuration

validation boolean(default true) - Enables the inbound payload validation functionality which provided by the constraint package. Enabled by default

laxDataBinding boolean(default true) - Enables relaxed data binding on the client side. When enabled, nil values are treated as optional, and absent fields are handled as nilable types. Enabled by default.

openai.responses: ContainerAutoParam

Fields

'type "container_auto" (default "container_auto") - Automatically creates a container for this request

file_ids? string[] - An optional list of uploaded files to make available to your code.

memory_limit? ContainerMemoryLimit - The memory limit for the container.

network_policy? ContainerNetworkPolicyDisabledParam|ContainerNetworkPolicyAllowlistParam - Network access policy for the container.

skills? (SkillReferenceParam|InlineSkillParam)[] - An optional list of skills referenced by id or inline data.

openai.responses: ContainerFileCitationBody

A citation for a container file used to generate a model response.

Fields

'type "container_file_citation" (default "container_file_citation") - The type of the container file citation. Always container_file_citation.

container_id string - The ID of the container file.

file_id string - The ID of the file.

start_index int - The index of the first character of the container file citation in the message.

end_index int - The index of the last character of the container file citation in the message.

filename string - The filename of the container file cited.

openai.responses: ContainerNetworkPolicyAllowlistParam

Fields

'type "allowlist" (default "allowlist") - Allow outbound network access only to specified domains. Always allowlist.

allowed_domains string[] - A list of allowed domains when type is allowlist.

domain_secrets? ContainerNetworkPolicyDomainSecretParam[] - Optional domain-scoped secrets for allowlisted domains.

openai.responses: ContainerNetworkPolicyDisabledParam

Fields

'type "disabled" (default "disabled") - Disable outbound network access. Always disabled.

openai.responses: ContainerNetworkPolicyDomainSecretParam

Fields

domain string - The domain associated with the secret.

name string - The name of the secret to inject for the domain.

value string - The secret value to inject for the domain.

openai.responses: ContainerReferenceParam

Fields

'type "container_reference" (default "container_reference") - References a container created with the /v1/containers endpoint

container_id string - The ID of the referenced container.

openai.responses: ContainerReferenceResource

Represents a container created with /v1/containers.

Fields

'type "container_reference" (default "container_reference") - The environment type. Always container_reference.

container_id string -

openai.responses: ContextManagementParam

Fields

'type string - The context management entry type. Currently only 'compaction' is supported.

compact_threshold? int? - Token threshold at which compaction should be triggered for this entry.

openai.responses: Conversation2

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

Fields

id string - The unique ID of the conversation that this response was associated with.

openai.responses: ConversationParam2

The conversation that this response belongs to.

Fields

id string - The unique ID of the conversation.

openai.responses: CoordParam

An x/y coordinate pair, e.g. { x: 100, y: 200 }.

Fields

x int - The x-coordinate.

y int - The y-coordinate.

openai.responses: CreateModelResponseProperties

Fields

Fields Included from *ModelResponseProperties

metadata Metadata|()
top_logprobs int|()
temperature decimal|()
top_p decimal|()
user string
safety_identifier string
prompt_cache_key string
service_tier "priority"|()|"auto"|"default"|"flex"|"scale"
prompt_cache_retention "24h"|()|"in_memory"
anydata...

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

openai.responses: CreateResponse

Fields

Fields Included from *CreateModelResponseProperties

top_logprobs int|()
metadata Metadata|()
temperature decimal|()
top_p decimal|()
user string
safety_identifier string
prompt_cache_key string
service_tier "priority"|()|"auto"|"default"|"flex"|"scale"
prompt_cache_retention "24h"|()|"in_memory"
anydata...

Fields Included from *ResponseProperties

previous_response_id string|()
model ModelIdsResponses
reasoning Reasoning
background boolean|()
max_tool_calls int|()
text ResponseTextParam
tools ToolsArray
tool_choice ToolChoiceParam
prompt Prompt|()
truncation "disabled"|()|"auto"
anydata...

input? InputParam - Text, image, or file inputs to the model, used to generate a response. Learn more:

include? IncludeEnum[]? - Specify additional output data to include in the model response. Currently supported values are:
- web_search_call.action.sources: Include the sources of the web search tool call.
- code_interpreter_call.outputs: Includes the outputs of python code execution in code interpreter tool call items.
- computer_call_output.output.image_url: Include image urls from the computer call output.
- file_search_call.results: Include the search results of the file search tool call.
- message.input_image.image_url: Include image urls from the input message.
- message.output_text.logprobs: Include logprobs with assistant messages.
- reasoning.encrypted_content: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the store parameter is set to false, or when an organization is enrolled in the zero data retention program).

parallel_tool_calls? boolean? - Whether to allow the model to run tool calls in parallel.

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

instructions? string? - 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.

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

stream_options? ResponseStreamOptions? - Options for streaming responses. Only set this when you set stream: true.

conversation? ConversationParam -

context_management? ContextManagementParam[]? - Context management configuration for this request.

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

openai.responses: CustomGrammarFormatParam

A grammar defined by the user.

Fields

'type "grammar" (default "grammar") - Grammar format. Always grammar.

syntax GrammarSyntax1 -

definition string - The grammar definition.

openai.responses: CustomTextFormatParam

Unconstrained free-form text.

Fields

'type "text" (default "text") - Unconstrained text format. Always text.

openai.responses: CustomToolCall

A call to a custom tool created by the model.

Fields

'type "custom_tool_call" - The type of the custom tool call. Always custom_tool_call.

id? string - The unique ID of the custom tool call in the OpenAI platform.

call_id string - An identifier used to map this custom tool call to a tool call output.

namespace? string - The namespace of the custom tool being called.

name string - The name of the custom tool being called.

input string - The input for the custom tool call generated by the model.

openai.responses: CustomToolCallOutput

The output of a custom tool call from your code, being sent back to the model.

Fields

'type "custom_tool_call_output" - The type of the custom tool call output. Always custom_tool_call_output.

id? string - The unique ID of the custom tool call output in the OpenAI platform.

call_id string - The call ID, used to map this custom tool call output to a custom tool call.

output string|FunctionAndCustomToolCallOutput[] - The output from the custom tool call generated by your code. Can be a string or an list of output content.

openai.responses: CustomToolCallOutputResource

Fields

Fields Included from *CustomToolCallOutput

type "custom_tool_call_output"
id string
call_id string
output string|FunctionAndCustomToolCallOutput[]
anydata...

id string - The unique ID of the custom tool call output item.

status FunctionCallOutputStatusEnum -

created_by? string - The identifier of the actor that created the item.

openai.responses: CustomToolParam

A custom tool that processes input using a specified format. Learn more about custom tools

Fields

'type "custom" (default "custom") - The type of the custom tool. Always custom.

name string - The name of the custom tool, used to identify it in tool calls.

description? string - Optional description of the custom tool, used to provide more context.

format? CustomTextFormatParam|CustomGrammarFormatParam - The input format for the custom tool. Default is unconstrained text.

defer_loading? boolean - Whether this tool should be deferred and discovered via tool search.

openai.responses: DoubleClickAction

A double click action.

Fields

'type "double_click" (default "double_click") - Specifies the event type. For a double click action, this property is always set to double_click.

x int - The x-coordinate where the double click occurred.

y int - The y-coordinate where the double click occurred.

keys string[]? - The keys being held while double-clicking.

openai.responses: DragParam

A drag action.

Fields

'type "drag" (default "drag") - Specifies the event type. For a drag action, this property is always set to drag.

path CoordParam[] - 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 }
]
```

keys? string[]? - The keys being held while dragging the mouse.

openai.responses: 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.

Fields

role "user"|"assistant"|"system"|"developer" - The role of the message input. One of user, assistant, system, or developer.

content string|InputMessageContentList - Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.

phase? MessagePhase -

'type? "message" - The type of the message input. Always message.

openai.responses: EmptyModelParam

openai.responses: FileCitationBody

A citation to a file.

Fields

'type "file_citation" (default "file_citation") - The type of the file citation. Always file_citation.

file_id string - The ID of the file.

index int - The index of the file in the list of files.

filename string - The filename of the file cited.

openai.responses: FilePath

A path to a file.

Fields

'type "file_path" - The type of the file path. Always file_path.

file_id string - The ID of the file.

index int - The index of the file in the list of files.

openai.responses: FileSearchTool

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

Fields

'type "file_search" (default "file_search") - The type of the file search tool. Always file_search.

vector_store_ids string[] - The IDs of the vector stores to search.

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

ranking_options? RankingOptions -

filters? Filters - A filter to apply.

openai.responses: FileSearchToolCall

The results of a file search tool call. See the file search guide for more information.

Fields

id string - The unique ID of the file search tool call.

'type "file_search_call" - The type of the file search tool call. Always file_search_call.

status "in_progress"|"searching"|"completed"|"incomplete"|"failed" - The status of the file search tool call. One of in_progress, searching, incomplete or failed,

queries string[] - The queries used to search for files.

results? FileSearchToolCallResults[]? - The results of the file search tool call.

openai.responses: FileSearchToolCallResults

Fields

file_id? string - The unique ID of the file.

text? string - The text that was retrieved from the file.

filename? string - The name of the file.

attributes? VectorStoreFileAttributes? - 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.

score? float - The relevance score of the file - a value between 0 and 1.

openai.responses: FunctionCallOutputItemParam

The output of a function tool call.

Fields

id? string? - The unique ID of the function tool call output. Populated when this item is returned via API.

call_id string - The unique ID of the function tool call generated by the model.

'type "function_call_output" (default "function_call_output") - The type of the function tool call output. Always function_call_output.

output string|(InputTextContentParam|InputImageContentParamAutoParam|InputFileContentParam)[] - Text, image, or file output of the function tool call.

status? FunctionCallItemStatus - The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.

openai.responses: FunctionShellAction

Execute a shell command.

Fields

commands string[] -

timeout_ms int? - Optional timeout in milliseconds for the commands.

max_output_length int? - Optional maximum number of characters to return from each command.

openai.responses: FunctionShellActionParam

Commands and limits describing how to run the shell tool call.

Fields

commands string[] - Ordered shell commands for the execution environment to run.

timeout_ms? int? - Maximum wall-clock time in milliseconds to allow the shell commands to run.

max_output_length? int? - Maximum number of UTF-8 characters to capture from combined stdout and stderr output.

openai.responses: FunctionShellCall

A tool call that executes one or more shell commands in a managed environment.

Fields

'type "shell_call" (default "shell_call") - The type of the item. Always shell_call.

id string - The unique ID of the shell tool call. Populated when this item is returned via API.

call_id string - The unique ID of the shell tool call generated by the model.

action FunctionShellAction - Execute a shell command.

status FunctionShellCallStatus -

environment LocalEnvironmentResource|ContainerReferenceResource? -

created_by? string - The ID of the entity that created this tool call.

openai.responses: FunctionShellCallItemParam

A tool representing a request to execute one or more shell commands.

Fields

id? string? - The unique ID of the shell tool call. Populated when this item is returned via API.

call_id string - The unique ID of the shell tool call generated by the model.

'type "shell_call" (default "shell_call") - The type of the item. Always shell_call.

action FunctionShellActionParam - Commands and limits describing how to run the shell tool call.

status? FunctionShellCallItemStatus - The status of the shell call. One of in_progress, completed, or incomplete.

environment? LocalEnvironmentParam|ContainerReferenceParam? - The environment to execute the shell commands in.

openai.responses: FunctionShellCallOutput

The output of a shell tool call that was emitted.

Fields

'type "shell_call_output" (default "shell_call_output") - The type of the shell call output. Always shell_call_output.

id string - The unique ID of the shell call output. Populated when this item is returned via API.

call_id string - The unique ID of the shell tool call generated by the model.

status FunctionShellCallOutputStatusEnum -

output FunctionShellCallOutputContent[] - An array of shell call output contents

max_output_length int? - The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.

created_by? string - The identifier of the actor that created the item.

openai.responses: FunctionShellCallOutputContent

The content of a shell tool call output that was emitted.

Fields

stdout string - The standard output that was captured.

stderr string - The standard error output that was captured.

outcome FunctionShellCallOutputTimeoutOutcome|FunctionShellCallOutputExitOutcome - Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.

created_by? string - The identifier of the actor that created the item.

openai.responses: FunctionShellCallOutputContentParam

Captured stdout and stderr for a portion of a shell tool call output.

Fields

stdout string - Captured stdout output for the shell call.

stderr string - Captured stderr output for the shell call.

outcome FunctionShellCallOutputOutcomeParam - The exit or timeout outcome associated with this shell call.

openai.responses: FunctionShellCallOutputExitOutcome

Indicates that the shell commands finished and returned an exit code.

Fields

'type "exit" (default "exit") - The outcome type. Always exit.

exit_code int - Exit code from the shell process.

openai.responses: FunctionShellCallOutputExitOutcomeParam

Indicates that the shell commands finished and returned an exit code.

Fields

'type "exit" (default "exit") - The outcome type. Always exit.

exit_code int - The exit code returned by the shell process.

openai.responses: FunctionShellCallOutputItemParam

The streamed output items emitted by a shell tool call.

Fields

id? string? - The unique ID of the shell tool call output. Populated when this item is returned via API.

call_id string - The unique ID of the shell tool call generated by the model.

'type "shell_call_output" (default "shell_call_output") - The type of the item. Always shell_call_output.

output FunctionShellCallOutputContentParam[] - Captured chunks of stdout and stderr output, along with their associated outcomes.

status? FunctionShellCallItemStatus - The status of the shell call output.

max_output_length? int? - The maximum number of UTF-8 characters captured for this shell call's combined output.

openai.responses: FunctionShellCallOutputTimeoutOutcome

Indicates that the shell call exceeded its configured time limit.

Fields

'type "timeout" (default "timeout") - The outcome type. Always timeout.

openai.responses: FunctionShellCallOutputTimeoutOutcomeParam

Indicates that the shell call exceeded its configured time limit.

Fields

'type "timeout" (default "timeout") - The outcome type. Always timeout.

openai.responses: FunctionShellToolParam

A tool that allows the model to execute shell commands.

Fields

'type "shell" (default "shell") - The type of the shell tool. Always shell.

environment? ContainerAutoParam|LocalEnvironmentParam|ContainerReferenceParam? -

openai.responses: FunctionTool

Defines a function in your own code the model can choose to call. Learn more about function calling.

Fields

'type "function" (default "function") - The type of the function tool. Always function.

name string - The name of the function to call.

description? string? - A description of the function. Used by the model to determine whether or not to call the function.

parameters record {}? - A JSON schema object describing the parameters of the function.

strict boolean? - Whether to enforce strict parameter validation. Default true.

defer_loading? boolean - Whether this function is deferred and loaded via tool search.

openai.responses: FunctionToolCall

A tool call to run a function. See the function calling guide for more information.

Fields

id? string - The unique ID of the function tool call.

'type "function_call" - The type of the function tool call. Always function_call.

call_id string - The unique ID of the function tool call generated by the model.

namespace? string - The namespace of the function to run.

name string - The name of the function to run.

arguments string - A JSON string of the arguments to pass to the function.

status? "in_progress"|"completed"|"incomplete" - The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.

openai.responses: FunctionToolCallOutput

The output of a function tool call.

Fields

id? string - The unique ID of the function tool call output. Populated when this item is returned via API.

'type "function_call_output" - The type of the function tool call output. Always function_call_output.

call_id string - The unique ID of the function tool call generated by the model.

output string|FunctionAndCustomToolCallOutput[] - The output from the function call generated by your code. Can be a string or an list of output content.

status? "in_progress"|"completed"|"incomplete" - The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.

openai.responses: FunctionToolCallOutputResource

Fields

Fields Included from *FunctionToolCallOutput

id string
type "function_call_output"
call_id string
output string|FunctionAndCustomToolCallOutput[]
status "in_progress"|"completed"|"incomplete"
anydata...

id string - The unique ID of the function call tool output.

status FunctionCallOutputStatusEnum -

created_by? string - The identifier of the actor that created the item.

openai.responses: FunctionToolParam

Fields

name string -

description? string? -

parameters? EmptyModelParam -

strict? boolean? -

'type "function" (default "function") -

defer_loading? boolean - Whether this function should be deferred and discovered via tool search.

openai.responses: HybridSearchOptions

Fields

embedding_weight decimal - The weight of the embedding in the reciprocal ranking fusion.

text_weight decimal - The weight of the text in the reciprocal ranking fusion.

openai.responses: ImageGenTool

A tool that generates images using the GPT image models.

Fields

'type "image_generation" - The type of the image generation tool. Always image_generation.

model? string|"gpt-image-1"|"gpt-image-1-mini"|"gpt-image-1.5" -

quality "low"|"medium"|"high"|"auto" (default "auto") - The quality of the generated image. One of low, medium, high, or auto. Default: auto.

size string|"1024x1024"|"1024x1536"|"1536x1024"|"auto" (default "auto") - The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.

output_format "png"|"webp"|"jpeg" (default "png") - The output format of the generated image. One of png, webp, or jpeg. Default: png.

output_compression int(default 100) - Compression level for the output image. Default: 100.

moderation "auto"|"low" (default "auto") - Moderation level for the generated image. Default: auto.

background "transparent"|"opaque"|"auto" (default "auto") - Background type for the generated image. One of transparent, opaque, or auto. Default: auto.

input_fidelity? InputFidelity -

input_image_mask? ImageGenToolInputImageMask - Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).

partial_images int(default 0) - Number of partial images to generate in streaming mode, from 0 (default value) to 3.

action? ImageGenActionEnum -

openai.responses: ImageGenToolCall

An image generation request made by the model.

Fields

'type "image_generation_call" - The type of the image generation call. Always image_generation_call.

id string - The unique ID of the image generation call.

status "in_progress"|"completed"|"generating"|"failed" - The status of the image generation call.

result string? - The generated image encoded in base64.

openai.responses: ImageGenToolInputImageMask

Closed record

Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).

Fields

image_url? string - Base64-encoded mask image.

file_id? string - File ID for the mask image.

openai.responses: InlineSkillParam

Fields

'type "inline" (default "inline") - Defines an inline skill for this request.

name string - The name of the skill.

description string - The description of the skill.

'source InlineSkillSourceParam - Inline skill payload

openai.responses: InlineSkillSourceParam

Inline skill payload

Fields

'type "base64" (default "base64") - The type of the inline skill source. Must be base64.

media_type "application/zip" (default "application/zip") - The media type of the inline skill payload. Must be application/zip.

data string - Base64-encoded skill zip bundle.

openai.responses: InputFileContent

A file input to the model.

Fields

'type "input_file" (default "input_file") - The type of the input item. Always input_file.

file_id? string? - The ID of the file to be sent to the model.

filename? string - The name of the file to be sent to the model.

file_data? string - The content of the file to be sent to the model.

file_url? string - The URL of the file to be sent to the model.

detail? FileInputDetail -

openai.responses: InputFileContentParam

A file input to the model.

Fields

'type "input_file" (default "input_file") - The type of the input item. Always input_file.

file_id? string? - The ID of the file to be sent to the model.

filename? string? - The name of the file to be sent to the model.

file_data? string? - The base64-encoded data of the file to be sent to the model.

file_url? string? - The URL of the file to be sent to the model.

detail? FileDetailEnum -

openai.responses: InputImageContent

An image input to the model. Learn about image inputs.

Fields

'type "input_image" (default "input_image") - The type of the input item. Always input_image.

image_url? string? - The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.

file_id? string? - The ID of the file to be sent to the model.

detail? ImageDetail -

openai.responses: InputImageContentParamAutoParam

An image input to the model. Learn about image inputs

Fields

'type "input_image" (default "input_image") - The type of the input item. Always input_image.

image_url? string? - The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.

file_id? string? - The ID of the file to be sent to the model.

detail? DetailEnum - The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.

openai.responses: InputMessage

Fields

'type? "message" - The type of the message input. Always set to message.

role "user"|"system"|"developer" - The role of the message input. One of user, system, or developer.

status? "in_progress"|"completed"|"incomplete" - The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.

content InputMessageContentList - A list of one or many input items to the model, containing different content types.

openai.responses: InputTextContent

A text input to the model.

Fields

'type "input_text" (default "input_text") - The type of the input item. Always input_text.

text string - The text input to the model.

openai.responses: InputTextContentParam

A text input to the model.

Fields

'type "input_text" (default "input_text") - The type of the input item. Always input_text.

text string - The text input to the model.

openai.responses: ItemReferenceParam

An internal identifier for an item to reference.

Fields

'type "item_reference"?(default "item_reference") - The type of item to reference. Always item_reference.

id string - The ID of the item to reference.

openai.responses: KeyPressAction

A collection of keypresses the model would like to perform.

Fields

'type "keypress" (default "keypress") - Specifies the event type. For a keypress action, this property is always set to keypress.

keys string[] - The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.

openai.responses: LocalEnvironmentParam

Fields

'type "local" (default "local") - Use a local computer environment.

skills? LocalSkillParam[] - An optional list of skills.

openai.responses: LocalEnvironmentResource

Represents the use of a local environment to perform shell actions.

Fields

'type "local" (default "local") - The environment type. Always local.

openai.responses: LocalShellExecAction

Execute a shell command on the server.

Fields

'type "exec" (default "exec") - The type of the local shell action. Always exec.

command string[] - The command to run.

timeout_ms? int? - Optional timeout in milliseconds for the command.

working_directory? string? - Optional working directory to run the command in.

env record { string... } - Environment variables to set for the command.

user? string? - Optional user to run the command as.

openai.responses: LocalShellToolCall

A tool call to run a command on the local shell.

Fields

'type "local_shell_call" - The type of the local shell call. Always local_shell_call.

id string - The unique ID of the local shell call.

call_id string - The unique ID of the local shell tool call generated by the model.

action LocalShellExecAction - Execute a shell command on the server.

status "in_progress"|"completed"|"incomplete" - The status of the local shell call.

openai.responses: LocalShellToolCallOutput

The output of a local shell tool call.

Fields

'type "local_shell_call_output" - The type of the local shell tool call output. Always local_shell_call_output.

id string - The unique ID of the local shell tool call generated by the model.

output string - A JSON string of the output of the local shell tool call.

status? "in_progress"|"completed"|"incomplete"? - The status of the item. One of in_progress, completed, or incomplete.

openai.responses: LocalShellToolParam

A tool that allows the model to execute shell commands in a local environment.

Fields

'type "local_shell" (default "local_shell") - The type of the local shell tool. Always local_shell.

openai.responses: LocalSkillParam

Fields

name string - The name of the skill.

description string - The description of the skill.

path string - The path to the directory containing the skill.

openai.responses: LogProb

The log probability of a token.

Fields

token string -

logprob decimal -

bytes int[] -

top_logprobs TopLogProb[] -

openai.responses: MCPApprovalRequest

A request for human approval of a tool invocation.

Fields

'type "mcp_approval_request" - The type of the item. Always mcp_approval_request.

id string - The unique ID of the approval request.

server_label string - The label of the MCP server making the request.

name string - The name of the tool to run.

arguments string - A JSON string of arguments for the tool.

openai.responses: MCPApprovalResponse

A response to an MCP approval request.

Fields

'type "mcp_approval_response" - The type of the item. Always mcp_approval_response.

id? string? - The unique ID of the approval response

approval_request_id string - The ID of the approval request being answered.

approve boolean - Whether the request was approved.

reason? string? - Optional reason for the decision.

openai.responses: MCPApprovalResponseResource

A response to an MCP approval request.

Fields

'type "mcp_approval_response" - The type of the item. Always mcp_approval_response.

id string - The unique ID of the approval response

approval_request_id string - The ID of the approval request being answered.

approve boolean - Whether the request was approved.

reason? string? - Optional reason for the decision.

openai.responses: MCPListTools

A list of tools available on an MCP server.

Fields

'type "mcp_list_tools" - The type of the item. Always mcp_list_tools.

id string - The unique ID of the list.

server_label string - The label of the MCP server.

tools MCPListToolsTool[] - The tools available on the server.

'error? string? - Error message if the server could not list tools.

openai.responses: MCPListToolsTool

A tool available on an MCP server.

Fields

name string - The name of the tool.

description? string? - The description of the tool.

input_schema record {} - The JSON schema describing the tool's input.

annotations? record {}? - Additional annotations about the tool.

openai.responses: MCPTool

Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.

Fields

'type "mcp" - The type of the MCP tool. Always mcp.

server_label string - A label for this MCP server, used to identify it in tool calls.

server_url? string - The URL for the MCP server. One of server_url or connector_id must be provided.

connector_id? "connector_dropbox"|"connector_gmail"|"connector_googlecalendar"|"connector_googledrive"|"connector_microsoftteams"|"connector_outlookcalendar"|"connector_outlookemail"|"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

authorization? string - 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.

server_description? string - Optional description of the MCP server, used to provide more context.

headers? record { string... }? - Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.

allowed_tools? string[]|MCPToolFilter? - List of allowed tool names or a filter object.

require_approval record {| always MCPToolFilter, 'never MCPToolFilter |}|"always"|"never"?(default "always") - Specify which of the MCP server's tools require approval.

defer_loading? boolean - Whether this MCP tool is deferred and discovered via tool search.

openai.responses: MCPToolCall

An invocation of a tool on an MCP server.

Fields

'type "mcp_call" - The type of the item. Always mcp_call.

id string - The unique ID of the tool call.

server_label string - The label of the MCP server running the tool.

name string - The name of the tool that was run.

arguments string - A JSON string of the arguments passed to the tool.

output? string? - The output from the tool call.

'error? string? - The error from the tool call, if any.

status? MCPToolCallStatus -

approval_request_id? string? - 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.

openai.responses: MCPToolFilter

Closed record

A filter object to specify which tools are allowed.

Fields

tool_names? string[] - List of allowed tool names.

read_only? boolean - 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.

openai.responses: Metadata

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

Fields

string... - Rest field

openai.responses: ModelResponseProperties

Fields

metadata? Metadata? - Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

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

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

top_p? decimal? - 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.

user? string - This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.

safety_identifier? string - A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.

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

service_tier? ServiceTier? - 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.

prompt_cache_retention? "in_memory"|"24h"? - 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.

openai.responses: MoveParam

A mouse move action.

Fields

'type "move" (default "move") - Specifies the event type. For a move action, this property is always set to move.

x int - The x-coordinate to move to.

y int - The y-coordinate to move to.

keys? string[]? - The keys being held while moving the mouse.

openai.responses: NamespaceToolParam

Groups function/custom tools under a shared namespace.

Fields

'type "namespace" (default "namespace") - The type of the tool. Always namespace.

name string - The namespace name used in tool calls (for example, crm).

description string - A description of the namespace shown to the model.

tools (FunctionToolParam|CustomToolParam)[] - The function/custom tools available inside this namespace.

openai.responses: OutputMessage

An output message from the model.

Fields

id string - The unique ID of the output message.

'type "message" - The type of the output message. Always message.

role "assistant" - The role of the output message. Always assistant.

content OutputMessageContent[] - The content of the output message.

phase? MessagePhase -

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

openai.responses: OutputTextContent

A text output from the model.

Fields

'type "output_text" (default "output_text") - The type of the output text. Always output_text.

text string - The text output from the model.

annotations Annotation[] - The annotations of the text output.

logprobs? LogProb[] -

openai.responses: Prompt

Reference to a prompt template and its variables. Learn more.

Fields

id string - The unique identifier of the prompt template to use.

version? string? - Optional version of the prompt template.

variables? ResponsePromptVariables? - 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.

openai.responses: RankingOptions

Fields

ranker? RankerVersionType -

score_threshold? decimal - 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.

hybrid_search? HybridSearchOptions -

openai.responses: Reasoning

gpt-5 and o-series models only

Configuration options for reasoning models.

Fields

effort? ReasoningEffort? - 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.

summary? "auto"|"concise"|"detailed"? - 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.

generate_summary? "auto"|"concise"|"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.

openai.responses: ReasoningItem

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.

Fields

'type "reasoning" - The type of the object. Always reasoning.

id string - The unique identifier of the reasoning content.

encrypted_content? string? - The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.

summary SummaryTextContent[] - Reasoning summary content.

content? ReasoningTextContent[] - Reasoning text content.

status? "in_progress"|"completed"|"incomplete" - The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.

openai.responses: ReasoningTextContent

Reasoning text from the model.

Fields

'type "reasoning_text" (default "reasoning_text") - The type of the reasoning text. Always reasoning_text.

text string - The reasoning text from the model.

openai.responses: RefusalContent

A refusal from the model.

Fields

'type "refusal" (default "refusal") - The type of the refusal. Always refusal.

refusal string - The refusal explanation from the model.

openai.responses: Response

Fields

Fields Included from *ModelResponseProperties

metadata Metadata|()
top_logprobs int|()
temperature decimal|()
top_p decimal|()
user string
safety_identifier string
prompt_cache_key string
service_tier "priority"|()|"auto"|"default"|"flex"|"scale"
prompt_cache_retention "24h"|()|"in_memory"
anydata...

Fields Included from *ResponseProperties

previous_response_id string|()
model ModelIdsResponses
reasoning Reasoning
background boolean|()
max_tool_calls int|()
text ResponseTextParam
tools ToolsArray
tool_choice ToolChoiceParam
prompt Prompt|()
truncation "disabled"|()|"auto"
anydata...

id string - Unique identifier for this Response.

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

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

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

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

'error ResponseError? - An error object returned when the model fails to generate a Response.

incomplete_details ResponseIncompleteDetails? - Details about why the response is incomplete.

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

instructions string|InputItem[]? - A system (or developer) message inserted into the model's context. When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.

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

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

parallel_tool_calls boolean(default true) - Whether to allow the model to run tool calls in parallel.

conversation? Conversation2 -

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

metadata Metadata? - Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

model ModelIdsResponses -

temperature decimal?(default 1) - 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.

tool_choice ToolChoiceParam - 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.

tools ToolsArray - 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.

top_p decimal?(default 1) - 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.

openai.responses: ResponseError

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

Fields

code ResponseErrorCode - The error code for the response.

message string - A human-readable description of the error.

openai.responses: 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.

Fields

'type "json_object" - The type of response format being defined. Always json_object.

openai.responses: ResponseFormatJsonSchemaSchema

The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

openai.responses: ResponseFormatText

Default response format. Used to generate text responses.

Fields

'type "text" - The type of response format being defined. Always text.

openai.responses: ResponseIncompleteDetails

Details about why the response is incomplete.

Fields

reason? "max_output_tokens"|"content_filter" - The reason why the response is incomplete.

openai.responses: ResponsePromptVariables

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.

openai.responses: ResponseProperties

Fields

previous_response_id? string? - 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.

model? ModelIdsResponses -

reasoning? Reasoning -

background? boolean? - Whether to run the model response in the background. Learn more.

max_tool_calls? int? - 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.

text? ResponseTextParam - Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
- Text inputs and outputs
- Structured Outputs

tools? ToolsArray - 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.

tool_choice? ToolChoiceParam - 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.

prompt? Prompt? - Reference to a prompt template and its variables. Learn more.

truncation? "auto"|"disabled"? - 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.

openai.responses: ResponseStreamOptions

Options for streaming responses. Only set this when you set stream: true.

Fields

include_obfuscation? boolean - 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.

openai.responses: ResponseTextParam

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

Fields

format? TextResponseFormatConfiguration - 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.

verbosity? Verbosity? - 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.

openai.responses: ResponseUsage

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

Fields

input_tokens int - The number of input tokens.

input_tokens_details ResponseUsageInputTokensDetails - A detailed breakdown of the input tokens.

output_tokens int - The number of output tokens.

output_tokens_details ResponseUsageOutputTokensDetails - A detailed breakdown of the output tokens.

total_tokens int - The total number of tokens used.

openai.responses: ResponseUsageInputTokensDetails

A detailed breakdown of the input tokens.

Fields

cached_tokens int - The number of tokens that were retrieved from the cache. More on prompt caching.

openai.responses: ResponseUsageOutputTokensDetails

A detailed breakdown of the output tokens.

Fields

reasoning_tokens int - The number of reasoning tokens.

openai.responses: ScreenshotParam

A screenshot action.

Fields

'type "screenshot" (default "screenshot") - Specifies the event type. For a screenshot action, this property is always set to screenshot.

openai.responses: ScrollParam

A scroll action.

Fields

'type "scroll" (default "scroll") - Specifies the event type. For a scroll action, this property is always set to scroll.

x int - The x-coordinate where the scroll occurred.

y int - The y-coordinate where the scroll occurred.

scroll_x int - The horizontal scroll distance.

scroll_y int - The vertical scroll distance.

keys? string[]? - The keys being held while scrolling.

openai.responses: SkillReferenceParam

Fields

'type "skill_reference" (default "skill_reference") - References a skill created with the /v1/skills endpoint.

skill_id string - The ID of the referenced skill.

version? string - Optional skill version. Use a positive integer or 'latest'. Omit for default.

openai.responses: SpecificApplyPatchParam

Forces the model to call the apply_patch tool when executing a tool call.

Fields

'type "apply_patch" (default "apply_patch") - The tool to call. Always apply_patch.

openai.responses: SpecificFunctionShellParam

Forces the model to call the shell tool when a tool call is required.

Fields

'type "shell" (default "shell") - The tool to call. Always shell.

openai.responses: SummaryTextContent

A summary text from the model.

Fields

'type "summary_text" (default "summary_text") - The type of the object. Always summary_text.

text string - A summary of the reasoning output from the model so far.

openai.responses: TextResponseFormatJsonSchema

JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

Fields

'type "json_schema" - The type of response format being defined. Always json_schema.

description? string - A description of what the response format is for, used by the model to determine how to respond in the format.

name string - 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.

schema ResponseFormatJsonSchemaSchema - The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

strict? boolean? - 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.

openai.responses: ToolChoiceAllowed

Constrains the tools available to the model to a pre-defined set.

Fields

'type "allowed_tools" - Allowed tool configuration type. Always allowed_tools.

mode "auto"|"required" - 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.

tools record {}[] - 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" }
]
```

openai.responses: ToolChoiceCustom

Use this option to force the model to call a specific custom tool.

Fields

'type "custom" - For custom tool calling, the type is always custom.

name string - The name of the custom tool to call.

openai.responses: ToolChoiceFunction

Use this option to force the model to call a specific function.

Fields

'type "function" - For function calling, the type is always function.

name string - The name of the function to call.

openai.responses: ToolChoiceMCP

Use this option to force the model to call a specific tool on a remote MCP server.

Fields

'type "mcp" - For MCP tools, the type is always mcp.

server_label string - The label of the MCP server to use.

name? string? - The name of the tool to call on the server.

openai.responses: ToolChoiceTypes

Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.

Fields

'type "file_search"|"web_search_preview"|"computer"|"computer_use_preview"|"computer_use"|"web_search_preview_2025_03_11"|"image_generation"|"code_interpreter" - The type of hosted tool the model should to use. Learn more about built-in tools. Allowed values are:
- file_search
- web_search_preview
- computer
- computer_use_preview
- computer_use
- code_interpreter
- image_generation

openai.responses: ToolSearchCall

Fields

'type "tool_search_call" (default "tool_search_call") - The type of the item. Always tool_search_call.

id string - The unique ID of the tool search call item.

call_id string? - The unique ID of the tool search call generated by the model.

execution ToolSearchExecutionType -

arguments anydata - Arguments used for the tool search call.

status FunctionCallStatus -

created_by? string - The identifier of the actor that created the item.

openai.responses: ToolSearchCallItemParam

Fields

id? string? - The unique ID of this tool search call.

call_id? string? - The unique ID of the tool search call generated by the model.

'type "tool_search_call" (default "tool_search_call") - The item type. Always tool_search_call.

execution? ToolSearchExecutionType -

arguments EmptyModelParam -

status? FunctionCallItemStatus - The status of the tool search call.

openai.responses: ToolSearchOutput

Fields

'type "tool_search_output" (default "tool_search_output") - The type of the item. Always tool_search_output.

id string - The unique ID of the tool search output item.

call_id string? - The unique ID of the tool search call generated by the model.

execution ToolSearchExecutionType -

tools Tool[] - The loaded tool definitions returned by tool search.

status FunctionCallOutputStatusEnum -

created_by? string - The identifier of the actor that created the item.

openai.responses: ToolSearchOutputItemParam

Fields

id? string? - The unique ID of this tool search output.

call_id? string? - The unique ID of the tool search call generated by the model.

'type "tool_search_output" (default "tool_search_output") - The item type. Always tool_search_output.

execution? ToolSearchExecutionType -

tools Tool[] - The loaded tool definitions returned by the tool search output.

status? FunctionCallItemStatus - The status of the tool search output.

openai.responses: ToolSearchToolParam

Hosted or BYOT tool search configuration for deferred tools.

Fields

'type "tool_search" (default "tool_search") - The type of the tool. Always tool_search.

execution? ToolSearchExecutionType -

description? string? - Description shown to the model for a client-executed tool search tool.

parameters? EmptyModelParam - Parameter schema for a client-executed tool search tool.

openai.responses: TopLogProb

The top log probability of a token.

Fields

token string -

logprob decimal -

bytes int[] -

openai.responses: TypeParam

An action to type in text.

Fields

'type "type" (default "type") - Specifies the event type. For a type action, this property is always set to type.

text string - The text to type.

openai.responses: UrlCitationBody

A citation for a web resource used to generate a model response.

Fields

'type "url_citation" (default "url_citation") - The type of the URL citation. Always url_citation.

url string - The URL of the web resource.

start_index int - The index of the first character of the URL citation in the message.

end_index int - The index of the last character of the URL citation in the message.

title string - The title of the web resource.

openai.responses: VectorStoreFileAttributes

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.

openai.responses: WaitParam

A wait action.

Fields

'type "wait" (default "wait") - Specifies the event type. For a wait action, this property is always set to wait.

openai.responses: WebSearchActionFind

Action type "find_in_page": Searches for a pattern within a loaded page.

Fields

'type "find_in_page" - The action type.

url string - The URL of the page searched for the pattern.

pattern string - The pattern or text to search for within the page.

openai.responses: WebSearchActionOpenPage

Action type "open_page" - Opens a specific URL from search results.

Fields

'type "open_page" - The action type.

url? string? - The URL opened by the model.

openai.responses: WebSearchActionSearch

Action type "search" - Performs a web search query.

Fields

'type "search" - The action type.

query string - [DEPRECATED] The search query.

queries? string[] - The search queries.

sources? WebSearchSource[] - The sources used in the search.

openai.responses: WebSearchApproximateLocation

The approximate location of the user.

Fields

'type "approximate" (default "approximate") - The type of location approximation. Always approximate.

country? string? - The two-letter ISO country code of the user, e.g. US.

region? string? - Free text input for the region of the user, e.g. California.

city? string? - Free text input for the city of the user, e.g. San Francisco.

timezone? string? - The IANA timezone of the user, e.g. America/Los_Angeles.

openai.responses: WebSearchPreviewTool

This tool searches the web for relevant results to use in a response. Learn more about the web search tool.

Fields

'type "web_search_preview"|"web_search_preview_2025_03_11" (default "web_search_preview") - The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.

user_location? ApproximateLocation - The user's location.

search_context_size? SearchContextSize -

search_content_types? SearchContentType[] -

openai.responses: WebSearchSource

A source used in the search.

Fields

'type "url" - The type of source. Always url.

url string - The URL of the source.

openai.responses: WebSearchTool

Search the Internet for sources related to the prompt. Learn more about the web search tool.

Fields

'type "web_search"|"web_search_2025_08_26" (default "web_search") - The type of the web search tool. One of web_search or web_search_2025_08_26.

filters? WebSearchToolFilters? - Filters for the search.

user_location? WebSearchApproximateLocation? - The approximate location of the user.

search_context_size "low"|"medium"|"high" (default "medium") - 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.

openai.responses: WebSearchToolCall

The results of a web search tool call. See the web search guide for more information.

Fields

id string - The unique ID of the web search tool call.

'type "web_search_call" - The type of the web search tool call. Always web_search_call.

status "in_progress"|"searching"|"completed"|"failed" - The status of the web search tool call.

action WebSearchActionSearch|WebSearchActionOpenPage|WebSearchActionFind - 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).

openai.responses: WebSearchToolFilters

Filters for the search.

Fields

allowed_domains string[]?(default []) - 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"]

Union types

openai.responses: ComputerEnvironment

"windows"|"mac"|"linux"|"ubuntu"|"browser"

ComputerEnvironment

openai.responses: FunctionCallStatus

"in_progress"|"completed"|"incomplete"

FunctionCallStatus

openai.responses: DetailEnum

"low"|"high"|"auto"|"original"

DetailEnum

openai.responses: InputContent

InputTextContent|InputImageContent|InputFileContent

InputContent

openai.responses: ClickButtonType

"left"|"right"|"wheel"|"back"|"forward"

ClickButtonType

openai.responses: ApplyPatchCallStatusParam

"in_progress"|"completed"

ApplyPatchCallStatusParam

Status values reported for apply_patch tool calls.

openai.responses: FunctionCallOutputStatusEnum

"in_progress"|"completed"|"incomplete"

FunctionCallOutputStatusEnum

openai.responses: ContainerMemoryLimit

"1g"|"4g"|"16g"|"64g"

ContainerMemoryLimit

openai.responses: ApplyPatchCallStatus

"in_progress"|"completed"

ApplyPatchCallStatus

openai.responses: GrammarSyntax1

"lark"|"regex"

GrammarSyntax1

openai.responses: ToolSearchExecutionType

"server"|"client"

ToolSearchExecutionType

openai.responses: IncludeEnum

IncludeEnum

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

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

openai.responses: ComputerCallOutputStatus

"completed"|"incomplete"|"failed"

ComputerCallOutputStatus

openai.responses: FileInputDetail

"low"|"high"

FileInputDetail

openai.responses: ApplyPatchCallOutputStatusParam

"completed"|"failed"

ApplyPatchCallOutputStatusParam

Outcome values reported for apply_patch tool call outputs.

openai.responses: ServiceTier

"auto"|"default"|"flex"|"scale"|"priority"?

ServiceTier

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.

openai.responses: Verbosity

"low"|"medium"|"high"?

Verbosity

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.

openai.responses: ApplyPatchCallOutputStatus

"completed"|"failed"

ApplyPatchCallOutputStatus

openai.responses: ImageGenActionEnum

"generate"|"edit"|"auto"

ImageGenActionEnum

openai.responses: OutputMessageContent

OutputTextContent|RefusalContent

OutputMessageContent

openai.responses: ToolChoiceOptions

"none"|"auto"|"required"

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.

openai.responses: ConversationParam

string|ConversationParam2

ConversationParam

The conversation that this response belongs to. Items from this conversation are prepended to input_items for this response request. Input items and output items from this response are automatically added to this conversation after this response completes.

openai.responses: FunctionCallItemStatus

"in_progress"|"completed"|"incomplete"

FunctionCallItemStatus

openai.responses: FunctionShellCallItemStatus

"in_progress"|"completed"|"incomplete"

FunctionShellCallItemStatus

Status values reported for shell tool calls.

openai.responses: TextResponseFormatConfiguration

ResponseFormatText|TextResponseFormatJsonSchema|ResponseFormatJsonObject

TextResponseFormatConfiguration

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.

openai.responses: InputItem

EasyInputMessage|Item|ItemReferenceParam

InputItem

openai.responses: ApplyPatchOperationParam

ApplyPatchCreateFileOperationParam|ApplyPatchDeleteFileOperationParam|ApplyPatchUpdateFileOperationParam

ApplyPatchOperationParam

One of the create_file, delete_file, or update_file operations supplied to the apply_patch tool.

openai.responses: ToolChoiceParam

ToolChoiceParam

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.

openai.responses: FunctionShellCallOutputStatusEnum

"in_progress"|"completed"|"incomplete"

FunctionShellCallOutputStatusEnum

openai.responses: FunctionShellCallStatus

"in_progress"|"completed"|"incomplete"

FunctionShellCallStatus

openai.responses: FileDetailEnum

"low"|"high"

FileDetailEnum

openai.responses: ComputerAction

ComputerAction

openai.responses: ModelIdsResponses

ModelIdsResponses

openai.responses: FunctionShellCallOutputOutcomeParam

FunctionShellCallOutputTimeoutOutcomeParam|FunctionShellCallOutputExitOutcomeParam

FunctionShellCallOutputOutcomeParam

The exit or timeout outcome associated with this shell call.

openai.responses: Annotation

FileCitationBody|UrlCitationBody|ContainerFileCitationBody|FilePath

Annotation

An annotation that applies to a span of output text.

openai.responses: ReasoningEffort

ReasoningEffort

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.

openai.responses: RankerVersionType

"auto"|"default-2024-11-15"

RankerVersionType

openai.responses: Filters

ComparisonFilter|CompoundFilter

Filters

openai.responses: MessagePhase

"commentary"|"final_answer"

MessagePhase

Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.

openai.responses: Tool

Tool

A tool that can be used to generate a response.

openai.responses: InputParam

string|InputItem[]

InputParam

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

Learn more:

openai.responses: MCPToolCallStatus

"in_progress"|"completed"|"incomplete"|"calling"|"failed"

MCPToolCallStatus

openai.responses: InputFidelity

"high"|"low"

InputFidelity

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.

openai.responses: ModelIdsShared

ModelIdsShared

openai.responses: ImageDetail

"low"|"high"|"auto"|"original"

ImageDetail

openai.responses: ResponseErrorCode

ResponseErrorCode

The error code for the response.

openai.responses: SearchContextSize

"low"|"medium"|"high"

SearchContextSize

openai.responses: FunctionAndCustomToolCallOutput

InputTextContent|InputImageContent|InputFileContent

FunctionAndCustomToolCallOutput

openai.responses: SearchContentType

"text"|"image"

SearchContentType

Array types

openai.responses: ToolsArray

Tool[]

ToolsArray

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.

openai.responses: ComputerActionList

ComputerAction[]

ComputerActionList

Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.

openai.responses: InputMessageContentList

InputContent[]

InputMessageContentList

A list of one or many input items to the model, containing different content types.

Import

import ballerinax/openai.responses;

Other versions

1.0.0

Metadata

Released date: about 13 hours ago

Version: 1.0.0

License: Apache-2.0

Compatibility

Platform: any

Ballerina version: 2201.12.0

GraalVM compatible: Yes

Pull count

Total: 6

Current verison: 6

Weekly downloads

Source repository

Keywords

AI/Chat

OpenAI

Cost/Paid

GPT-4

ChatGPT

Vendor/OpenAI

Contributors

Dependencies

ballerina/constraint/1.7.0 ballerina/os/1.10.1 ballerina/log/2.14.0

Dependents

orgsd/ai.openai/1.4.0

Cookie policy

Delete policy

clients

records

unionTypes

arrayTypes

ballerinax/openai.responses Ballerina library

Overview

Setup guide

Create an OpenAI API Key

Quickstart

Step 1: Import the module

Step 2: Create a new connector instance

Step 3: Invoke the connector operation

Create a model response

Step 4: Run the Ballerina application

Examples

Clients

openai.responses: Client

Constructor

post responses

Parameters

Return Type

Records

openai.responses: ApplyPatchCreateFileOperation

Fields

openai.responses: ApplyPatchCreateFileOperationParam

Fields

openai.responses: ApplyPatchDeleteFileOperation

Fields

openai.responses: ApplyPatchDeleteFileOperationParam

Fields

openai.responses: ApplyPatchToolCall

Fields

openai.responses: ApplyPatchToolCallItemParam

Fields

openai.responses: ApplyPatchToolCallOutput

Fields

openai.responses: ApplyPatchToolCallOutputItemParam

Fields

openai.responses: ApplyPatchToolParam

Fields

openai.responses: ApplyPatchUpdateFileOperation

Fields

openai.responses: ApplyPatchUpdateFileOperationParam

Fields

openai.responses: ApproximateLocation

Fields

openai.responses: AutoCodeInterpreterToolParam

Fields

openai.responses: ClickParam

Fields

openai.responses: CodeInterpreterOutputImage

Fields

openai.responses: CodeInterpreterOutputLogs

Fields

openai.responses: CodeInterpreterTool

Fields

openai.responses: CodeInterpreterToolCall

Fields

openai.responses: CompactionBody

Fields

openai.responses: CompactionSummaryItemParam

Fields

openai.responses: ComparisonFilter

Fields

openai.responses: CompoundFilter

Fields

openai.responses: ComputerCallOutputItemParam

Fields

openai.responses: ComputerCallSafetyCheckParam

Fields

openai.responses: ComputerScreenshotImage

Fields

openai.responses: ComputerTool

Fields

openai.responses: ComputerToolCall

Fields

openai.responses: ComputerToolCallOutput

Fields

openai.responses: ComputerToolCallOutputResource

Fields