# Responses ## Run OpenAI Responses API (OpenAI only) `client.responses.create(ResponseCreateParamsbody, RequestOptionsoptions?): ResponseCreateResponse` **post** `/v5/responses` Runs inference using the OpenAI Responses API contract, taking an `input` rather than a chat `messages` array. This endpoint is restricted to OpenAI-vendor models: requests whose `model` (`vendor/name`) resolves to any other vendor are rejected with an unsupported-vendor error, unlike /v5/chat/completions and /v5/inference which support many vendors. Use it when you specifically need Responses API features such as `previous_response_id` chaining, `instructions`, or `store`; use /v5/chat/completions for the standard messages-based chat contract. When `stream` is set the response streams as server-sent events; otherwise a single `response` object is returned. ### Parameters - `body: ResponseCreateParams` - `input: string | Array` - `string` - `Array` - `EasyInputMessageParam` A message input to the model with a role indicating instruction following hierarchy. Instructions given with the `developer` or `system` role take precedence over instructions given with the `user` role. Messages with the `assistant` role are presumed to have been generated by the model in previous interactions. - `content: string | Array` - `string` - `Array` - `OpenAIResponseInputTextParam` A text input to the model. - `text: string` - `type: "input_text"` - `"input_text"` - `OpenAIResponseInputImageParam` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `detail: "low" | "high" | "auto"` - `"low"` - `"high"` - `"auto"` - `type: "input_image"` - `"input_image"` - `file_id?: string` - `image_url?: string` - `OpenAIResponseInputFileParam` A file input to the model. - `type: "input_file"` - `"input_file"` - `file_data?: string` - `file_id?: string` - `file_url?: string` - `filename?: string` - `role: "user" | "assistant" | "system" | "developer"` - `"user"` - `"assistant"` - `"system"` - `"developer"` - `phase?: "commentary" | "final_answer"` - `"commentary"` - `"final_answer"` - `type?: "message"` - `"message"` - `OpenAITypesResponsesResponseInputParamMessage` 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. - `content: Array` - `OpenAIResponseInputTextParam` A text input to the model. - `OpenAIResponseInputImageParam` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `OpenAIResponseInputFileParam` A file input to the model. - `role: "user" | "system" | "developer"` - `"user"` - `"system"` - `"developer"` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type?: "message"` - `"message"` - `ResponseOutputMessageParam` An output message from the model. - `id: string` - `content: Array` - `ResponseOutputTextParam` A text output from the model. - `annotations: Array` - `AnnotationFileCitation` A citation to a file. - `file_id: string` - `filename: string` - `index: number` - `type: "file_citation"` - `"file_citation"` - `OpenAITypesResponsesResponseOutputTextParamAnnotationURLCitation` A citation for a web resource used to generate a model response. - `end_index: number` - `start_index: number` - `title: string` - `type: "url_citation"` - `"url_citation"` - `url: string` - `AnnotationContainerFileCitation` A citation for a container file used to generate a model response. - `container_id: string` - `end_index: number` - `file_id: string` - `filename: string` - `start_index: number` - `type: "container_file_citation"` - `"container_file_citation"` - `AnnotationFilePath` A path to a file. - `file_id: string` - `index: number` - `type: "file_path"` - `"file_path"` - `text: string` - `type: "output_text"` - `"output_text"` - `logprobs?: Array` - `token: string` - `bytes: Array` - `logprob: number` - `top_logprobs: Array` - `token: string` - `bytes: Array` - `logprob: number` - `ResponseOutputRefusalParam` A refusal from the model. - `refusal: string` - `type: "refusal"` - `"refusal"` - `role: "assistant"` - `"assistant"` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "message"` - `"message"` - `phase?: "commentary" | "final_answer"` - `"commentary"` - `"final_answer"` - `ResponseFileSearchToolCallParam` The results of a file search tool call. See the [file search guide](https://platform.openai.com/docs/guides/tools-file-search) for more information. - `id: string` - `queries: Array` - `status: "in_progress" | "searching" | "completed" | 2 more` - `"in_progress"` - `"searching"` - `"completed"` - `"incomplete"` - `"failed"` - `type: "file_search_call"` - `"file_search_call"` - `results?: Array` - `attributes?: Record` - `string` - `number` - `boolean` - `file_id?: string` - `filename?: string` - `score?: number` - `text?: string` - `ResponseComputerToolCallParam` A tool call to a computer use tool. See the [computer use guide](https://platform.openai.com/docs/guides/tools-computer-use) for more information. - `id: string` - `action: ActionClick | ActionDoubleClick | ActionDrag | 6 more` A click action. - `ActionClick` A click action. - `button: "left" | "right" | "wheel" | 2 more` - `"left"` - `"right"` - `"wheel"` - `"back"` - `"forward"` - `type: "click"` - `"click"` - `x: number` - `y: number` - `ActionDoubleClick` A double click action. - `type: "double_click"` - `"double_click"` - `x: number` - `y: number` - `ActionDrag` A drag action. - `path: Array` - `x: number` - `y: number` - `type: "drag"` - `"drag"` - `ActionKeypress` A collection of keypresses the model would like to perform. - `keys: Array` - `type: "keypress"` - `"keypress"` - `ActionMove` A mouse move action. - `type: "move"` - `"move"` - `x: number` - `y: number` - `ActionScreenshot` A screenshot action. - `type: "screenshot"` - `"screenshot"` - `ActionScroll` A scroll action. - `scroll_x: number` - `scroll_y: number` - `type: "scroll"` - `"scroll"` - `x: number` - `y: number` - `ActionType` An action to type in text. - `text: string` - `type: "type"` - `"type"` - `ActionWait` A wait action. - `type: "wait"` - `"wait"` - `call_id: string` - `pending_safety_checks: Array` - `id: string` - `code?: string` - `message?: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "computer_call"` - `"computer_call"` - `OpenAITypesResponsesResponseInputParamComputerCallOutput` The output of a computer tool call. - `call_id: string` - `output: Output` A computer screenshot image used with the computer use tool. - `type: "computer_screenshot"` - `"computer_screenshot"` - `file_id?: string` - `image_url?: string` - `type: "computer_call_output"` - `"computer_call_output"` - `id?: string` - `acknowledged_safety_checks?: Array` - `id: string` - `code?: string` - `message?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `ResponseFunctionWebSearchParam` The results of a web search tool call. See the [web search guide](https://platform.openai.com/docs/guides/tools-web-search) for more information. - `id: string` - `action: OpenAITypesResponsesResponseFunctionWebSearchParamActionSearch | OpenAITypesResponsesResponseFunctionWebSearchParamActionOpenPage | ActionFind` Action type "search" - Performs a web search query. - `OpenAITypesResponsesResponseFunctionWebSearchParamActionSearch` Action type "search" - Performs a web search query. - `query: string` - `type: "search"` - `"search"` - `queries?: Array` - `sources?: Array` - `type: "url"` - `"url"` - `url: string` - `OpenAITypesResponsesResponseFunctionWebSearchParamActionOpenPage` Action type "open_page" - Opens a specific URL from search results. - `type: "open_page"` - `"open_page"` - `url?: string` - `ActionFind` Action type "find_in_page": Searches for a pattern within a loaded page. - `pattern: string` - `type: "find_in_page"` - `"find_in_page"` - `url: string` - `status: "in_progress" | "searching" | "completed" | "failed"` - `"in_progress"` - `"searching"` - `"completed"` - `"failed"` - `type: "web_search_call"` - `"web_search_call"` - `ResponseFunctionToolCallParam` A tool call to run a function. See the [function calling guide](https://platform.openai.com/docs/guides/function-calling) for more information. - `arguments: string` - `call_id: string` - `name: string` - `type: "function_call"` - `"function_call"` - `id?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `OpenAITypesResponsesResponseInputParamFunctionCallOutput` The output of a function tool call. - `call_id: string` - `output: string | Array` - `string` - `Array` - `ResponseInputTextContentParam` A text input to the model. - `text: string` - `type: "input_text"` - `"input_text"` - `ResponseInputImageContentParam` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision) - `type: "input_image"` - `"input_image"` - `detail?: "low" | "high" | "auto"` - `"low"` - `"high"` - `"auto"` - `file_id?: string` - `image_url?: string` - `ResponseInputFileContentParam` A file input to the model. - `type: "input_file"` - `"input_file"` - `file_data?: string` - `file_id?: string` - `file_url?: string` - `filename?: string` - `type: "function_call_output"` - `"function_call_output"` - `id?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `ResponseReasoningItemParam` 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](https://platform.openai.com/docs/guides/conversation-state). - `id: string` - `summary: Array` - `text: string` - `type: "summary_text"` - `"summary_text"` - `type: "reasoning"` - `"reasoning"` - `content?: Array` - `text: string` - `type: "reasoning_text"` - `"reasoning_text"` - `encrypted_content?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `ResponseCompactionItemParamParam` A compaction item generated by the [`v1/responses/compact` API](https://platform.openai.com/docs/api-reference/responses/compact). - `encrypted_content: string` - `type: "compaction"` - `"compaction"` - `id?: string` - `OpenAITypesResponsesResponseInputParamImageGenerationCall` An image generation request made by the model. - `id: string` - `result: string | null` - `status: "in_progress" | "completed" | "generating" | "failed"` - `"in_progress"` - `"completed"` - `"generating"` - `"failed"` - `type: "image_generation_call"` - `"image_generation_call"` - `ResponseCodeInterpreterToolCallParam` A tool call to run code. - `id: string` - `code: string | null` - `container_id: string` - `outputs: Array | null` - `OutputLogs` The logs output from the code interpreter. - `logs: string` - `type: "logs"` - `"logs"` - `OutputImage` The image output from the code interpreter. - `type: "image"` - `"image"` - `url: string` - `status: "in_progress" | "completed" | "incomplete" | 2 more` - `"in_progress"` - `"completed"` - `"incomplete"` - `"interpreting"` - `"failed"` - `type: "code_interpreter_call"` - `"code_interpreter_call"` - `OpenAITypesResponsesResponseInputParamLocalShellCall` A tool call to run a command on the local shell. - `id: string` - `action: Action` Execute a shell command on the server. - `command: Array` - `env: Record` - `type: "exec"` - `"exec"` - `timeout_ms?: number` - `user?: string` - `working_directory?: string` - `call_id: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "local_shell_call"` - `"local_shell_call"` - `OpenAITypesResponsesResponseInputParamLocalShellCallOutput` The output of a local shell tool call. - `id: string` - `output: string` - `type: "local_shell_call_output"` - `"local_shell_call_output"` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `OpenAITypesResponsesResponseInputParamShellCall` A tool representing a request to execute one or more shell commands. - `action: Action` The shell commands and limits that describe how to run the tool call. - `commands: Array` - `max_output_length?: number` - `timeout_ms?: number` - `call_id: string` - `type: "shell_call"` - `"shell_call"` - `id?: string` - `environment?: LocalEnvironmentParam | ContainerReferenceParam` - `LocalEnvironmentParam` - `type: "local"` - `"local"` - `skills?: Array` - `description: string` - `name: string` - `path: string` - `ContainerReferenceParam` - `container_id: string` - `type: "container_reference"` - `"container_reference"` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `OpenAITypesResponsesResponseInputParamShellCallOutput` The streamed output items emitted by a shell tool call. - `call_id: string` - `output: Array` - `outcome: OutcomeTimeout | OutcomeExit` Indicates that the shell call exceeded its configured time limit. - `OutcomeTimeout` Indicates that the shell call exceeded its configured time limit. - `type: "timeout"` - `"timeout"` - `OutcomeExit` Indicates that the shell commands finished and returned an exit code. - `exit_code: number` - `type: "exit"` - `"exit"` - `stderr: string` - `stdout: string` - `type: "shell_call_output"` - `"shell_call_output"` - `id?: string` - `max_output_length?: number` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `OpenAITypesResponsesResponseInputParamApplyPatchCall` A tool call representing a request to create, delete, or update files using diff patches. - `call_id: string` - `operation: ApplyPatchCallOperationCreateFile | ApplyPatchCallOperationDeleteFile | ApplyPatchCallOperationUpdateFile` Instruction for creating a new file via the apply_patch tool. - `ApplyPatchCallOperationCreateFile` Instruction for creating a new file via the apply_patch tool. - `diff: string` - `path: string` - `type: "create_file"` - `"create_file"` - `ApplyPatchCallOperationDeleteFile` Instruction for deleting an existing file via the apply_patch tool. - `path: string` - `type: "delete_file"` - `"delete_file"` - `ApplyPatchCallOperationUpdateFile` Instruction for updating an existing file via the apply_patch tool. - `diff: string` - `path: string` - `type: "update_file"` - `"update_file"` - `status: "in_progress" | "completed"` - `"in_progress"` - `"completed"` - `type: "apply_patch_call"` - `"apply_patch_call"` - `id?: string` - `OpenAITypesResponsesResponseInputParamApplyPatchCallOutput` The streamed output emitted by an apply patch tool call. - `call_id: string` - `status: "completed" | "failed"` - `"completed"` - `"failed"` - `type: "apply_patch_call_output"` - `"apply_patch_call_output"` - `id?: string` - `output?: string` - `OpenAITypesResponsesResponseInputParamMcpListTools` A list of tools available on an MCP server. - `id: string` - `server_label: string` - `tools: Array` - `input_schema: unknown` - `name: string` - `annotations?: unknown` - `description?: string` - `type: "mcp_list_tools"` - `"mcp_list_tools"` - `error?: string` - `McpApprovalRequest` A request for human approval of a tool invocation. - `id: string` - `arguments: string` - `name: string` - `server_label: string` - `type: "mcp_approval_request"` - `"mcp_approval_request"` - `OpenAITypesResponsesResponseInputParamMcpApprovalResponse` A response to an MCP approval request. - `approval_request_id: string` - `approve: boolean` - `type: "mcp_approval_response"` - `"mcp_approval_response"` - `id?: string` - `reason?: string` - `OpenAITypesResponsesResponseInputParamMcpCall` An invocation of a tool on an MCP server. - `id: string` - `arguments: string` - `name: string` - `server_label: string` - `type: "mcp_call"` - `"mcp_call"` - `approval_request_id?: string` - `error?: string` - `output?: string` - `status?: "in_progress" | "completed" | "incomplete" | 2 more` - `"in_progress"` - `"completed"` - `"incomplete"` - `"calling"` - `"failed"` - `ResponseCustomToolCallOutputParam` The output of a custom tool call from your code, being sent back to the model. - `call_id: string` - `output: string | Array` - `string` - `Array` - `OpenAIResponseInputTextParam` A text input to the model. - `OpenAIResponseInputImageParam` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `OpenAIResponseInputFileParam` A file input to the model. - `type: "custom_tool_call_output"` - `"custom_tool_call_output"` - `id?: string` - `ResponseCustomToolCallParam` A call to a custom tool created by the model. - `call_id: string` - `input: string` - `name: string` - `type: "custom_tool_call"` - `"custom_tool_call"` - `id?: string` - `OpenAITypesResponsesResponseInputParamItemReference` An internal identifier for an item to reference. - `id: string` - `type?: "item_reference"` - `"item_reference"` - `model: string` model specified as `model_vendor/model`, for example `openai/gpt-4o` - `include?: Array` Which fields to include in the response - `instructions?: string` Instructions for the response generation - `max_output_tokens?: number` Maximum number of output tokens - `metadata?: Record` Metadata for the response - `parallel_tool_calls?: boolean` Whether to enable parallel tool calls - `previous_response_id?: string` ID of the previous response for chaining - `reasoning?: Record` Reasoning configuration for the response - `store?: boolean` Whether to store the response - `stream?: boolean` Whether to stream the response - `temperature?: number` Sampling temperature for randomness control - `text?: Record` Text configuration parameters - `tool_choice?: string | Record` Tool choice configuration - `string` - `Record` - `tools?: Array>` Tools available for the response - `top_p?: number` Top-p sampling parameter - `truncation?: "auto" | "disabled"` Truncation configuration - `"auto"` - `"disabled"` ### Returns - `ResponseCreateResponse = OpenAIResponse | ResponseAudioDeltaEvent | ResponseAudioDoneEvent | 52 more` Emitted when there is a partial audio response. - `OpenAIResponse` - `id: string` - `created_at: number` - `model: "gpt-5.2" | "gpt-5.2-2025-12-11" | "gpt-5.2-chat-latest" | 83 more | (string & {})` - `"gpt-5.2" | "gpt-5.2-2025-12-11" | "gpt-5.2-chat-latest" | 83 more` - `"gpt-5.2"` - `"gpt-5.2-2025-12-11"` - `"gpt-5.2-chat-latest"` - `"gpt-5.2-pro"` - `"gpt-5.2-pro-2025-12-11"` - `"gpt-5.1"` - `"gpt-5.1-2025-11-13"` - `"gpt-5.1-codex"` - `"gpt-5.1-mini"` - `"gpt-5.1-chat-latest"` - `"gpt-5"` - `"gpt-5-mini"` - `"gpt-5-nano"` - `"gpt-5-2025-08-07"` - `"gpt-5-mini-2025-08-07"` - `"gpt-5-nano-2025-08-07"` - `"gpt-5-chat-latest"` - `"gpt-4.1"` - `"gpt-4.1-mini"` - `"gpt-4.1-nano"` - `"gpt-4.1-2025-04-14"` - `"gpt-4.1-mini-2025-04-14"` - `"gpt-4.1-nano-2025-04-14"` - `"o4-mini"` - `"o4-mini-2025-04-16"` - `"o3"` - `"o3-2025-04-16"` - `"o3-mini"` - `"o3-mini-2025-01-31"` - `"o1"` - `"o1-2024-12-17"` - `"o1-preview"` - `"o1-preview-2024-09-12"` - `"o1-mini"` - `"o1-mini-2024-09-12"` - `"gpt-4o"` - `"gpt-4o-2024-11-20"` - `"gpt-4o-2024-08-06"` - `"gpt-4o-2024-05-13"` - `"gpt-4o-audio-preview"` - `"gpt-4o-audio-preview-2024-10-01"` - `"gpt-4o-audio-preview-2024-12-17"` - `"gpt-4o-audio-preview-2025-06-03"` - `"gpt-4o-mini-audio-preview"` - `"gpt-4o-mini-audio-preview-2024-12-17"` - `"gpt-4o-search-preview"` - `"gpt-4o-mini-search-preview"` - `"gpt-4o-search-preview-2025-03-11"` - `"gpt-4o-mini-search-preview-2025-03-11"` - `"chatgpt-4o-latest"` - `"codex-mini-latest"` - `"gpt-4o-mini"` - `"gpt-4o-mini-2024-07-18"` - `"gpt-4-turbo"` - `"gpt-4-turbo-2024-04-09"` - `"gpt-4-0125-preview"` - `"gpt-4-turbo-preview"` - `"gpt-4-1106-preview"` - `"gpt-4-vision-preview"` - `"gpt-4"` - `"gpt-4-0314"` - `"gpt-4-0613"` - `"gpt-4-32k"` - `"gpt-4-32k-0314"` - `"gpt-4-32k-0613"` - `"gpt-3.5-turbo"` - `"gpt-3.5-turbo-16k"` - `"gpt-3.5-turbo-0301"` - `"gpt-3.5-turbo-0613"` - `"gpt-3.5-turbo-1106"` - `"gpt-3.5-turbo-0125"` - `"gpt-3.5-turbo-16k-0613"` - `"o1-pro"` - `"o1-pro-2025-03-19"` - `"o3-pro"` - `"o3-pro-2025-06-10"` - `"o3-deep-research"` - `"o3-deep-research-2025-06-26"` - `"o4-mini-deep-research"` - `"o4-mini-deep-research-2025-06-26"` - `"computer-use-preview"` - `"computer-use-preview-2025-03-11"` - `"gpt-5-codex"` - `"gpt-5-pro"` - `"gpt-5-pro-2025-10-06"` - `"gpt-5.1-codex-max"` - `(string & {})` - `object: "response"` - `"response"` - `output: Array` - `OpenAIResponseOutputMessage` An output message from the model. - `id: string` - `content: Array` - `OpenAIResponseOutputText` A text output from the model. - `annotations: Array` - `AnnotationFileCitation` A citation to a file. - `file_id: string` - `filename: string` - `index: number` - `type: "file_citation"` - `"file_citation"` - `OpenAITypesResponsesResponseOutputTextAnnotationURLCitation` A citation for a web resource used to generate a model response. - `end_index: number` - `start_index: number` - `title: string` - `type: "url_citation"` - `"url_citation"` - `url: string` - `AnnotationContainerFileCitation` A citation for a container file used to generate a model response. - `container_id: string` - `end_index: number` - `file_id: string` - `filename: string` - `start_index: number` - `type: "container_file_citation"` - `"container_file_citation"` - `AnnotationFilePath` A path to a file. - `file_id: string` - `index: number` - `type: "file_path"` - `"file_path"` - `text: string` - `type: "output_text"` - `"output_text"` - `logprobs?: Array` - `token: string` - `bytes: Array` - `logprob: number` - `top_logprobs: Array` - `token: string` - `bytes: Array` - `logprob: number` - `OpenAIResponseOutputRefusal` A refusal from the model. - `refusal: string` - `type: "refusal"` - `"refusal"` - `role: "assistant"` - `"assistant"` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "message"` - `"message"` - `phase?: "commentary" | "final_answer"` - `"commentary"` - `"final_answer"` - `OpenAIResponseFileSearchToolCall` The results of a file search tool call. See the [file search guide](https://platform.openai.com/docs/guides/tools-file-search) for more information. - `id: string` - `queries: Array` - `status: "in_progress" | "searching" | "completed" | 2 more` - `"in_progress"` - `"searching"` - `"completed"` - `"incomplete"` - `"failed"` - `type: "file_search_call"` - `"file_search_call"` - `results?: Array` - `attributes?: Record` - `string` - `number` - `boolean` - `file_id?: string` - `filename?: string` - `score?: number` - `text?: string` - `OpenAIResponseFunctionToolCall` A tool call to run a function. See the [function calling guide](https://platform.openai.com/docs/guides/function-calling) for more information. - `arguments: string` - `call_id: string` - `name: string` - `type: "function_call"` - `"function_call"` - `id?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `OpenAIResponseFunctionWebSearch` The results of a web search tool call. See the [web search guide](https://platform.openai.com/docs/guides/tools-web-search) for more information. - `id: string` - `action: OpenAITypesResponsesResponseFunctionWebSearchActionSearch | OpenAITypesResponsesResponseFunctionWebSearchActionOpenPage | ActionFind` Action type "search" - Performs a web search query. - `OpenAITypesResponsesResponseFunctionWebSearchActionSearch` Action type "search" - Performs a web search query. - `query: string` - `type: "search"` - `"search"` - `queries?: Array` - `sources?: Array` - `type: "url"` - `"url"` - `url: string` - `OpenAITypesResponsesResponseFunctionWebSearchActionOpenPage` Action type "open_page" - Opens a specific URL from search results. - `type: "open_page"` - `"open_page"` - `url?: string` - `ActionFind` Action type "find_in_page": Searches for a pattern within a loaded page. - `pattern: string` - `type: "find_in_page"` - `"find_in_page"` - `url: string` - `status: "in_progress" | "searching" | "completed" | "failed"` - `"in_progress"` - `"searching"` - `"completed"` - `"failed"` - `type: "web_search_call"` - `"web_search_call"` - `OpenAIResponseComputerToolCall` A tool call to a computer use tool. See the [computer use guide](https://platform.openai.com/docs/guides/tools-computer-use) for more information. - `id: string` - `action: ActionClick | ActionDoubleClick | ActionDrag | 6 more` A click action. - `ActionClick` A click action. - `button: "left" | "right" | "wheel" | 2 more` - `"left"` - `"right"` - `"wheel"` - `"back"` - `"forward"` - `type: "click"` - `"click"` - `x: number` - `y: number` - `ActionDoubleClick` A double click action. - `type: "double_click"` - `"double_click"` - `x: number` - `y: number` - `ActionDrag` A drag action. - `path: Array` - `x: number` - `y: number` - `type: "drag"` - `"drag"` - `ActionKeypress` A collection of keypresses the model would like to perform. - `keys: Array` - `type: "keypress"` - `"keypress"` - `ActionMove` A mouse move action. - `type: "move"` - `"move"` - `x: number` - `y: number` - `ActionScreenshot` A screenshot action. - `type: "screenshot"` - `"screenshot"` - `ActionScroll` A scroll action. - `scroll_x: number` - `scroll_y: number` - `type: "scroll"` - `"scroll"` - `x: number` - `y: number` - `ActionType` An action to type in text. - `text: string` - `type: "type"` - `"type"` - `ActionWait` A wait action. - `type: "wait"` - `"wait"` - `call_id: string` - `pending_safety_checks: Array` - `id: string` - `code?: string` - `message?: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "computer_call"` - `"computer_call"` - `OpenAIResponseReasoningItem` 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](https://platform.openai.com/docs/guides/conversation-state). - `id: string` - `summary: Array` - `text: string` - `type: "summary_text"` - `"summary_text"` - `type: "reasoning"` - `"reasoning"` - `content?: Array` - `text: string` - `type: "reasoning_text"` - `"reasoning_text"` - `encrypted_content?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `ResponseCompactionItem` A compaction item generated by the [`v1/responses/compact` API](https://platform.openai.com/docs/api-reference/responses/compact). - `id: string` - `encrypted_content: string` - `type: "compaction"` - `"compaction"` - `created_by?: string` - `OpenAITypesResponsesResponseOutputItemImageGenerationCall` An image generation request made by the model. - `id: string` - `status: "in_progress" | "completed" | "generating" | "failed"` - `"in_progress"` - `"completed"` - `"generating"` - `"failed"` - `type: "image_generation_call"` - `"image_generation_call"` - `result?: string` - `OpenAIResponseCodeInterpreterToolCall` A tool call to run code. - `id: string` - `container_id: string` - `status: "in_progress" | "completed" | "incomplete" | 2 more` - `"in_progress"` - `"completed"` - `"incomplete"` - `"interpreting"` - `"failed"` - `type: "code_interpreter_call"` - `"code_interpreter_call"` - `code?: string` - `outputs?: Array` - `OutputLogs` The logs output from the code interpreter. - `logs: string` - `type: "logs"` - `"logs"` - `OutputImage` The image output from the code interpreter. - `type: "image"` - `"image"` - `url: string` - `OpenAITypesResponsesResponseOutputItemLocalShellCall` A tool call to run a command on the local shell. - `id: string` - `action: Action` Execute a shell command on the server. - `command: Array` - `env: Record` - `type: "exec"` - `"exec"` - `timeout_ms?: number` - `user?: string` - `working_directory?: string` - `call_id: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "local_shell_call"` - `"local_shell_call"` - `ResponseFunctionShellToolCall` A tool call that executes one or more shell commands in a managed environment. - `id: string` - `action: Action` The shell commands and limits that describe how to run the tool call. - `commands: Array` - `max_output_length?: number` - `timeout_ms?: number` - `call_id: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "shell_call"` - `"shell_call"` - `created_by?: string` - `environment?: ResponseLocalEnvironment | ResponseContainerReference` Represents the use of a local environment to perform shell actions. - `ResponseLocalEnvironment` Represents the use of a local environment to perform shell actions. - `type: "local"` - `"local"` - `ResponseContainerReference` Represents a container created with /v1/containers. - `container_id: string` - `type: "container_reference"` - `"container_reference"` - `ResponseFunctionShellToolCallOutput` The output of a shell tool call that was emitted. - `id: string` - `call_id: string` - `output: Array` - `outcome: OutputOutcomeTimeout | OutputOutcomeExit` Indicates that the shell call exceeded its configured time limit. - `OutputOutcomeTimeout` Indicates that the shell call exceeded its configured time limit. - `type: "timeout"` - `"timeout"` - `OutputOutcomeExit` Indicates that the shell commands finished and returned an exit code. - `exit_code: number` - `type: "exit"` - `"exit"` - `stderr: string` - `stdout: string` - `created_by?: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "shell_call_output"` - `"shell_call_output"` - `created_by?: string` - `max_output_length?: number` - `ResponseApplyPatchToolCall` A tool call that applies file diffs by creating, deleting, or updating files. - `id: string` - `call_id: string` - `operation: OperationCreateFile | OperationDeleteFile | OperationUpdateFile` Instruction describing how to create a file via the apply_patch tool. - `OperationCreateFile` Instruction describing how to create a file via the apply_patch tool. - `diff: string` - `path: string` - `type: "create_file"` - `"create_file"` - `OperationDeleteFile` Instruction describing how to delete a file via the apply_patch tool. - `path: string` - `type: "delete_file"` - `"delete_file"` - `OperationUpdateFile` Instruction describing how to update a file via the apply_patch tool. - `diff: string` - `path: string` - `type: "update_file"` - `"update_file"` - `status: "in_progress" | "completed"` - `"in_progress"` - `"completed"` - `type: "apply_patch_call"` - `"apply_patch_call"` - `created_by?: string` - `ResponseApplyPatchToolCallOutput` The output emitted by an apply patch tool call. - `id: string` - `call_id: string` - `status: "completed" | "failed"` - `"completed"` - `"failed"` - `type: "apply_patch_call_output"` - `"apply_patch_call_output"` - `created_by?: string` - `output?: string` - `OpenAITypesResponsesResponseOutputItemMcpCall` An invocation of a tool on an MCP server. - `id: string` - `arguments: string` - `name: string` - `server_label: string` - `type: "mcp_call"` - `"mcp_call"` - `approval_request_id?: string` - `error?: string` - `output?: string` - `status?: "in_progress" | "completed" | "incomplete" | 2 more` - `"in_progress"` - `"completed"` - `"incomplete"` - `"calling"` - `"failed"` - `OpenAITypesResponsesResponseOutputItemMcpListTools` A list of tools available on an MCP server. - `id: string` - `server_label: string` - `tools: Array` - `input_schema: unknown` - `name: string` - `annotations?: unknown` - `description?: string` - `type: "mcp_list_tools"` - `"mcp_list_tools"` - `error?: string` - `McpApprovalRequest` A request for human approval of a tool invocation. - `id: string` - `arguments: string` - `name: string` - `server_label: string` - `type: "mcp_approval_request"` - `"mcp_approval_request"` - `OpenAIResponseCustomToolCall` A call to a custom tool created by the model. - `call_id: string` - `input: string` - `name: string` - `type: "custom_tool_call"` - `"custom_tool_call"` - `id?: string` - `parallel_tool_calls: boolean` - `tool_choice: "none" | "auto" | "required" | ToolChoiceAllowed | ToolChoiceTypes | 5 more` Constrains the tools available to the model to a pre-defined set. - `"none" | "auto" | "required"` - `"none"` - `"auto"` - `"required"` - `ToolChoiceAllowed` Constrains the tools available to the model to a pre-defined set. - `mode: "auto" | "required"` - `"auto"` - `"required"` - `tools: Array>` - `type: "allowed_tools"` - `"allowed_tools"` - `ToolChoiceTypes` Indicates that the model should use a built-in tool to generate a response. [Learn more about built-in tools](https://platform.openai.com/docs/guides/tools). - `type: "file_search" | "web_search_preview" | "computer_use_preview" | 3 more` - `"file_search"` - `"web_search_preview"` - `"computer_use_preview"` - `"web_search_preview_2025_03_11"` - `"image_generation"` - `"code_interpreter"` - `ToolChoiceFunction` Use this option to force the model to call a specific function. - `name: string` - `type: "function"` - `"function"` - `ToolChoiceMcp` Use this option to force the model to call a specific tool on a remote MCP server. - `server_label: string` - `type: "mcp"` - `"mcp"` - `name?: string` - `ToolChoiceCustom` Use this option to force the model to call a specific custom tool. - `name: string` - `type: "custom"` - `"custom"` - `ToolChoiceApplyPatch` Forces the model to call the apply_patch tool when executing a tool call. - `type: "apply_patch"` - `"apply_patch"` - `ToolChoiceShell` Forces the model to call the shell tool when a tool call is required. - `type: "shell"` - `"shell"` - `tools: Array` - `FunctionTool` Defines a function in your own code the model can choose to call. Learn more about [function calling](https://platform.openai.com/docs/guides/function-calling). - `name: string` - `type: "function"` - `"function"` - `description?: string` - `parameters?: Record` - `strict?: boolean` - `FileSearchTool` A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](https://platform.openai.com/docs/guides/tools-file-search). - `type: "file_search"` - `"file_search"` - `vector_store_ids: Array` - `filters?: ComparisonFilter | CompoundFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `ComparisonFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `key: string` - `type: "eq" | "ne" | "gt" | 3 more` - `"eq"` - `"ne"` - `"gt"` - `"gte"` - `"lt"` - `"lte"` - `value: string | number | boolean | Array` - `string` - `number` - `boolean` - `Array` - `string` - `number` - `CompoundFilter` Combine multiple filters using `and` or `or`. - `filters: Array` - `ComparisonFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `key: string` - `type: "eq" | "ne" | "gt" | 3 more` - `"eq"` - `"ne"` - `"gt"` - `"gte"` - `"lt"` - `"lte"` - `value: string | number | boolean | Array` - `string` - `number` - `boolean` - `Array` - `string` - `number` - `unknown` - `type: "and" | "or"` - `"and"` - `"or"` - `max_num_results?: number` - `ranking_options?: RankingOptions` Ranking options for search. - `hybrid_search?: HybridSearch` Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled. - `embedding_weight: number` - `text_weight: number` - `ranker?: "auto" | "default-2024-11-15"` - `"auto"` - `"default-2024-11-15"` - `score_threshold?: number` - `ComputerTool` A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use). - `display_height: number` - `display_width: number` - `environment: "windows" | "mac" | "linux" | 2 more` - `"windows"` - `"mac"` - `"linux"` - `"ubuntu"` - `"browser"` - `type: "computer_use_preview"` - `"computer_use_preview"` - `WebSearchTool` Search the Internet for sources related to the prompt. Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search). - `type: "web_search" | "web_search_2025_08_26"` - `"web_search"` - `"web_search_2025_08_26"` - `filters?: Filters` Filters for the search. - `allowed_domains?: Array` - `search_context_size?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `user_location?: UserLocation` The approximate location of the user. - `city?: string` - `country?: string` - `region?: string` - `timezone?: string` - `type?: "approximate"` - `"approximate"` - `Mcp` Give the model access to additional tools via remote Model Context Protocol (MCP) servers. [Learn more about MCP](https://platform.openai.com/docs/guides/tools-remote-mcp). - `server_label: string` - `type: "mcp"` - `"mcp"` - `allowed_tools?: Array | McpAllowedToolsMcpToolFilter` A filter object to specify which tools are allowed. - `Array` - `McpAllowedToolsMcpToolFilter` A filter object to specify which tools are allowed. - `read_only?: boolean` - `tool_names?: Array` - `authorization?: string` - `connector_id?: "connector_dropbox" | "connector_gmail" | "connector_googlecalendar" | 5 more` - `"connector_dropbox"` - `"connector_gmail"` - `"connector_googlecalendar"` - `"connector_googledrive"` - `"connector_microsoftteams"` - `"connector_outlookcalendar"` - `"connector_outlookemail"` - `"connector_sharepoint"` - `headers?: Record` - `require_approval?: McpRequireApprovalMcpToolApprovalFilter | "always" | "never"` Specify which of the MCP server's tools require approval. Can be `always`, `never`, or a filter object associated with tools that require approval. - `McpRequireApprovalMcpToolApprovalFilter` Specify which of the MCP server's tools require approval. Can be `always`, `never`, or a filter object associated with tools that require approval. - `always?: Always` A filter object to specify which tools are allowed. - `read_only?: boolean` - `tool_names?: Array` - `never?: Never` A filter object to specify which tools are allowed. - `read_only?: boolean` - `tool_names?: Array` - `"always" | "never"` - `"always"` - `"never"` - `server_description?: string` - `server_url?: string` - `CodeInterpreter` A tool that runs Python code to help generate a response to a prompt. - `container: string | CodeInterpreterContainerCodeInterpreterToolAuto` Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on. - `string` - `CodeInterpreterContainerCodeInterpreterToolAuto` Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on. - `type: "auto"` - `"auto"` - `file_ids?: Array` - `memory_limit?: "1g" | "4g" | "16g" | "64g"` - `"1g"` - `"4g"` - `"16g"` - `"64g"` - `network_policy?: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` - `ContainerNetworkPolicyDisabled` - `type: "disabled"` - `"disabled"` - `ContainerNetworkPolicyAllowlist` - `allowed_domains: Array` - `type: "allowlist"` - `"allowlist"` - `domain_secrets?: Array` - `domain: string` - `name: string` - `value: string` - `type: "code_interpreter"` - `"code_interpreter"` - `ImageGeneration` A tool that generates images using the GPT image models. - `type: "image_generation"` - `"image_generation"` - `action?: "generate" | "edit" | "auto"` - `"generate"` - `"edit"` - `"auto"` - `background?: "transparent" | "opaque" | "auto"` - `"transparent"` - `"opaque"` - `"auto"` - `input_fidelity?: "high" | "low"` - `"high"` - `"low"` - `input_image_mask?: InputImageMask` Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional). - `file_id?: string` - `image_url?: string` - `model?: (string & {}) | "gpt-image-1" | "gpt-image-1-mini" | "gpt-image-1.5"` - `(string & {})` - `"gpt-image-1" | "gpt-image-1-mini" | "gpt-image-1.5"` - `"gpt-image-1"` - `"gpt-image-1-mini"` - `"gpt-image-1.5"` - `moderation?: "auto" | "low"` - `"auto"` - `"low"` - `output_compression?: number` - `output_format?: "png" | "webp" | "jpeg"` - `"png"` - `"webp"` - `"jpeg"` - `partial_images?: number` - `quality?: "low" | "medium" | "high" | "auto"` - `"low"` - `"medium"` - `"high"` - `"auto"` - `size?: "1024x1024" | "1024x1536" | "1536x1024" | "auto"` - `"1024x1024"` - `"1024x1536"` - `"1536x1024"` - `"auto"` - `LocalShell` A tool that allows the model to execute shell commands in a local environment. - `type: "local_shell"` - `"local_shell"` - `FunctionShellTool` A tool that allows the model to execute shell commands. - `type: "shell"` - `"shell"` - `environment?: ContainerAuto | LocalEnvironment | ContainerReference` - `ContainerAuto` - `type: "container_auto"` - `"container_auto"` - `file_ids?: Array` - `memory_limit?: "1g" | "4g" | "16g" | "64g"` - `"1g"` - `"4g"` - `"16g"` - `"64g"` - `network_policy?: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` - `ContainerNetworkPolicyDisabled` - `ContainerNetworkPolicyAllowlist` - `skills?: Array` - `SkillReference` - `skill_id: string` - `type: "skill_reference"` - `"skill_reference"` - `version?: string` - `InlineSkill` - `description: string` - `name: string` - `source: Source` Inline skill payload - `data: string` - `media_type: "application/zip"` - `"application/zip"` - `type: "base64"` - `"base64"` - `type: "inline"` - `"inline"` - `LocalEnvironment` - `type: "local"` - `"local"` - `skills?: Array` - `description: string` - `name: string` - `path: string` - `ContainerReference` - `container_id: string` - `type: "container_reference"` - `"container_reference"` - `CustomTool` A custom tool that processes input using a specified format. Learn more about [custom tools](https://platform.openai.com/docs/guides/function-calling#custom-tools) - `name: string` - `type: "custom"` - `"custom"` - `description?: string` - `format?: Text | Grammar` Unconstrained free-form text. - `Text` Unconstrained free-form text. - `type: "text"` - `"text"` - `Grammar` A grammar defined by the user. - `definition: string` - `syntax: "lark" | "regex"` - `"lark"` - `"regex"` - `type: "grammar"` - `"grammar"` - `WebSearchPreviewTool` This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search). - `type: "web_search_preview" | "web_search_preview_2025_03_11"` - `"web_search_preview"` - `"web_search_preview_2025_03_11"` - `search_context_size?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `user_location?: UserLocation` The user's location. - `type: "approximate"` - `"approximate"` - `city?: string` - `country?: string` - `region?: string` - `timezone?: string` - `ApplyPatchTool` Allows the assistant to create, delete, or update files using unified diffs. - `type: "apply_patch"` - `"apply_patch"` - `background?: boolean` - `completed_at?: number` - `conversation?: Conversation` The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation. - `id: string` - `error?: OpenAIResponseError` An error object returned when the model fails to generate a Response. - `code: "server_error" | "rate_limit_exceeded" | "invalid_prompt" | 15 more` - `"server_error"` - `"rate_limit_exceeded"` - `"invalid_prompt"` - `"vector_store_timeout"` - `"invalid_image"` - `"invalid_image_format"` - `"invalid_base64_image"` - `"invalid_image_url"` - `"image_too_large"` - `"image_too_small"` - `"image_parse_error"` - `"image_content_policy_violation"` - `"invalid_image_mode"` - `"image_file_too_large"` - `"unsupported_image_media_type"` - `"empty_image_file"` - `"failed_to_download_image"` - `"image_file_not_found"` - `message: string` - `incomplete_details?: IncompleteDetails` Details about why the response is incomplete. - `reason?: "max_output_tokens" | "content_filter"` - `"max_output_tokens"` - `"content_filter"` - `instructions?: string | Array` - `string` - `Array` - `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. - `content: string | Array` - `string` - `Array` - `OpenAIResponseInputText` A text input to the model. - `text: string` - `type: "input_text"` - `"input_text"` - `OpenAIResponseInputImage` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `detail: "low" | "high" | "auto"` - `"low"` - `"high"` - `"auto"` - `type: "input_image"` - `"input_image"` - `file_id?: string` - `image_url?: string` - `OpenAIResponseInputFile` A file input to the model. - `type: "input_file"` - `"input_file"` - `file_data?: string` - `file_id?: string` - `file_url?: string` - `filename?: string` - `role: "user" | "assistant" | "system" | "developer"` - `"user"` - `"assistant"` - `"system"` - `"developer"` - `phase?: "commentary" | "final_answer"` - `"commentary"` - `"final_answer"` - `type?: "message"` - `"message"` - `OpenAITypesResponsesResponseInputItemMessage` 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. - `content: Array` - `OpenAIResponseInputText` A text input to the model. - `OpenAIResponseInputImage` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `OpenAIResponseInputFile` A file input to the model. - `role: "user" | "system" | "developer"` - `"user"` - `"system"` - `"developer"` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type?: "message"` - `"message"` - `OpenAIResponseOutputMessage` An output message from the model. - `OpenAIResponseFileSearchToolCall` The results of a file search tool call. See the [file search guide](https://platform.openai.com/docs/guides/tools-file-search) for more information. - `OpenAIResponseComputerToolCall` A tool call to a computer use tool. See the [computer use guide](https://platform.openai.com/docs/guides/tools-computer-use) for more information. - `OpenAITypesResponsesResponseInputItemComputerCallOutput` The output of a computer tool call. - `call_id: string` - `output: ResponseComputerToolCallOutputScreenshot` A computer screenshot image used with the computer use tool. - `type: "computer_screenshot"` - `"computer_screenshot"` - `file_id?: string` - `image_url?: string` - `type: "computer_call_output"` - `"computer_call_output"` - `id?: string` - `acknowledged_safety_checks?: Array` - `id: string` - `code?: string` - `message?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `OpenAIResponseFunctionWebSearch` The results of a web search tool call. See the [web search guide](https://platform.openai.com/docs/guides/tools-web-search) for more information. - `OpenAIResponseFunctionToolCall` A tool call to run a function. See the [function calling guide](https://platform.openai.com/docs/guides/function-calling) for more information. - `OpenAITypesResponsesResponseInputItemFunctionCallOutput` The output of a function tool call. - `call_id: string` - `output: string | Array` - `string` - `Array` - `ResponseInputTextContent` A text input to the model. - `text: string` - `type: "input_text"` - `"input_text"` - `ResponseInputImageContent` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision) - `type: "input_image"` - `"input_image"` - `detail?: "low" | "high" | "auto"` - `"low"` - `"high"` - `"auto"` - `file_id?: string` - `image_url?: string` - `ResponseInputFileContent` A file input to the model. - `type: "input_file"` - `"input_file"` - `file_data?: string` - `file_id?: string` - `file_url?: string` - `filename?: string` - `type: "function_call_output"` - `"function_call_output"` - `id?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `OpenAIResponseReasoningItem` 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](https://platform.openai.com/docs/guides/conversation-state). - `ResponseCompactionItemParam` A compaction item generated by the [`v1/responses/compact` API](https://platform.openai.com/docs/api-reference/responses/compact). - `encrypted_content: string` - `type: "compaction"` - `"compaction"` - `id?: string` - `OpenAITypesResponsesResponseInputItemImageGenerationCall` An image generation request made by the model. - `id: string` - `status: "in_progress" | "completed" | "generating" | "failed"` - `"in_progress"` - `"completed"` - `"generating"` - `"failed"` - `type: "image_generation_call"` - `"image_generation_call"` - `result?: string` - `OpenAIResponseCodeInterpreterToolCall` A tool call to run code. - `OpenAITypesResponsesResponseInputItemLocalShellCall` A tool call to run a command on the local shell. - `id: string` - `action: Action` Execute a shell command on the server. - `command: Array` - `env: Record` - `type: "exec"` - `"exec"` - `timeout_ms?: number` - `user?: string` - `working_directory?: string` - `call_id: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "local_shell_call"` - `"local_shell_call"` - `OpenAITypesResponsesResponseInputItemLocalShellCallOutput` The output of a local shell tool call. - `id: string` - `output: string` - `type: "local_shell_call_output"` - `"local_shell_call_output"` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `ShellCall` A tool representing a request to execute one or more shell commands. - `action: Action` The shell commands and limits that describe how to run the tool call. - `commands: Array` - `max_output_length?: number` - `timeout_ms?: number` - `call_id: string` - `type: "shell_call"` - `"shell_call"` - `id?: string` - `environment?: LocalEnvironment | ContainerReference` - `LocalEnvironment` - `ContainerReference` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `ShellCallOutput` The streamed output items emitted by a shell tool call. - `call_id: string` - `output: Array` - `outcome: OutcomeTimeout | OutcomeExit` Indicates that the shell call exceeded its configured time limit. - `OutcomeTimeout` Indicates that the shell call exceeded its configured time limit. - `type: "timeout"` - `"timeout"` - `OutcomeExit` Indicates that the shell commands finished and returned an exit code. - `exit_code: number` - `type: "exit"` - `"exit"` - `stderr: string` - `stdout: string` - `type: "shell_call_output"` - `"shell_call_output"` - `id?: string` - `max_output_length?: number` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `ApplyPatchCall` A tool call representing a request to create, delete, or update files using diff patches. - `call_id: string` - `operation: ApplyPatchCallOperationCreateFile | ApplyPatchCallOperationDeleteFile | ApplyPatchCallOperationUpdateFile` Instruction for creating a new file via the apply_patch tool. - `ApplyPatchCallOperationCreateFile` Instruction for creating a new file via the apply_patch tool. - `diff: string` - `path: string` - `type: "create_file"` - `"create_file"` - `ApplyPatchCallOperationDeleteFile` Instruction for deleting an existing file via the apply_patch tool. - `path: string` - `type: "delete_file"` - `"delete_file"` - `ApplyPatchCallOperationUpdateFile` Instruction for updating an existing file via the apply_patch tool. - `diff: string` - `path: string` - `type: "update_file"` - `"update_file"` - `status: "in_progress" | "completed"` - `"in_progress"` - `"completed"` - `type: "apply_patch_call"` - `"apply_patch_call"` - `id?: string` - `ApplyPatchCallOutput` The streamed output emitted by an apply patch tool call. - `call_id: string` - `status: "completed" | "failed"` - `"completed"` - `"failed"` - `type: "apply_patch_call_output"` - `"apply_patch_call_output"` - `id?: string` - `output?: string` - `OpenAITypesResponsesResponseInputItemMcpListTools` A list of tools available on an MCP server. - `id: string` - `server_label: string` - `tools: Array` - `input_schema: unknown` - `name: string` - `annotations?: unknown` - `description?: string` - `type: "mcp_list_tools"` - `"mcp_list_tools"` - `error?: string` - `McpApprovalRequest` A request for human approval of a tool invocation. - `OpenAITypesResponsesResponseInputItemMcpApprovalResponse` A response to an MCP approval request. - `approval_request_id: string` - `approve: boolean` - `type: "mcp_approval_response"` - `"mcp_approval_response"` - `id?: string` - `reason?: string` - `OpenAITypesResponsesResponseInputItemMcpCall` An invocation of a tool on an MCP server. - `id: string` - `arguments: string` - `name: string` - `server_label: string` - `type: "mcp_call"` - `"mcp_call"` - `approval_request_id?: string` - `error?: string` - `output?: string` - `status?: "in_progress" | "completed" | "incomplete" | 2 more` - `"in_progress"` - `"completed"` - `"incomplete"` - `"calling"` - `"failed"` - `OpenAIResponseCustomToolCallOutput` The output of a custom tool call from your code, being sent back to the model. - `call_id: string` - `output: string | Array` - `string` - `Array` - `OpenAIResponseInputText` A text input to the model. - `OpenAIResponseInputImage` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `OpenAIResponseInputFile` A file input to the model. - `type: "custom_tool_call_output"` - `"custom_tool_call_output"` - `id?: string` - `OpenAIResponseCustomToolCall` A call to a custom tool created by the model. - `OpenAITypesResponsesResponseInputItemItemReference` An internal identifier for an item to reference. - `id: string` - `type?: "item_reference"` - `"item_reference"` - `max_output_tokens?: number` - `max_tool_calls?: number` - `metadata?: Record` - `previous_response_id?: string` - `prompt?: OpenAIResponsePrompt` Reference to a prompt template and its variables. [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). - `id: string` - `variables?: Record` - `string` - `OpenAIResponseInputText` A text input to the model. - `OpenAIResponseInputImage` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `OpenAIResponseInputFile` A file input to the model. - `version?: string` - `prompt_cache_key?: string` - `prompt_cache_retention?: "in-memory" | "24h"` - `"in-memory"` - `"24h"` - `reasoning?: Reasoning` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - `effort?: "none" | "minimal" | "low" | 3 more` - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `generate_summary?: "auto" | "concise" | "detailed"` - `"auto"` - `"concise"` - `"detailed"` - `summary?: "auto" | "concise" | "detailed"` - `"auto"` - `"concise"` - `"detailed"` - `safety_identifier?: string` - `service_tier?: "auto" | "default" | "flex" | 2 more` - `"auto"` - `"default"` - `"flex"` - `"scale"` - `"priority"` - `status?: "completed" | "failed" | "in_progress" | 3 more` - `"completed"` - `"failed"` - `"in_progress"` - `"cancelled"` - `"queued"` - `"incomplete"` - `temperature?: number` - `text?: OpenAIResponseTextConfig` Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - [Text inputs and outputs](https://platform.openai.com/docs/guides/text) - [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs) - `format?: ResponseFormatText | ResponseFormatTextJsonSchemaConfig | ResponseFormatJsonObject` Default response format. Used to generate text responses. - `ResponseFormatText` Default response format. Used to generate text responses. - `type: "text"` - `"text"` - `ResponseFormatTextJsonSchemaConfig` JSON Schema response format. Used to generate structured JSON responses. Learn more about [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs). - `name: string` - `schema: Record` - `type: "json_schema"` - `"json_schema"` - `description?: string` - `strict?: boolean` - `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. - `type: "json_object"` - `"json_object"` - `verbosity?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `top_logprobs?: number` - `top_p?: number` - `truncation?: "auto" | "disabled"` - `"auto"` - `"disabled"` - `usage?: OpenAIResponseUsage` Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used. - `input_tokens: number` - `input_tokens_details: InputTokensDetails` A detailed breakdown of the input tokens. - `cached_tokens: number` - `output_tokens: number` - `output_tokens_details: OutputTokensDetails` A detailed breakdown of the output tokens. - `reasoning_tokens: number` - `total_tokens: number` - `user?: string` - `ResponseAudioDeltaEvent` Emitted when there is a partial audio response. - `delta: string` - `sequence_number: number` - `type: "response.audio.delta"` - `"response.audio.delta"` - `ResponseAudioDoneEvent` Emitted when the audio response is complete. - `sequence_number: number` - `type: "response.audio.done"` - `"response.audio.done"` - `ResponseAudioTranscriptDeltaEvent` Emitted when there is a partial transcript of audio. - `delta: string` - `sequence_number: number` - `type: "response.audio.transcript.delta"` - `"response.audio.transcript.delta"` - `ResponseAudioTranscriptDoneEvent` Emitted when the full audio transcript is completed. - `sequence_number: number` - `type: "response.audio.transcript.done"` - `"response.audio.transcript.done"` - `ResponseCodeInterpreterCallCodeDeltaEvent` Emitted when a partial code snippet is streamed by the code interpreter. - `delta: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.code_interpreter_call_code.delta"` - `"response.code_interpreter_call_code.delta"` - `ResponseCodeInterpreterCallCodeDoneEvent` Emitted when the code snippet is finalized by the code interpreter. - `code: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.code_interpreter_call_code.done"` - `"response.code_interpreter_call_code.done"` - `ResponseCodeInterpreterCallCompletedEvent` Emitted when the code interpreter call is completed. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.code_interpreter_call.completed"` - `"response.code_interpreter_call.completed"` - `ResponseCodeInterpreterCallInProgressEvent` Emitted when a code interpreter call is in progress. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.code_interpreter_call.in_progress"` - `"response.code_interpreter_call.in_progress"` - `ResponseCodeInterpreterCallInterpretingEvent` Emitted when the code interpreter is actively interpreting the code snippet. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.code_interpreter_call.interpreting"` - `"response.code_interpreter_call.interpreting"` - `ResponseCompletedEvent` Emitted when the model response is complete. - `response: OpenAIResponse` - `sequence_number: number` - `type: "response.completed"` - `"response.completed"` - `ResponseContentPartAddedEvent` Emitted when a new content part is added. - `content_index: number` - `item_id: string` - `output_index: number` - `part: OpenAIResponseOutputText | OpenAIResponseOutputRefusal | PartReasoningText` A text output from the model. - `OpenAIResponseOutputText` A text output from the model. - `OpenAIResponseOutputRefusal` A refusal from the model. - `PartReasoningText` Reasoning text from the model. - `text: string` - `type: "reasoning_text"` - `"reasoning_text"` - `sequence_number: number` - `type: "response.content_part.added"` - `"response.content_part.added"` - `ResponseContentPartDoneEvent` Emitted when a content part is done. - `content_index: number` - `item_id: string` - `output_index: number` - `part: OpenAIResponseOutputText | OpenAIResponseOutputRefusal | PartReasoningText` A text output from the model. - `OpenAIResponseOutputText` A text output from the model. - `OpenAIResponseOutputRefusal` A refusal from the model. - `PartReasoningText` Reasoning text from the model. - `sequence_number: number` - `type: "response.content_part.done"` - `"response.content_part.done"` - `ResponseCreatedEvent` An event that is emitted when a response is created. - `response: OpenAIResponse` - `sequence_number: number` - `type: "response.created"` - `"response.created"` - `ResponseErrorEvent` Emitted when an error occurs. - `message: string` - `sequence_number: number` - `type: "error"` - `"error"` - `code?: string` - `param?: string` - `ResponseFileSearchCallCompletedEvent` Emitted when a file search call is completed (results found). - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.file_search_call.completed"` - `"response.file_search_call.completed"` - `ResponseFileSearchCallInProgressEvent` Emitted when a file search call is initiated. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.file_search_call.in_progress"` - `"response.file_search_call.in_progress"` - `ResponseFileSearchCallSearchingEvent` Emitted when a file search is currently searching. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.file_search_call.searching"` - `"response.file_search_call.searching"` - `ResponseFunctionCallArgumentsDeltaEvent` Emitted when there is a partial function-call arguments delta. - `delta: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.function_call_arguments.delta"` - `"response.function_call_arguments.delta"` - `ResponseFunctionCallArgumentsDoneEvent` Emitted when function-call arguments are finalized. - `arguments: string` - `item_id: string` - `name: string` - `output_index: number` - `sequence_number: number` - `type: "response.function_call_arguments.done"` - `"response.function_call_arguments.done"` - `ResponseInProgressEvent` Emitted when the response is in progress. - `response: OpenAIResponse` - `sequence_number: number` - `type: "response.in_progress"` - `"response.in_progress"` - `ResponseFailedEvent` An event that is emitted when a response fails. - `response: OpenAIResponse` - `sequence_number: number` - `type: "response.failed"` - `"response.failed"` - `ResponseIncompleteEvent` An event that is emitted when a response finishes as incomplete. - `response: OpenAIResponse` - `sequence_number: number` - `type: "response.incomplete"` - `"response.incomplete"` - `ResponseOutputItemAddedEvent` Emitted when a new output item is added. - `item: OpenAIResponseOutputMessage | OpenAIResponseFileSearchToolCall | OpenAIResponseFunctionToolCall | 15 more` An output message from the model. - `OpenAIResponseOutputMessage` An output message from the model. - `OpenAIResponseFileSearchToolCall` The results of a file search tool call. See the [file search guide](https://platform.openai.com/docs/guides/tools-file-search) for more information. - `OpenAIResponseFunctionToolCall` A tool call to run a function. See the [function calling guide](https://platform.openai.com/docs/guides/function-calling) for more information. - `OpenAIResponseFunctionWebSearch` The results of a web search tool call. See the [web search guide](https://platform.openai.com/docs/guides/tools-web-search) for more information. - `OpenAIResponseComputerToolCall` A tool call to a computer use tool. See the [computer use guide](https://platform.openai.com/docs/guides/tools-computer-use) for more information. - `OpenAIResponseReasoningItem` 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](https://platform.openai.com/docs/guides/conversation-state). - `ResponseCompactionItem` A compaction item generated by the [`v1/responses/compact` API](https://platform.openai.com/docs/api-reference/responses/compact). - `OpenAITypesResponsesResponseOutputItemImageGenerationCall` An image generation request made by the model. - `OpenAIResponseCodeInterpreterToolCall` A tool call to run code. - `OpenAITypesResponsesResponseOutputItemLocalShellCall` A tool call to run a command on the local shell. - `ResponseFunctionShellToolCall` A tool call that executes one or more shell commands in a managed environment. - `ResponseFunctionShellToolCallOutput` The output of a shell tool call that was emitted. - `ResponseApplyPatchToolCall` A tool call that applies file diffs by creating, deleting, or updating files. - `ResponseApplyPatchToolCallOutput` The output emitted by an apply patch tool call. - `OpenAITypesResponsesResponseOutputItemMcpCall` An invocation of a tool on an MCP server. - `OpenAITypesResponsesResponseOutputItemMcpListTools` A list of tools available on an MCP server. - `McpApprovalRequest` A request for human approval of a tool invocation. - `OpenAIResponseCustomToolCall` A call to a custom tool created by the model. - `output_index: number` - `sequence_number: number` - `type: "response.output_item.added"` - `"response.output_item.added"` - `ResponseOutputItemDoneEvent` Emitted when an output item is marked done. - `item: OpenAIResponseOutputMessage | OpenAIResponseFileSearchToolCall | OpenAIResponseFunctionToolCall | 15 more` An output message from the model. - `OpenAIResponseOutputMessage` An output message from the model. - `OpenAIResponseFileSearchToolCall` The results of a file search tool call. See the [file search guide](https://platform.openai.com/docs/guides/tools-file-search) for more information. - `OpenAIResponseFunctionToolCall` A tool call to run a function. See the [function calling guide](https://platform.openai.com/docs/guides/function-calling) for more information. - `OpenAIResponseFunctionWebSearch` The results of a web search tool call. See the [web search guide](https://platform.openai.com/docs/guides/tools-web-search) for more information. - `OpenAIResponseComputerToolCall` A tool call to a computer use tool. See the [computer use guide](https://platform.openai.com/docs/guides/tools-computer-use) for more information. - `OpenAIResponseReasoningItem` 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](https://platform.openai.com/docs/guides/conversation-state). - `ResponseCompactionItem` A compaction item generated by the [`v1/responses/compact` API](https://platform.openai.com/docs/api-reference/responses/compact). - `OpenAITypesResponsesResponseOutputItemImageGenerationCall` An image generation request made by the model. - `OpenAIResponseCodeInterpreterToolCall` A tool call to run code. - `OpenAITypesResponsesResponseOutputItemLocalShellCall` A tool call to run a command on the local shell. - `ResponseFunctionShellToolCall` A tool call that executes one or more shell commands in a managed environment. - `ResponseFunctionShellToolCallOutput` The output of a shell tool call that was emitted. - `ResponseApplyPatchToolCall` A tool call that applies file diffs by creating, deleting, or updating files. - `ResponseApplyPatchToolCallOutput` The output emitted by an apply patch tool call. - `OpenAITypesResponsesResponseOutputItemMcpCall` An invocation of a tool on an MCP server. - `OpenAITypesResponsesResponseOutputItemMcpListTools` A list of tools available on an MCP server. - `McpApprovalRequest` A request for human approval of a tool invocation. - `OpenAIResponseCustomToolCall` A call to a custom tool created by the model. - `output_index: number` - `sequence_number: number` - `type: "response.output_item.done"` - `"response.output_item.done"` - `ResponseReasoningSummaryPartAddedEvent` Emitted when a new reasoning summary part is added. - `item_id: string` - `output_index: number` - `part: Part` The summary part that was added. - `text: string` - `type: "summary_text"` - `"summary_text"` - `sequence_number: number` - `summary_index: number` - `type: "response.reasoning_summary_part.added"` - `"response.reasoning_summary_part.added"` - `ResponseReasoningSummaryPartDoneEvent` Emitted when a reasoning summary part is completed. - `item_id: string` - `output_index: number` - `part: Part` The completed summary part. - `text: string` - `type: "summary_text"` - `"summary_text"` - `sequence_number: number` - `summary_index: number` - `type: "response.reasoning_summary_part.done"` - `"response.reasoning_summary_part.done"` - `ResponseReasoningSummaryTextDeltaEvent` Emitted when a delta is added to a reasoning summary text. - `delta: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `summary_index: number` - `type: "response.reasoning_summary_text.delta"` - `"response.reasoning_summary_text.delta"` - `ResponseReasoningSummaryTextDoneEvent` Emitted when a reasoning summary text is completed. - `item_id: string` - `output_index: number` - `sequence_number: number` - `summary_index: number` - `text: string` - `type: "response.reasoning_summary_text.done"` - `"response.reasoning_summary_text.done"` - `ResponseReasoningTextDeltaEvent` Emitted when a delta is added to a reasoning text. - `content_index: number` - `delta: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.reasoning_text.delta"` - `"response.reasoning_text.delta"` - `ResponseReasoningTextDoneEvent` Emitted when a reasoning text is completed. - `content_index: number` - `item_id: string` - `output_index: number` - `sequence_number: number` - `text: string` - `type: "response.reasoning_text.done"` - `"response.reasoning_text.done"` - `ResponseRefusalDeltaEvent` Emitted when there is a partial refusal text. - `content_index: number` - `delta: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.refusal.delta"` - `"response.refusal.delta"` - `ResponseRefusalDoneEvent` Emitted when refusal text is finalized. - `content_index: number` - `item_id: string` - `output_index: number` - `refusal: string` - `sequence_number: number` - `type: "response.refusal.done"` - `"response.refusal.done"` - `ResponseTextDeltaEvent` Emitted when there is an additional text delta. - `content_index: number` - `delta: string` - `item_id: string` - `logprobs: Array` - `token: string` - `logprob: number` - `top_logprobs?: Array` - `token?: string` - `logprob?: number` - `output_index: number` - `sequence_number: number` - `type: "response.output_text.delta"` - `"response.output_text.delta"` - `ResponseTextDoneEvent` Emitted when text content is finalized. - `content_index: number` - `item_id: string` - `logprobs: Array` - `token: string` - `logprob: number` - `top_logprobs?: Array` - `token?: string` - `logprob?: number` - `output_index: number` - `sequence_number: number` - `text: string` - `type: "response.output_text.done"` - `"response.output_text.done"` - `ResponseWebSearchCallCompletedEvent` Emitted when a web search call is completed. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.web_search_call.completed"` - `"response.web_search_call.completed"` - `ResponseWebSearchCallInProgressEvent` Emitted when a web search call is initiated. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.web_search_call.in_progress"` - `"response.web_search_call.in_progress"` - `ResponseWebSearchCallSearchingEvent` Emitted when a web search call is executing. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.web_search_call.searching"` - `"response.web_search_call.searching"` - `ResponseImageGenCallCompletedEvent` Emitted when an image generation tool call has completed and the final image is available. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.image_generation_call.completed"` - `"response.image_generation_call.completed"` - `ResponseImageGenCallGeneratingEvent` Emitted when an image generation tool call is actively generating an image (intermediate state). - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.image_generation_call.generating"` - `"response.image_generation_call.generating"` - `ResponseImageGenCallInProgressEvent` Emitted when an image generation tool call is in progress. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.image_generation_call.in_progress"` - `"response.image_generation_call.in_progress"` - `ResponseImageGenCallPartialImageEvent` Emitted when a partial image is available during image generation streaming. - `item_id: string` - `output_index: number` - `partial_image_b64: string` - `partial_image_index: number` - `sequence_number: number` - `type: "response.image_generation_call.partial_image"` - `"response.image_generation_call.partial_image"` - `ResponseMcpCallArgumentsDeltaEvent` Emitted when there is a delta (partial update) to the arguments of an MCP tool call. - `delta: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.mcp_call_arguments.delta"` - `"response.mcp_call_arguments.delta"` - `ResponseMcpCallArgumentsDoneEvent` Emitted when the arguments for an MCP tool call are finalized. - `arguments: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.mcp_call_arguments.done"` - `"response.mcp_call_arguments.done"` - `ResponseMcpCallCompletedEvent` Emitted when an MCP tool call has completed successfully. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.mcp_call.completed"` - `"response.mcp_call.completed"` - `ResponseMcpCallFailedEvent` Emitted when an MCP tool call has failed. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.mcp_call.failed"` - `"response.mcp_call.failed"` - `ResponseMcpCallInProgressEvent` Emitted when an MCP tool call is in progress. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.mcp_call.in_progress"` - `"response.mcp_call.in_progress"` - `ResponseMcpListToolsCompletedEvent` Emitted when the list of available MCP tools has been successfully retrieved. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.mcp_list_tools.completed"` - `"response.mcp_list_tools.completed"` - `ResponseMcpListToolsFailedEvent` Emitted when the attempt to list available MCP tools has failed. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.mcp_list_tools.failed"` - `"response.mcp_list_tools.failed"` - `ResponseMcpListToolsInProgressEvent` Emitted when the system is in the process of retrieving the list of available MCP tools. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.mcp_list_tools.in_progress"` - `"response.mcp_list_tools.in_progress"` - `ResponseOutputTextAnnotationAddedEvent` Emitted when an annotation is added to output text content. - `annotation: unknown` - `annotation_index: number` - `content_index: number` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.output_text.annotation.added"` - `"response.output_text.annotation.added"` - `ResponseQueuedEvent` Emitted when a response is queued and waiting to be processed. - `response: OpenAIResponse` - `sequence_number: number` - `type: "response.queued"` - `"response.queued"` - `ResponseCustomToolCallInputDeltaEvent` Event representing a delta (partial update) to the input of a custom tool call. - `delta: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.custom_tool_call_input.delta"` - `"response.custom_tool_call_input.delta"` - `ResponseCustomToolCallInputDoneEvent` Event indicating that input for a custom tool call is complete. - `input: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.custom_tool_call_input.done"` - `"response.custom_tool_call_input.done"` - `GenericResponseEvent` - `type: string` ### Example ```typescript import SGPClient from 'scale-gp'; const client = new SGPClient({ accountID: 'My Account ID', apiKey: process.env['SGP_API_KEY'], // This is the default and can be omitted }); const response = await client.responses.create({ input: 'string', model: 'model' }); console.log(response); ``` #### Response ```json { "id": "id", "created_at": 0, "model": "gpt-5.2", "object": "response", "output": [ { "id": "id", "content": [ { "annotations": [ { "file_id": "file_id", "filename": "filename", "index": 0, "type": "file_citation" } ], "text": "text", "type": "output_text", "logprobs": [ { "token": "token", "bytes": [ 0 ], "logprob": 0, "top_logprobs": [ { "token": "token", "bytes": [ 0 ], "logprob": 0 } ] } ] } ], "role": "assistant", "status": "in_progress", "type": "message", "phase": "commentary" } ], "parallel_tool_calls": true, "tool_choice": "none", "tools": [ { "name": "name", "type": "function", "description": "description", "parameters": { "foo": "bar" }, "strict": true } ], "background": true, "completed_at": 0, "conversation": { "id": "id" }, "error": { "code": "server_error", "message": "message" }, "incomplete_details": { "reason": "max_output_tokens" }, "instructions": "string", "max_output_tokens": 0, "max_tool_calls": 0, "metadata": { "foo": "string" }, "previous_response_id": "previous_response_id", "prompt": { "id": "id", "variables": { "foo": "string" }, "version": "version" }, "prompt_cache_key": "prompt_cache_key", "prompt_cache_retention": "in-memory", "reasoning": { "effort": "none", "generate_summary": "auto", "summary": "auto" }, "safety_identifier": "safety_identifier", "service_tier": "auto", "status": "completed", "temperature": 0, "text": { "format": { "type": "text" }, "verbosity": "low" }, "top_logprobs": 0, "top_p": 0, "truncation": "auto", "usage": { "input_tokens": 0, "input_tokens_details": { "cached_tokens": 0 }, "output_tokens": 0, "output_tokens_details": { "reasoning_tokens": 0 }, "total_tokens": 0 }, "user": "user" } ``` ## Domain Types ### Apply Patch Call - `ApplyPatchCall` A tool call representing a request to create, delete, or update files using diff patches. - `call_id: string` - `operation: ApplyPatchCallOperationCreateFile | ApplyPatchCallOperationDeleteFile | ApplyPatchCallOperationUpdateFile` Instruction for creating a new file via the apply_patch tool. - `ApplyPatchCallOperationCreateFile` Instruction for creating a new file via the apply_patch tool. - `diff: string` - `path: string` - `type: "create_file"` - `"create_file"` - `ApplyPatchCallOperationDeleteFile` Instruction for deleting an existing file via the apply_patch tool. - `path: string` - `type: "delete_file"` - `"delete_file"` - `ApplyPatchCallOperationUpdateFile` Instruction for updating an existing file via the apply_patch tool. - `diff: string` - `path: string` - `type: "update_file"` - `"update_file"` - `status: "in_progress" | "completed"` - `"in_progress"` - `"completed"` - `type: "apply_patch_call"` - `"apply_patch_call"` - `id?: string` ### Apply Patch Call Output - `ApplyPatchCallOutput` The streamed output emitted by an apply patch tool call. - `call_id: string` - `status: "completed" | "failed"` - `"completed"` - `"failed"` - `type: "apply_patch_call_output"` - `"apply_patch_call_output"` - `id?: string` - `output?: string` ### Apply Patch Tool - `ApplyPatchTool` Allows the assistant to create, delete, or update files using unified diffs. - `type: "apply_patch"` - `"apply_patch"` ### Computer Tool - `ComputerTool` A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use). - `display_height: number` - `display_width: number` - `environment: "windows" | "mac" | "linux" | 2 more` - `"windows"` - `"mac"` - `"linux"` - `"ubuntu"` - `"browser"` - `type: "computer_use_preview"` - `"computer_use_preview"` ### Container Network Policy Allowlist - `ContainerNetworkPolicyAllowlist` - `allowed_domains: Array` - `type: "allowlist"` - `"allowlist"` - `domain_secrets?: Array` - `domain: string` - `name: string` - `value: string` ### Container Network Policy Disabled - `ContainerNetworkPolicyDisabled` - `type: "disabled"` - `"disabled"` ### Container Reference - `ContainerReference` - `container_id: string` - `type: "container_reference"` - `"container_reference"` ### Container Reference Param - `ContainerReferenceParam` - `container_id: string` - `type: "container_reference"` - `"container_reference"` ### Conversation - `Conversation` The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation. - `id: string` ### Custom Tool - `CustomTool` A custom tool that processes input using a specified format. Learn more about [custom tools](https://platform.openai.com/docs/guides/function-calling#custom-tools) - `name: string` - `type: "custom"` - `"custom"` - `description?: string` - `format?: Text | Grammar` Unconstrained free-form text. - `Text` Unconstrained free-form text. - `type: "text"` - `"text"` - `Grammar` A grammar defined by the user. - `definition: string` - `syntax: "lark" | "regex"` - `"lark"` - `"regex"` - `type: "grammar"` - `"grammar"` ### Easy Input Message - `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. - `content: string | Array` - `string` - `Array` - `OpenAIResponseInputText` A text input to the model. - `text: string` - `type: "input_text"` - `"input_text"` - `OpenAIResponseInputImage` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `detail: "low" | "high" | "auto"` - `"low"` - `"high"` - `"auto"` - `type: "input_image"` - `"input_image"` - `file_id?: string` - `image_url?: string` - `OpenAIResponseInputFile` A file input to the model. - `type: "input_file"` - `"input_file"` - `file_data?: string` - `file_id?: string` - `file_url?: string` - `filename?: string` - `role: "user" | "assistant" | "system" | "developer"` - `"user"` - `"assistant"` - `"system"` - `"developer"` - `phase?: "commentary" | "final_answer"` - `"commentary"` - `"final_answer"` - `type?: "message"` - `"message"` ### File Search Tool - `FileSearchTool` A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](https://platform.openai.com/docs/guides/tools-file-search). - `type: "file_search"` - `"file_search"` - `vector_store_ids: Array` - `filters?: ComparisonFilter | CompoundFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `ComparisonFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `key: string` - `type: "eq" | "ne" | "gt" | 3 more` - `"eq"` - `"ne"` - `"gt"` - `"gte"` - `"lt"` - `"lte"` - `value: string | number | boolean | Array` - `string` - `number` - `boolean` - `Array` - `string` - `number` - `CompoundFilter` Combine multiple filters using `and` or `or`. - `filters: Array` - `ComparisonFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `key: string` - `type: "eq" | "ne" | "gt" | 3 more` - `"eq"` - `"ne"` - `"gt"` - `"gte"` - `"lt"` - `"lte"` - `value: string | number | boolean | Array` - `string` - `number` - `boolean` - `Array` - `string` - `number` - `unknown` - `type: "and" | "or"` - `"and"` - `"or"` - `max_num_results?: number` - `ranking_options?: RankingOptions` Ranking options for search. - `hybrid_search?: HybridSearch` Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled. - `embedding_weight: number` - `text_weight: number` - `ranker?: "auto" | "default-2024-11-15"` - `"auto"` - `"default-2024-11-15"` - `score_threshold?: number` ### Function Shell Tool - `FunctionShellTool` A tool that allows the model to execute shell commands. - `type: "shell"` - `"shell"` - `environment?: ContainerAuto | LocalEnvironment | ContainerReference` - `ContainerAuto` - `type: "container_auto"` - `"container_auto"` - `file_ids?: Array` - `memory_limit?: "1g" | "4g" | "16g" | "64g"` - `"1g"` - `"4g"` - `"16g"` - `"64g"` - `network_policy?: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` - `ContainerNetworkPolicyDisabled` - `type: "disabled"` - `"disabled"` - `ContainerNetworkPolicyAllowlist` - `allowed_domains: Array` - `type: "allowlist"` - `"allowlist"` - `domain_secrets?: Array` - `domain: string` - `name: string` - `value: string` - `skills?: Array` - `SkillReference` - `skill_id: string` - `type: "skill_reference"` - `"skill_reference"` - `version?: string` - `InlineSkill` - `description: string` - `name: string` - `source: Source` Inline skill payload - `data: string` - `media_type: "application/zip"` - `"application/zip"` - `type: "base64"` - `"base64"` - `type: "inline"` - `"inline"` - `LocalEnvironment` - `type: "local"` - `"local"` - `skills?: Array` - `description: string` - `name: string` - `path: string` - `ContainerReference` - `container_id: string` - `type: "container_reference"` - `"container_reference"` ### Function Tool - `FunctionTool` Defines a function in your own code the model can choose to call. Learn more about [function calling](https://platform.openai.com/docs/guides/function-calling). - `name: string` - `type: "function"` - `"function"` - `description?: string` - `parameters?: Record` - `strict?: boolean` ### Incomplete Details - `IncompleteDetails` Details about why the response is incomplete. - `reason?: "max_output_tokens" | "content_filter"` - `"max_output_tokens"` - `"content_filter"` ### Local Environment - `LocalEnvironment` - `type: "local"` - `"local"` - `skills?: Array` - `description: string` - `name: string` - `path: string` ### Local Environment Param - `LocalEnvironmentParam` - `type: "local"` - `"local"` - `skills?: Array` - `description: string` - `name: string` - `path: string` ### Mcp Approval Request - `McpApprovalRequest` A request for human approval of a tool invocation. - `id: string` - `arguments: string` - `name: string` - `server_label: string` - `type: "mcp_approval_request"` - `"mcp_approval_request"` ### OpenAI Response - `OpenAIResponse` - `id: string` - `created_at: number` - `model: "gpt-5.2" | "gpt-5.2-2025-12-11" | "gpt-5.2-chat-latest" | 83 more | (string & {})` - `"gpt-5.2" | "gpt-5.2-2025-12-11" | "gpt-5.2-chat-latest" | 83 more` - `"gpt-5.2"` - `"gpt-5.2-2025-12-11"` - `"gpt-5.2-chat-latest"` - `"gpt-5.2-pro"` - `"gpt-5.2-pro-2025-12-11"` - `"gpt-5.1"` - `"gpt-5.1-2025-11-13"` - `"gpt-5.1-codex"` - `"gpt-5.1-mini"` - `"gpt-5.1-chat-latest"` - `"gpt-5"` - `"gpt-5-mini"` - `"gpt-5-nano"` - `"gpt-5-2025-08-07"` - `"gpt-5-mini-2025-08-07"` - `"gpt-5-nano-2025-08-07"` - `"gpt-5-chat-latest"` - `"gpt-4.1"` - `"gpt-4.1-mini"` - `"gpt-4.1-nano"` - `"gpt-4.1-2025-04-14"` - `"gpt-4.1-mini-2025-04-14"` - `"gpt-4.1-nano-2025-04-14"` - `"o4-mini"` - `"o4-mini-2025-04-16"` - `"o3"` - `"o3-2025-04-16"` - `"o3-mini"` - `"o3-mini-2025-01-31"` - `"o1"` - `"o1-2024-12-17"` - `"o1-preview"` - `"o1-preview-2024-09-12"` - `"o1-mini"` - `"o1-mini-2024-09-12"` - `"gpt-4o"` - `"gpt-4o-2024-11-20"` - `"gpt-4o-2024-08-06"` - `"gpt-4o-2024-05-13"` - `"gpt-4o-audio-preview"` - `"gpt-4o-audio-preview-2024-10-01"` - `"gpt-4o-audio-preview-2024-12-17"` - `"gpt-4o-audio-preview-2025-06-03"` - `"gpt-4o-mini-audio-preview"` - `"gpt-4o-mini-audio-preview-2024-12-17"` - `"gpt-4o-search-preview"` - `"gpt-4o-mini-search-preview"` - `"gpt-4o-search-preview-2025-03-11"` - `"gpt-4o-mini-search-preview-2025-03-11"` - `"chatgpt-4o-latest"` - `"codex-mini-latest"` - `"gpt-4o-mini"` - `"gpt-4o-mini-2024-07-18"` - `"gpt-4-turbo"` - `"gpt-4-turbo-2024-04-09"` - `"gpt-4-0125-preview"` - `"gpt-4-turbo-preview"` - `"gpt-4-1106-preview"` - `"gpt-4-vision-preview"` - `"gpt-4"` - `"gpt-4-0314"` - `"gpt-4-0613"` - `"gpt-4-32k"` - `"gpt-4-32k-0314"` - `"gpt-4-32k-0613"` - `"gpt-3.5-turbo"` - `"gpt-3.5-turbo-16k"` - `"gpt-3.5-turbo-0301"` - `"gpt-3.5-turbo-0613"` - `"gpt-3.5-turbo-1106"` - `"gpt-3.5-turbo-0125"` - `"gpt-3.5-turbo-16k-0613"` - `"o1-pro"` - `"o1-pro-2025-03-19"` - `"o3-pro"` - `"o3-pro-2025-06-10"` - `"o3-deep-research"` - `"o3-deep-research-2025-06-26"` - `"o4-mini-deep-research"` - `"o4-mini-deep-research-2025-06-26"` - `"computer-use-preview"` - `"computer-use-preview-2025-03-11"` - `"gpt-5-codex"` - `"gpt-5-pro"` - `"gpt-5-pro-2025-10-06"` - `"gpt-5.1-codex-max"` - `(string & {})` - `object: "response"` - `"response"` - `output: Array` - `OpenAIResponseOutputMessage` An output message from the model. - `id: string` - `content: Array` - `OpenAIResponseOutputText` A text output from the model. - `annotations: Array` - `AnnotationFileCitation` A citation to a file. - `file_id: string` - `filename: string` - `index: number` - `type: "file_citation"` - `"file_citation"` - `OpenAITypesResponsesResponseOutputTextAnnotationURLCitation` A citation for a web resource used to generate a model response. - `end_index: number` - `start_index: number` - `title: string` - `type: "url_citation"` - `"url_citation"` - `url: string` - `AnnotationContainerFileCitation` A citation for a container file used to generate a model response. - `container_id: string` - `end_index: number` - `file_id: string` - `filename: string` - `start_index: number` - `type: "container_file_citation"` - `"container_file_citation"` - `AnnotationFilePath` A path to a file. - `file_id: string` - `index: number` - `type: "file_path"` - `"file_path"` - `text: string` - `type: "output_text"` - `"output_text"` - `logprobs?: Array` - `token: string` - `bytes: Array` - `logprob: number` - `top_logprobs: Array` - `token: string` - `bytes: Array` - `logprob: number` - `OpenAIResponseOutputRefusal` A refusal from the model. - `refusal: string` - `type: "refusal"` - `"refusal"` - `role: "assistant"` - `"assistant"` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "message"` - `"message"` - `phase?: "commentary" | "final_answer"` - `"commentary"` - `"final_answer"` - `OpenAIResponseFileSearchToolCall` The results of a file search tool call. See the [file search guide](https://platform.openai.com/docs/guides/tools-file-search) for more information. - `id: string` - `queries: Array` - `status: "in_progress" | "searching" | "completed" | 2 more` - `"in_progress"` - `"searching"` - `"completed"` - `"incomplete"` - `"failed"` - `type: "file_search_call"` - `"file_search_call"` - `results?: Array` - `attributes?: Record` - `string` - `number` - `boolean` - `file_id?: string` - `filename?: string` - `score?: number` - `text?: string` - `OpenAIResponseFunctionToolCall` A tool call to run a function. See the [function calling guide](https://platform.openai.com/docs/guides/function-calling) for more information. - `arguments: string` - `call_id: string` - `name: string` - `type: "function_call"` - `"function_call"` - `id?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `OpenAIResponseFunctionWebSearch` The results of a web search tool call. See the [web search guide](https://platform.openai.com/docs/guides/tools-web-search) for more information. - `id: string` - `action: OpenAITypesResponsesResponseFunctionWebSearchActionSearch | OpenAITypesResponsesResponseFunctionWebSearchActionOpenPage | ActionFind` Action type "search" - Performs a web search query. - `OpenAITypesResponsesResponseFunctionWebSearchActionSearch` Action type "search" - Performs a web search query. - `query: string` - `type: "search"` - `"search"` - `queries?: Array` - `sources?: Array` - `type: "url"` - `"url"` - `url: string` - `OpenAITypesResponsesResponseFunctionWebSearchActionOpenPage` Action type "open_page" - Opens a specific URL from search results. - `type: "open_page"` - `"open_page"` - `url?: string` - `ActionFind` Action type "find_in_page": Searches for a pattern within a loaded page. - `pattern: string` - `type: "find_in_page"` - `"find_in_page"` - `url: string` - `status: "in_progress" | "searching" | "completed" | "failed"` - `"in_progress"` - `"searching"` - `"completed"` - `"failed"` - `type: "web_search_call"` - `"web_search_call"` - `OpenAIResponseComputerToolCall` A tool call to a computer use tool. See the [computer use guide](https://platform.openai.com/docs/guides/tools-computer-use) for more information. - `id: string` - `action: ActionClick | ActionDoubleClick | ActionDrag | 6 more` A click action. - `ActionClick` A click action. - `button: "left" | "right" | "wheel" | 2 more` - `"left"` - `"right"` - `"wheel"` - `"back"` - `"forward"` - `type: "click"` - `"click"` - `x: number` - `y: number` - `ActionDoubleClick` A double click action. - `type: "double_click"` - `"double_click"` - `x: number` - `y: number` - `ActionDrag` A drag action. - `path: Array` - `x: number` - `y: number` - `type: "drag"` - `"drag"` - `ActionKeypress` A collection of keypresses the model would like to perform. - `keys: Array` - `type: "keypress"` - `"keypress"` - `ActionMove` A mouse move action. - `type: "move"` - `"move"` - `x: number` - `y: number` - `ActionScreenshot` A screenshot action. - `type: "screenshot"` - `"screenshot"` - `ActionScroll` A scroll action. - `scroll_x: number` - `scroll_y: number` - `type: "scroll"` - `"scroll"` - `x: number` - `y: number` - `ActionType` An action to type in text. - `text: string` - `type: "type"` - `"type"` - `ActionWait` A wait action. - `type: "wait"` - `"wait"` - `call_id: string` - `pending_safety_checks: Array` - `id: string` - `code?: string` - `message?: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "computer_call"` - `"computer_call"` - `OpenAIResponseReasoningItem` 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](https://platform.openai.com/docs/guides/conversation-state). - `id: string` - `summary: Array` - `text: string` - `type: "summary_text"` - `"summary_text"` - `type: "reasoning"` - `"reasoning"` - `content?: Array` - `text: string` - `type: "reasoning_text"` - `"reasoning_text"` - `encrypted_content?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `ResponseCompactionItem` A compaction item generated by the [`v1/responses/compact` API](https://platform.openai.com/docs/api-reference/responses/compact). - `id: string` - `encrypted_content: string` - `type: "compaction"` - `"compaction"` - `created_by?: string` - `OpenAITypesResponsesResponseOutputItemImageGenerationCall` An image generation request made by the model. - `id: string` - `status: "in_progress" | "completed" | "generating" | "failed"` - `"in_progress"` - `"completed"` - `"generating"` - `"failed"` - `type: "image_generation_call"` - `"image_generation_call"` - `result?: string` - `OpenAIResponseCodeInterpreterToolCall` A tool call to run code. - `id: string` - `container_id: string` - `status: "in_progress" | "completed" | "incomplete" | 2 more` - `"in_progress"` - `"completed"` - `"incomplete"` - `"interpreting"` - `"failed"` - `type: "code_interpreter_call"` - `"code_interpreter_call"` - `code?: string` - `outputs?: Array` - `OutputLogs` The logs output from the code interpreter. - `logs: string` - `type: "logs"` - `"logs"` - `OutputImage` The image output from the code interpreter. - `type: "image"` - `"image"` - `url: string` - `OpenAITypesResponsesResponseOutputItemLocalShellCall` A tool call to run a command on the local shell. - `id: string` - `action: Action` Execute a shell command on the server. - `command: Array` - `env: Record` - `type: "exec"` - `"exec"` - `timeout_ms?: number` - `user?: string` - `working_directory?: string` - `call_id: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "local_shell_call"` - `"local_shell_call"` - `ResponseFunctionShellToolCall` A tool call that executes one or more shell commands in a managed environment. - `id: string` - `action: Action` The shell commands and limits that describe how to run the tool call. - `commands: Array` - `max_output_length?: number` - `timeout_ms?: number` - `call_id: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "shell_call"` - `"shell_call"` - `created_by?: string` - `environment?: ResponseLocalEnvironment | ResponseContainerReference` Represents the use of a local environment to perform shell actions. - `ResponseLocalEnvironment` Represents the use of a local environment to perform shell actions. - `type: "local"` - `"local"` - `ResponseContainerReference` Represents a container created with /v1/containers. - `container_id: string` - `type: "container_reference"` - `"container_reference"` - `ResponseFunctionShellToolCallOutput` The output of a shell tool call that was emitted. - `id: string` - `call_id: string` - `output: Array` - `outcome: OutputOutcomeTimeout | OutputOutcomeExit` Indicates that the shell call exceeded its configured time limit. - `OutputOutcomeTimeout` Indicates that the shell call exceeded its configured time limit. - `type: "timeout"` - `"timeout"` - `OutputOutcomeExit` Indicates that the shell commands finished and returned an exit code. - `exit_code: number` - `type: "exit"` - `"exit"` - `stderr: string` - `stdout: string` - `created_by?: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "shell_call_output"` - `"shell_call_output"` - `created_by?: string` - `max_output_length?: number` - `ResponseApplyPatchToolCall` A tool call that applies file diffs by creating, deleting, or updating files. - `id: string` - `call_id: string` - `operation: OperationCreateFile | OperationDeleteFile | OperationUpdateFile` Instruction describing how to create a file via the apply_patch tool. - `OperationCreateFile` Instruction describing how to create a file via the apply_patch tool. - `diff: string` - `path: string` - `type: "create_file"` - `"create_file"` - `OperationDeleteFile` Instruction describing how to delete a file via the apply_patch tool. - `path: string` - `type: "delete_file"` - `"delete_file"` - `OperationUpdateFile` Instruction describing how to update a file via the apply_patch tool. - `diff: string` - `path: string` - `type: "update_file"` - `"update_file"` - `status: "in_progress" | "completed"` - `"in_progress"` - `"completed"` - `type: "apply_patch_call"` - `"apply_patch_call"` - `created_by?: string` - `ResponseApplyPatchToolCallOutput` The output emitted by an apply patch tool call. - `id: string` - `call_id: string` - `status: "completed" | "failed"` - `"completed"` - `"failed"` - `type: "apply_patch_call_output"` - `"apply_patch_call_output"` - `created_by?: string` - `output?: string` - `OpenAITypesResponsesResponseOutputItemMcpCall` An invocation of a tool on an MCP server. - `id: string` - `arguments: string` - `name: string` - `server_label: string` - `type: "mcp_call"` - `"mcp_call"` - `approval_request_id?: string` - `error?: string` - `output?: string` - `status?: "in_progress" | "completed" | "incomplete" | 2 more` - `"in_progress"` - `"completed"` - `"incomplete"` - `"calling"` - `"failed"` - `OpenAITypesResponsesResponseOutputItemMcpListTools` A list of tools available on an MCP server. - `id: string` - `server_label: string` - `tools: Array` - `input_schema: unknown` - `name: string` - `annotations?: unknown` - `description?: string` - `type: "mcp_list_tools"` - `"mcp_list_tools"` - `error?: string` - `McpApprovalRequest` A request for human approval of a tool invocation. - `id: string` - `arguments: string` - `name: string` - `server_label: string` - `type: "mcp_approval_request"` - `"mcp_approval_request"` - `OpenAIResponseCustomToolCall` A call to a custom tool created by the model. - `call_id: string` - `input: string` - `name: string` - `type: "custom_tool_call"` - `"custom_tool_call"` - `id?: string` - `parallel_tool_calls: boolean` - `tool_choice: "none" | "auto" | "required" | ToolChoiceAllowed | ToolChoiceTypes | 5 more` Constrains the tools available to the model to a pre-defined set. - `"none" | "auto" | "required"` - `"none"` - `"auto"` - `"required"` - `ToolChoiceAllowed` Constrains the tools available to the model to a pre-defined set. - `mode: "auto" | "required"` - `"auto"` - `"required"` - `tools: Array>` - `type: "allowed_tools"` - `"allowed_tools"` - `ToolChoiceTypes` Indicates that the model should use a built-in tool to generate a response. [Learn more about built-in tools](https://platform.openai.com/docs/guides/tools). - `type: "file_search" | "web_search_preview" | "computer_use_preview" | 3 more` - `"file_search"` - `"web_search_preview"` - `"computer_use_preview"` - `"web_search_preview_2025_03_11"` - `"image_generation"` - `"code_interpreter"` - `ToolChoiceFunction` Use this option to force the model to call a specific function. - `name: string` - `type: "function"` - `"function"` - `ToolChoiceMcp` Use this option to force the model to call a specific tool on a remote MCP server. - `server_label: string` - `type: "mcp"` - `"mcp"` - `name?: string` - `ToolChoiceCustom` Use this option to force the model to call a specific custom tool. - `name: string` - `type: "custom"` - `"custom"` - `ToolChoiceApplyPatch` Forces the model to call the apply_patch tool when executing a tool call. - `type: "apply_patch"` - `"apply_patch"` - `ToolChoiceShell` Forces the model to call the shell tool when a tool call is required. - `type: "shell"` - `"shell"` - `tools: Array` - `FunctionTool` Defines a function in your own code the model can choose to call. Learn more about [function calling](https://platform.openai.com/docs/guides/function-calling). - `name: string` - `type: "function"` - `"function"` - `description?: string` - `parameters?: Record` - `strict?: boolean` - `FileSearchTool` A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](https://platform.openai.com/docs/guides/tools-file-search). - `type: "file_search"` - `"file_search"` - `vector_store_ids: Array` - `filters?: ComparisonFilter | CompoundFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `ComparisonFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `key: string` - `type: "eq" | "ne" | "gt" | 3 more` - `"eq"` - `"ne"` - `"gt"` - `"gte"` - `"lt"` - `"lte"` - `value: string | number | boolean | Array` - `string` - `number` - `boolean` - `Array` - `string` - `number` - `CompoundFilter` Combine multiple filters using `and` or `or`. - `filters: Array` - `ComparisonFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `key: string` - `type: "eq" | "ne" | "gt" | 3 more` - `"eq"` - `"ne"` - `"gt"` - `"gte"` - `"lt"` - `"lte"` - `value: string | number | boolean | Array` - `string` - `number` - `boolean` - `Array` - `string` - `number` - `unknown` - `type: "and" | "or"` - `"and"` - `"or"` - `max_num_results?: number` - `ranking_options?: RankingOptions` Ranking options for search. - `hybrid_search?: HybridSearch` Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled. - `embedding_weight: number` - `text_weight: number` - `ranker?: "auto" | "default-2024-11-15"` - `"auto"` - `"default-2024-11-15"` - `score_threshold?: number` - `ComputerTool` A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use). - `display_height: number` - `display_width: number` - `environment: "windows" | "mac" | "linux" | 2 more` - `"windows"` - `"mac"` - `"linux"` - `"ubuntu"` - `"browser"` - `type: "computer_use_preview"` - `"computer_use_preview"` - `WebSearchTool` Search the Internet for sources related to the prompt. Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search). - `type: "web_search" | "web_search_2025_08_26"` - `"web_search"` - `"web_search_2025_08_26"` - `filters?: Filters` Filters for the search. - `allowed_domains?: Array` - `search_context_size?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `user_location?: UserLocation` The approximate location of the user. - `city?: string` - `country?: string` - `region?: string` - `timezone?: string` - `type?: "approximate"` - `"approximate"` - `Mcp` Give the model access to additional tools via remote Model Context Protocol (MCP) servers. [Learn more about MCP](https://platform.openai.com/docs/guides/tools-remote-mcp). - `server_label: string` - `type: "mcp"` - `"mcp"` - `allowed_tools?: Array | McpAllowedToolsMcpToolFilter` A filter object to specify which tools are allowed. - `Array` - `McpAllowedToolsMcpToolFilter` A filter object to specify which tools are allowed. - `read_only?: boolean` - `tool_names?: Array` - `authorization?: string` - `connector_id?: "connector_dropbox" | "connector_gmail" | "connector_googlecalendar" | 5 more` - `"connector_dropbox"` - `"connector_gmail"` - `"connector_googlecalendar"` - `"connector_googledrive"` - `"connector_microsoftteams"` - `"connector_outlookcalendar"` - `"connector_outlookemail"` - `"connector_sharepoint"` - `headers?: Record` - `require_approval?: McpRequireApprovalMcpToolApprovalFilter | "always" | "never"` Specify which of the MCP server's tools require approval. Can be `always`, `never`, or a filter object associated with tools that require approval. - `McpRequireApprovalMcpToolApprovalFilter` Specify which of the MCP server's tools require approval. Can be `always`, `never`, or a filter object associated with tools that require approval. - `always?: Always` A filter object to specify which tools are allowed. - `read_only?: boolean` - `tool_names?: Array` - `never?: Never` A filter object to specify which tools are allowed. - `read_only?: boolean` - `tool_names?: Array` - `"always" | "never"` - `"always"` - `"never"` - `server_description?: string` - `server_url?: string` - `CodeInterpreter` A tool that runs Python code to help generate a response to a prompt. - `container: string | CodeInterpreterContainerCodeInterpreterToolAuto` Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on. - `string` - `CodeInterpreterContainerCodeInterpreterToolAuto` Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on. - `type: "auto"` - `"auto"` - `file_ids?: Array` - `memory_limit?: "1g" | "4g" | "16g" | "64g"` - `"1g"` - `"4g"` - `"16g"` - `"64g"` - `network_policy?: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` - `ContainerNetworkPolicyDisabled` - `type: "disabled"` - `"disabled"` - `ContainerNetworkPolicyAllowlist` - `allowed_domains: Array` - `type: "allowlist"` - `"allowlist"` - `domain_secrets?: Array` - `domain: string` - `name: string` - `value: string` - `type: "code_interpreter"` - `"code_interpreter"` - `ImageGeneration` A tool that generates images using the GPT image models. - `type: "image_generation"` - `"image_generation"` - `action?: "generate" | "edit" | "auto"` - `"generate"` - `"edit"` - `"auto"` - `background?: "transparent" | "opaque" | "auto"` - `"transparent"` - `"opaque"` - `"auto"` - `input_fidelity?: "high" | "low"` - `"high"` - `"low"` - `input_image_mask?: InputImageMask` Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional). - `file_id?: string` - `image_url?: string` - `model?: (string & {}) | "gpt-image-1" | "gpt-image-1-mini" | "gpt-image-1.5"` - `(string & {})` - `"gpt-image-1" | "gpt-image-1-mini" | "gpt-image-1.5"` - `"gpt-image-1"` - `"gpt-image-1-mini"` - `"gpt-image-1.5"` - `moderation?: "auto" | "low"` - `"auto"` - `"low"` - `output_compression?: number` - `output_format?: "png" | "webp" | "jpeg"` - `"png"` - `"webp"` - `"jpeg"` - `partial_images?: number` - `quality?: "low" | "medium" | "high" | "auto"` - `"low"` - `"medium"` - `"high"` - `"auto"` - `size?: "1024x1024" | "1024x1536" | "1536x1024" | "auto"` - `"1024x1024"` - `"1024x1536"` - `"1536x1024"` - `"auto"` - `LocalShell` A tool that allows the model to execute shell commands in a local environment. - `type: "local_shell"` - `"local_shell"` - `FunctionShellTool` A tool that allows the model to execute shell commands. - `type: "shell"` - `"shell"` - `environment?: ContainerAuto | LocalEnvironment | ContainerReference` - `ContainerAuto` - `type: "container_auto"` - `"container_auto"` - `file_ids?: Array` - `memory_limit?: "1g" | "4g" | "16g" | "64g"` - `"1g"` - `"4g"` - `"16g"` - `"64g"` - `network_policy?: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` - `ContainerNetworkPolicyDisabled` - `ContainerNetworkPolicyAllowlist` - `skills?: Array` - `SkillReference` - `skill_id: string` - `type: "skill_reference"` - `"skill_reference"` - `version?: string` - `InlineSkill` - `description: string` - `name: string` - `source: Source` Inline skill payload - `data: string` - `media_type: "application/zip"` - `"application/zip"` - `type: "base64"` - `"base64"` - `type: "inline"` - `"inline"` - `LocalEnvironment` - `type: "local"` - `"local"` - `skills?: Array` - `description: string` - `name: string` - `path: string` - `ContainerReference` - `container_id: string` - `type: "container_reference"` - `"container_reference"` - `CustomTool` A custom tool that processes input using a specified format. Learn more about [custom tools](https://platform.openai.com/docs/guides/function-calling#custom-tools) - `name: string` - `type: "custom"` - `"custom"` - `description?: string` - `format?: Text | Grammar` Unconstrained free-form text. - `Text` Unconstrained free-form text. - `type: "text"` - `"text"` - `Grammar` A grammar defined by the user. - `definition: string` - `syntax: "lark" | "regex"` - `"lark"` - `"regex"` - `type: "grammar"` - `"grammar"` - `WebSearchPreviewTool` This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search). - `type: "web_search_preview" | "web_search_preview_2025_03_11"` - `"web_search_preview"` - `"web_search_preview_2025_03_11"` - `search_context_size?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `user_location?: UserLocation` The user's location. - `type: "approximate"` - `"approximate"` - `city?: string` - `country?: string` - `region?: string` - `timezone?: string` - `ApplyPatchTool` Allows the assistant to create, delete, or update files using unified diffs. - `type: "apply_patch"` - `"apply_patch"` - `background?: boolean` - `completed_at?: number` - `conversation?: Conversation` The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation. - `id: string` - `error?: OpenAIResponseError` An error object returned when the model fails to generate a Response. - `code: "server_error" | "rate_limit_exceeded" | "invalid_prompt" | 15 more` - `"server_error"` - `"rate_limit_exceeded"` - `"invalid_prompt"` - `"vector_store_timeout"` - `"invalid_image"` - `"invalid_image_format"` - `"invalid_base64_image"` - `"invalid_image_url"` - `"image_too_large"` - `"image_too_small"` - `"image_parse_error"` - `"image_content_policy_violation"` - `"invalid_image_mode"` - `"image_file_too_large"` - `"unsupported_image_media_type"` - `"empty_image_file"` - `"failed_to_download_image"` - `"image_file_not_found"` - `message: string` - `incomplete_details?: IncompleteDetails` Details about why the response is incomplete. - `reason?: "max_output_tokens" | "content_filter"` - `"max_output_tokens"` - `"content_filter"` - `instructions?: string | Array` - `string` - `Array` - `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. - `content: string | Array` - `string` - `Array` - `OpenAIResponseInputText` A text input to the model. - `text: string` - `type: "input_text"` - `"input_text"` - `OpenAIResponseInputImage` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `detail: "low" | "high" | "auto"` - `"low"` - `"high"` - `"auto"` - `type: "input_image"` - `"input_image"` - `file_id?: string` - `image_url?: string` - `OpenAIResponseInputFile` A file input to the model. - `type: "input_file"` - `"input_file"` - `file_data?: string` - `file_id?: string` - `file_url?: string` - `filename?: string` - `role: "user" | "assistant" | "system" | "developer"` - `"user"` - `"assistant"` - `"system"` - `"developer"` - `phase?: "commentary" | "final_answer"` - `"commentary"` - `"final_answer"` - `type?: "message"` - `"message"` - `OpenAITypesResponsesResponseInputItemMessage` 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. - `content: Array` - `OpenAIResponseInputText` A text input to the model. - `OpenAIResponseInputImage` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `OpenAIResponseInputFile` A file input to the model. - `role: "user" | "system" | "developer"` - `"user"` - `"system"` - `"developer"` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type?: "message"` - `"message"` - `OpenAIResponseOutputMessage` An output message from the model. - `OpenAIResponseFileSearchToolCall` The results of a file search tool call. See the [file search guide](https://platform.openai.com/docs/guides/tools-file-search) for more information. - `OpenAIResponseComputerToolCall` A tool call to a computer use tool. See the [computer use guide](https://platform.openai.com/docs/guides/tools-computer-use) for more information. - `OpenAITypesResponsesResponseInputItemComputerCallOutput` The output of a computer tool call. - `call_id: string` - `output: ResponseComputerToolCallOutputScreenshot` A computer screenshot image used with the computer use tool. - `type: "computer_screenshot"` - `"computer_screenshot"` - `file_id?: string` - `image_url?: string` - `type: "computer_call_output"` - `"computer_call_output"` - `id?: string` - `acknowledged_safety_checks?: Array` - `id: string` - `code?: string` - `message?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `OpenAIResponseFunctionWebSearch` The results of a web search tool call. See the [web search guide](https://platform.openai.com/docs/guides/tools-web-search) for more information. - `OpenAIResponseFunctionToolCall` A tool call to run a function. See the [function calling guide](https://platform.openai.com/docs/guides/function-calling) for more information. - `OpenAITypesResponsesResponseInputItemFunctionCallOutput` The output of a function tool call. - `call_id: string` - `output: string | Array` - `string` - `Array` - `ResponseInputTextContent` A text input to the model. - `text: string` - `type: "input_text"` - `"input_text"` - `ResponseInputImageContent` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision) - `type: "input_image"` - `"input_image"` - `detail?: "low" | "high" | "auto"` - `"low"` - `"high"` - `"auto"` - `file_id?: string` - `image_url?: string` - `ResponseInputFileContent` A file input to the model. - `type: "input_file"` - `"input_file"` - `file_data?: string` - `file_id?: string` - `file_url?: string` - `filename?: string` - `type: "function_call_output"` - `"function_call_output"` - `id?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `OpenAIResponseReasoningItem` 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](https://platform.openai.com/docs/guides/conversation-state). - `ResponseCompactionItemParam` A compaction item generated by the [`v1/responses/compact` API](https://platform.openai.com/docs/api-reference/responses/compact). - `encrypted_content: string` - `type: "compaction"` - `"compaction"` - `id?: string` - `OpenAITypesResponsesResponseInputItemImageGenerationCall` An image generation request made by the model. - `id: string` - `status: "in_progress" | "completed" | "generating" | "failed"` - `"in_progress"` - `"completed"` - `"generating"` - `"failed"` - `type: "image_generation_call"` - `"image_generation_call"` - `result?: string` - `OpenAIResponseCodeInterpreterToolCall` A tool call to run code. - `OpenAITypesResponsesResponseInputItemLocalShellCall` A tool call to run a command on the local shell. - `id: string` - `action: Action` Execute a shell command on the server. - `command: Array` - `env: Record` - `type: "exec"` - `"exec"` - `timeout_ms?: number` - `user?: string` - `working_directory?: string` - `call_id: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "local_shell_call"` - `"local_shell_call"` - `OpenAITypesResponsesResponseInputItemLocalShellCallOutput` The output of a local shell tool call. - `id: string` - `output: string` - `type: "local_shell_call_output"` - `"local_shell_call_output"` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `ShellCall` A tool representing a request to execute one or more shell commands. - `action: Action` The shell commands and limits that describe how to run the tool call. - `commands: Array` - `max_output_length?: number` - `timeout_ms?: number` - `call_id: string` - `type: "shell_call"` - `"shell_call"` - `id?: string` - `environment?: LocalEnvironment | ContainerReference` - `LocalEnvironment` - `ContainerReference` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `ShellCallOutput` The streamed output items emitted by a shell tool call. - `call_id: string` - `output: Array` - `outcome: OutcomeTimeout | OutcomeExit` Indicates that the shell call exceeded its configured time limit. - `OutcomeTimeout` Indicates that the shell call exceeded its configured time limit. - `type: "timeout"` - `"timeout"` - `OutcomeExit` Indicates that the shell commands finished and returned an exit code. - `exit_code: number` - `type: "exit"` - `"exit"` - `stderr: string` - `stdout: string` - `type: "shell_call_output"` - `"shell_call_output"` - `id?: string` - `max_output_length?: number` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `ApplyPatchCall` A tool call representing a request to create, delete, or update files using diff patches. - `call_id: string` - `operation: ApplyPatchCallOperationCreateFile | ApplyPatchCallOperationDeleteFile | ApplyPatchCallOperationUpdateFile` Instruction for creating a new file via the apply_patch tool. - `ApplyPatchCallOperationCreateFile` Instruction for creating a new file via the apply_patch tool. - `diff: string` - `path: string` - `type: "create_file"` - `"create_file"` - `ApplyPatchCallOperationDeleteFile` Instruction for deleting an existing file via the apply_patch tool. - `path: string` - `type: "delete_file"` - `"delete_file"` - `ApplyPatchCallOperationUpdateFile` Instruction for updating an existing file via the apply_patch tool. - `diff: string` - `path: string` - `type: "update_file"` - `"update_file"` - `status: "in_progress" | "completed"` - `"in_progress"` - `"completed"` - `type: "apply_patch_call"` - `"apply_patch_call"` - `id?: string` - `ApplyPatchCallOutput` The streamed output emitted by an apply patch tool call. - `call_id: string` - `status: "completed" | "failed"` - `"completed"` - `"failed"` - `type: "apply_patch_call_output"` - `"apply_patch_call_output"` - `id?: string` - `output?: string` - `OpenAITypesResponsesResponseInputItemMcpListTools` A list of tools available on an MCP server. - `id: string` - `server_label: string` - `tools: Array` - `input_schema: unknown` - `name: string` - `annotations?: unknown` - `description?: string` - `type: "mcp_list_tools"` - `"mcp_list_tools"` - `error?: string` - `McpApprovalRequest` A request for human approval of a tool invocation. - `OpenAITypesResponsesResponseInputItemMcpApprovalResponse` A response to an MCP approval request. - `approval_request_id: string` - `approve: boolean` - `type: "mcp_approval_response"` - `"mcp_approval_response"` - `id?: string` - `reason?: string` - `OpenAITypesResponsesResponseInputItemMcpCall` An invocation of a tool on an MCP server. - `id: string` - `arguments: string` - `name: string` - `server_label: string` - `type: "mcp_call"` - `"mcp_call"` - `approval_request_id?: string` - `error?: string` - `output?: string` - `status?: "in_progress" | "completed" | "incomplete" | 2 more` - `"in_progress"` - `"completed"` - `"incomplete"` - `"calling"` - `"failed"` - `OpenAIResponseCustomToolCallOutput` The output of a custom tool call from your code, being sent back to the model. - `call_id: string` - `output: string | Array` - `string` - `Array` - `OpenAIResponseInputText` A text input to the model. - `OpenAIResponseInputImage` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `OpenAIResponseInputFile` A file input to the model. - `type: "custom_tool_call_output"` - `"custom_tool_call_output"` - `id?: string` - `OpenAIResponseCustomToolCall` A call to a custom tool created by the model. - `OpenAITypesResponsesResponseInputItemItemReference` An internal identifier for an item to reference. - `id: string` - `type?: "item_reference"` - `"item_reference"` - `max_output_tokens?: number` - `max_tool_calls?: number` - `metadata?: Record` - `previous_response_id?: string` - `prompt?: OpenAIResponsePrompt` Reference to a prompt template and its variables. [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). - `id: string` - `variables?: Record` - `string` - `OpenAIResponseInputText` A text input to the model. - `OpenAIResponseInputImage` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `OpenAIResponseInputFile` A file input to the model. - `version?: string` - `prompt_cache_key?: string` - `prompt_cache_retention?: "in-memory" | "24h"` - `"in-memory"` - `"24h"` - `reasoning?: Reasoning` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - `effort?: "none" | "minimal" | "low" | 3 more` - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `generate_summary?: "auto" | "concise" | "detailed"` - `"auto"` - `"concise"` - `"detailed"` - `summary?: "auto" | "concise" | "detailed"` - `"auto"` - `"concise"` - `"detailed"` - `safety_identifier?: string` - `service_tier?: "auto" | "default" | "flex" | 2 more` - `"auto"` - `"default"` - `"flex"` - `"scale"` - `"priority"` - `status?: "completed" | "failed" | "in_progress" | 3 more` - `"completed"` - `"failed"` - `"in_progress"` - `"cancelled"` - `"queued"` - `"incomplete"` - `temperature?: number` - `text?: OpenAIResponseTextConfig` Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - [Text inputs and outputs](https://platform.openai.com/docs/guides/text) - [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs) - `format?: ResponseFormatText | ResponseFormatTextJsonSchemaConfig | ResponseFormatJsonObject` Default response format. Used to generate text responses. - `ResponseFormatText` Default response format. Used to generate text responses. - `type: "text"` - `"text"` - `ResponseFormatTextJsonSchemaConfig` JSON Schema response format. Used to generate structured JSON responses. Learn more about [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs). - `name: string` - `schema: Record` - `type: "json_schema"` - `"json_schema"` - `description?: string` - `strict?: boolean` - `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. - `type: "json_object"` - `"json_object"` - `verbosity?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `top_logprobs?: number` - `top_p?: number` - `truncation?: "auto" | "disabled"` - `"auto"` - `"disabled"` - `usage?: OpenAIResponseUsage` Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used. - `input_tokens: number` - `input_tokens_details: InputTokensDetails` A detailed breakdown of the input tokens. - `cached_tokens: number` - `output_tokens: number` - `output_tokens_details: OutputTokensDetails` A detailed breakdown of the output tokens. - `reasoning_tokens: number` - `total_tokens: number` - `user?: string` ### OpenAI Response Code Interpreter Tool Call - `OpenAIResponseCodeInterpreterToolCall` A tool call to run code. - `id: string` - `container_id: string` - `status: "in_progress" | "completed" | "incomplete" | 2 more` - `"in_progress"` - `"completed"` - `"incomplete"` - `"interpreting"` - `"failed"` - `type: "code_interpreter_call"` - `"code_interpreter_call"` - `code?: string` - `outputs?: Array` - `OutputLogs` The logs output from the code interpreter. - `logs: string` - `type: "logs"` - `"logs"` - `OutputImage` The image output from the code interpreter. - `type: "image"` - `"image"` - `url: string` ### OpenAI Response Computer Tool Call - `OpenAIResponseComputerToolCall` A tool call to a computer use tool. See the [computer use guide](https://platform.openai.com/docs/guides/tools-computer-use) for more information. - `id: string` - `action: ActionClick | ActionDoubleClick | ActionDrag | 6 more` A click action. - `ActionClick` A click action. - `button: "left" | "right" | "wheel" | 2 more` - `"left"` - `"right"` - `"wheel"` - `"back"` - `"forward"` - `type: "click"` - `"click"` - `x: number` - `y: number` - `ActionDoubleClick` A double click action. - `type: "double_click"` - `"double_click"` - `x: number` - `y: number` - `ActionDrag` A drag action. - `path: Array` - `x: number` - `y: number` - `type: "drag"` - `"drag"` - `ActionKeypress` A collection of keypresses the model would like to perform. - `keys: Array` - `type: "keypress"` - `"keypress"` - `ActionMove` A mouse move action. - `type: "move"` - `"move"` - `x: number` - `y: number` - `ActionScreenshot` A screenshot action. - `type: "screenshot"` - `"screenshot"` - `ActionScroll` A scroll action. - `scroll_x: number` - `scroll_y: number` - `type: "scroll"` - `"scroll"` - `x: number` - `y: number` - `ActionType` An action to type in text. - `text: string` - `type: "type"` - `"type"` - `ActionWait` A wait action. - `type: "wait"` - `"wait"` - `call_id: string` - `pending_safety_checks: Array` - `id: string` - `code?: string` - `message?: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "computer_call"` - `"computer_call"` ### OpenAI Response Custom Tool Call - `OpenAIResponseCustomToolCall` A call to a custom tool created by the model. - `call_id: string` - `input: string` - `name: string` - `type: "custom_tool_call"` - `"custom_tool_call"` - `id?: string` ### OpenAI Response Custom Tool Call Output - `OpenAIResponseCustomToolCallOutput` The output of a custom tool call from your code, being sent back to the model. - `call_id: string` - `output: string | Array` - `string` - `Array` - `OpenAIResponseInputText` A text input to the model. - `text: string` - `type: "input_text"` - `"input_text"` - `OpenAIResponseInputImage` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `detail: "low" | "high" | "auto"` - `"low"` - `"high"` - `"auto"` - `type: "input_image"` - `"input_image"` - `file_id?: string` - `image_url?: string` - `OpenAIResponseInputFile` A file input to the model. - `type: "input_file"` - `"input_file"` - `file_data?: string` - `file_id?: string` - `file_url?: string` - `filename?: string` - `type: "custom_tool_call_output"` - `"custom_tool_call_output"` - `id?: string` ### OpenAI Response Error - `OpenAIResponseError` An error object returned when the model fails to generate a Response. - `code: "server_error" | "rate_limit_exceeded" | "invalid_prompt" | 15 more` - `"server_error"` - `"rate_limit_exceeded"` - `"invalid_prompt"` - `"vector_store_timeout"` - `"invalid_image"` - `"invalid_image_format"` - `"invalid_base64_image"` - `"invalid_image_url"` - `"image_too_large"` - `"image_too_small"` - `"image_parse_error"` - `"image_content_policy_violation"` - `"invalid_image_mode"` - `"image_file_too_large"` - `"unsupported_image_media_type"` - `"empty_image_file"` - `"failed_to_download_image"` - `"image_file_not_found"` - `message: string` ### OpenAI Response File Search Tool Call - `OpenAIResponseFileSearchToolCall` The results of a file search tool call. See the [file search guide](https://platform.openai.com/docs/guides/tools-file-search) for more information. - `id: string` - `queries: Array` - `status: "in_progress" | "searching" | "completed" | 2 more` - `"in_progress"` - `"searching"` - `"completed"` - `"incomplete"` - `"failed"` - `type: "file_search_call"` - `"file_search_call"` - `results?: Array` - `attributes?: Record` - `string` - `number` - `boolean` - `file_id?: string` - `filename?: string` - `score?: number` - `text?: string` ### OpenAI Response Function Tool Call - `OpenAIResponseFunctionToolCall` A tool call to run a function. See the [function calling guide](https://platform.openai.com/docs/guides/function-calling) for more information. - `arguments: string` - `call_id: string` - `name: string` - `type: "function_call"` - `"function_call"` - `id?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` ### OpenAI Response Function Web Search - `OpenAIResponseFunctionWebSearch` The results of a web search tool call. See the [web search guide](https://platform.openai.com/docs/guides/tools-web-search) for more information. - `id: string` - `action: OpenAITypesResponsesResponseFunctionWebSearchActionSearch | OpenAITypesResponsesResponseFunctionWebSearchActionOpenPage | ActionFind` Action type "search" - Performs a web search query. - `OpenAITypesResponsesResponseFunctionWebSearchActionSearch` Action type "search" - Performs a web search query. - `query: string` - `type: "search"` - `"search"` - `queries?: Array` - `sources?: Array` - `type: "url"` - `"url"` - `url: string` - `OpenAITypesResponsesResponseFunctionWebSearchActionOpenPage` Action type "open_page" - Opens a specific URL from search results. - `type: "open_page"` - `"open_page"` - `url?: string` - `ActionFind` Action type "find_in_page": Searches for a pattern within a loaded page. - `pattern: string` - `type: "find_in_page"` - `"find_in_page"` - `url: string` - `status: "in_progress" | "searching" | "completed" | "failed"` - `"in_progress"` - `"searching"` - `"completed"` - `"failed"` - `type: "web_search_call"` - `"web_search_call"` ### OpenAI Response Input File - `OpenAIResponseInputFile` A file input to the model. - `type: "input_file"` - `"input_file"` - `file_data?: string` - `file_id?: string` - `file_url?: string` - `filename?: string` ### OpenAI Response Input File Param - `OpenAIResponseInputFileParam` A file input to the model. - `type: "input_file"` - `"input_file"` - `file_data?: string` - `file_id?: string` - `file_url?: string` - `filename?: string` ### OpenAI Response Input Image - `OpenAIResponseInputImage` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `detail: "low" | "high" | "auto"` - `"low"` - `"high"` - `"auto"` - `type: "input_image"` - `"input_image"` - `file_id?: string` - `image_url?: string` ### OpenAI Response Input Image Param - `OpenAIResponseInputImageParam` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `detail: "low" | "high" | "auto"` - `"low"` - `"high"` - `"auto"` - `type: "input_image"` - `"input_image"` - `file_id?: string` - `image_url?: string` ### OpenAI Response Input Text - `OpenAIResponseInputText` A text input to the model. - `text: string` - `type: "input_text"` - `"input_text"` ### OpenAI Response Input Text Param - `OpenAIResponseInputTextParam` A text input to the model. - `text: string` - `type: "input_text"` - `"input_text"` ### OpenAI Response Output Message - `OpenAIResponseOutputMessage` An output message from the model. - `id: string` - `content: Array` - `OpenAIResponseOutputText` A text output from the model. - `annotations: Array` - `AnnotationFileCitation` A citation to a file. - `file_id: string` - `filename: string` - `index: number` - `type: "file_citation"` - `"file_citation"` - `OpenAITypesResponsesResponseOutputTextAnnotationURLCitation` A citation for a web resource used to generate a model response. - `end_index: number` - `start_index: number` - `title: string` - `type: "url_citation"` - `"url_citation"` - `url: string` - `AnnotationContainerFileCitation` A citation for a container file used to generate a model response. - `container_id: string` - `end_index: number` - `file_id: string` - `filename: string` - `start_index: number` - `type: "container_file_citation"` - `"container_file_citation"` - `AnnotationFilePath` A path to a file. - `file_id: string` - `index: number` - `type: "file_path"` - `"file_path"` - `text: string` - `type: "output_text"` - `"output_text"` - `logprobs?: Array` - `token: string` - `bytes: Array` - `logprob: number` - `top_logprobs: Array` - `token: string` - `bytes: Array` - `logprob: number` - `OpenAIResponseOutputRefusal` A refusal from the model. - `refusal: string` - `type: "refusal"` - `"refusal"` - `role: "assistant"` - `"assistant"` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "message"` - `"message"` - `phase?: "commentary" | "final_answer"` - `"commentary"` - `"final_answer"` ### OpenAI Response Output Refusal - `OpenAIResponseOutputRefusal` A refusal from the model. - `refusal: string` - `type: "refusal"` - `"refusal"` ### OpenAI Response Output Text - `OpenAIResponseOutputText` A text output from the model. - `annotations: Array` - `AnnotationFileCitation` A citation to a file. - `file_id: string` - `filename: string` - `index: number` - `type: "file_citation"` - `"file_citation"` - `OpenAITypesResponsesResponseOutputTextAnnotationURLCitation` A citation for a web resource used to generate a model response. - `end_index: number` - `start_index: number` - `title: string` - `type: "url_citation"` - `"url_citation"` - `url: string` - `AnnotationContainerFileCitation` A citation for a container file used to generate a model response. - `container_id: string` - `end_index: number` - `file_id: string` - `filename: string` - `start_index: number` - `type: "container_file_citation"` - `"container_file_citation"` - `AnnotationFilePath` A path to a file. - `file_id: string` - `index: number` - `type: "file_path"` - `"file_path"` - `text: string` - `type: "output_text"` - `"output_text"` - `logprobs?: Array` - `token: string` - `bytes: Array` - `logprob: number` - `top_logprobs: Array` - `token: string` - `bytes: Array` - `logprob: number` ### OpenAI Response Prompt - `OpenAIResponsePrompt` Reference to a prompt template and its variables. [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). - `id: string` - `variables?: Record` - `string` - `OpenAIResponseInputText` A text input to the model. - `text: string` - `type: "input_text"` - `"input_text"` - `OpenAIResponseInputImage` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `detail: "low" | "high" | "auto"` - `"low"` - `"high"` - `"auto"` - `type: "input_image"` - `"input_image"` - `file_id?: string` - `image_url?: string` - `OpenAIResponseInputFile` A file input to the model. - `type: "input_file"` - `"input_file"` - `file_data?: string` - `file_id?: string` - `file_url?: string` - `filename?: string` - `version?: string` ### OpenAI Response Reasoning Item - `OpenAIResponseReasoningItem` 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](https://platform.openai.com/docs/guides/conversation-state). - `id: string` - `summary: Array` - `text: string` - `type: "summary_text"` - `"summary_text"` - `type: "reasoning"` - `"reasoning"` - `content?: Array` - `text: string` - `type: "reasoning_text"` - `"reasoning_text"` - `encrypted_content?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` ### OpenAI Response Text Config - `OpenAIResponseTextConfig` Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - [Text inputs and outputs](https://platform.openai.com/docs/guides/text) - [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs) - `format?: ResponseFormatText | ResponseFormatTextJsonSchemaConfig | ResponseFormatJsonObject` Default response format. Used to generate text responses. - `ResponseFormatText` Default response format. Used to generate text responses. - `type: "text"` - `"text"` - `ResponseFormatTextJsonSchemaConfig` JSON Schema response format. Used to generate structured JSON responses. Learn more about [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs). - `name: string` - `schema: Record` - `type: "json_schema"` - `"json_schema"` - `description?: string` - `strict?: boolean` - `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. - `type: "json_object"` - `"json_object"` - `verbosity?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` ### OpenAI Response Usage - `OpenAIResponseUsage` Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used. - `input_tokens: number` - `input_tokens_details: InputTokensDetails` A detailed breakdown of the input tokens. - `cached_tokens: number` - `output_tokens: number` - `output_tokens_details: OutputTokensDetails` A detailed breakdown of the output tokens. - `reasoning_tokens: number` - `total_tokens: number` ### OpenAI Types Responses Response Input Item Computer Call Output - `OpenAITypesResponsesResponseInputItemComputerCallOutput` The output of a computer tool call. - `call_id: string` - `output: ResponseComputerToolCallOutputScreenshot` A computer screenshot image used with the computer use tool. - `type: "computer_screenshot"` - `"computer_screenshot"` - `file_id?: string` - `image_url?: string` - `type: "computer_call_output"` - `"computer_call_output"` - `id?: string` - `acknowledged_safety_checks?: Array` - `id: string` - `code?: string` - `message?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` ### OpenAI Types Responses Response Input Item Function Call Output - `OpenAITypesResponsesResponseInputItemFunctionCallOutput` The output of a function tool call. - `call_id: string` - `output: string | Array` - `string` - `Array` - `ResponseInputTextContent` A text input to the model. - `text: string` - `type: "input_text"` - `"input_text"` - `ResponseInputImageContent` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision) - `type: "input_image"` - `"input_image"` - `detail?: "low" | "high" | "auto"` - `"low"` - `"high"` - `"auto"` - `file_id?: string` - `image_url?: string` - `ResponseInputFileContent` A file input to the model. - `type: "input_file"` - `"input_file"` - `file_data?: string` - `file_id?: string` - `file_url?: string` - `filename?: string` - `type: "function_call_output"` - `"function_call_output"` - `id?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` ### OpenAI Types Responses Response Input Item Image Generation Call - `OpenAITypesResponsesResponseInputItemImageGenerationCall` An image generation request made by the model. - `id: string` - `status: "in_progress" | "completed" | "generating" | "failed"` - `"in_progress"` - `"completed"` - `"generating"` - `"failed"` - `type: "image_generation_call"` - `"image_generation_call"` - `result?: string` ### OpenAI Types Responses Response Input Item Item Reference - `OpenAITypesResponsesResponseInputItemItemReference` An internal identifier for an item to reference. - `id: string` - `type?: "item_reference"` - `"item_reference"` ### OpenAI Types Responses Response Input Item Local Shell Call - `OpenAITypesResponsesResponseInputItemLocalShellCall` A tool call to run a command on the local shell. - `id: string` - `action: Action` Execute a shell command on the server. - `command: Array` - `env: Record` - `type: "exec"` - `"exec"` - `timeout_ms?: number` - `user?: string` - `working_directory?: string` - `call_id: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "local_shell_call"` - `"local_shell_call"` ### OpenAI Types Responses Response Input Item Local Shell Call Output - `OpenAITypesResponsesResponseInputItemLocalShellCallOutput` The output of a local shell tool call. - `id: string` - `output: string` - `type: "local_shell_call_output"` - `"local_shell_call_output"` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` ### OpenAI Types Responses Response Input Item Mcp Approval Response - `OpenAITypesResponsesResponseInputItemMcpApprovalResponse` A response to an MCP approval request. - `approval_request_id: string` - `approve: boolean` - `type: "mcp_approval_response"` - `"mcp_approval_response"` - `id?: string` - `reason?: string` ### OpenAI Types Responses Response Input Item Mcp Call - `OpenAITypesResponsesResponseInputItemMcpCall` An invocation of a tool on an MCP server. - `id: string` - `arguments: string` - `name: string` - `server_label: string` - `type: "mcp_call"` - `"mcp_call"` - `approval_request_id?: string` - `error?: string` - `output?: string` - `status?: "in_progress" | "completed" | "incomplete" | 2 more` - `"in_progress"` - `"completed"` - `"incomplete"` - `"calling"` - `"failed"` ### OpenAI Types Responses Response Input Item Mcp List Tools - `OpenAITypesResponsesResponseInputItemMcpListTools` A list of tools available on an MCP server. - `id: string` - `server_label: string` - `tools: Array` - `input_schema: unknown` - `name: string` - `annotations?: unknown` - `description?: string` - `type: "mcp_list_tools"` - `"mcp_list_tools"` - `error?: string` ### OpenAI Types Responses Response Input Item Message - `OpenAITypesResponsesResponseInputItemMessage` 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. - `content: Array` - `OpenAIResponseInputText` A text input to the model. - `text: string` - `type: "input_text"` - `"input_text"` - `OpenAIResponseInputImage` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `detail: "low" | "high" | "auto"` - `"low"` - `"high"` - `"auto"` - `type: "input_image"` - `"input_image"` - `file_id?: string` - `image_url?: string` - `OpenAIResponseInputFile` A file input to the model. - `type: "input_file"` - `"input_file"` - `file_data?: string` - `file_id?: string` - `file_url?: string` - `filename?: string` - `role: "user" | "system" | "developer"` - `"user"` - `"system"` - `"developer"` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type?: "message"` - `"message"` ### OpenAI Types Responses Response Output Item Image Generation Call - `OpenAITypesResponsesResponseOutputItemImageGenerationCall` An image generation request made by the model. - `id: string` - `status: "in_progress" | "completed" | "generating" | "failed"` - `"in_progress"` - `"completed"` - `"generating"` - `"failed"` - `type: "image_generation_call"` - `"image_generation_call"` - `result?: string` ### OpenAI Types Responses Response Output Item Local Shell Call - `OpenAITypesResponsesResponseOutputItemLocalShellCall` A tool call to run a command on the local shell. - `id: string` - `action: Action` Execute a shell command on the server. - `command: Array` - `env: Record` - `type: "exec"` - `"exec"` - `timeout_ms?: number` - `user?: string` - `working_directory?: string` - `call_id: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "local_shell_call"` - `"local_shell_call"` ### OpenAI Types Responses Response Output Item Mcp Call - `OpenAITypesResponsesResponseOutputItemMcpCall` An invocation of a tool on an MCP server. - `id: string` - `arguments: string` - `name: string` - `server_label: string` - `type: "mcp_call"` - `"mcp_call"` - `approval_request_id?: string` - `error?: string` - `output?: string` - `status?: "in_progress" | "completed" | "incomplete" | 2 more` - `"in_progress"` - `"completed"` - `"incomplete"` - `"calling"` - `"failed"` ### OpenAI Types Responses Response Output Item Mcp List Tools - `OpenAITypesResponsesResponseOutputItemMcpListTools` A list of tools available on an MCP server. - `id: string` - `server_label: string` - `tools: Array` - `input_schema: unknown` - `name: string` - `annotations?: unknown` - `description?: string` - `type: "mcp_list_tools"` - `"mcp_list_tools"` - `error?: string` ### Part Reasoning Text - `PartReasoningText` Reasoning text from the model. - `text: string` - `type: "reasoning_text"` - `"reasoning_text"` ### Reasoning - `Reasoning` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - `effort?: "none" | "minimal" | "low" | 3 more` - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `generate_summary?: "auto" | "concise" | "detailed"` - `"auto"` - `"concise"` - `"detailed"` - `summary?: "auto" | "concise" | "detailed"` - `"auto"` - `"concise"` - `"detailed"` ### Response Apply Patch Tool Call - `ResponseApplyPatchToolCall` A tool call that applies file diffs by creating, deleting, or updating files. - `id: string` - `call_id: string` - `operation: OperationCreateFile | OperationDeleteFile | OperationUpdateFile` Instruction describing how to create a file via the apply_patch tool. - `OperationCreateFile` Instruction describing how to create a file via the apply_patch tool. - `diff: string` - `path: string` - `type: "create_file"` - `"create_file"` - `OperationDeleteFile` Instruction describing how to delete a file via the apply_patch tool. - `path: string` - `type: "delete_file"` - `"delete_file"` - `OperationUpdateFile` Instruction describing how to update a file via the apply_patch tool. - `diff: string` - `path: string` - `type: "update_file"` - `"update_file"` - `status: "in_progress" | "completed"` - `"in_progress"` - `"completed"` - `type: "apply_patch_call"` - `"apply_patch_call"` - `created_by?: string` ### Response Apply Patch Tool Call Output - `ResponseApplyPatchToolCallOutput` The output emitted by an apply patch tool call. - `id: string` - `call_id: string` - `status: "completed" | "failed"` - `"completed"` - `"failed"` - `type: "apply_patch_call_output"` - `"apply_patch_call_output"` - `created_by?: string` - `output?: string` ### Response Compaction Item - `ResponseCompactionItem` A compaction item generated by the [`v1/responses/compact` API](https://platform.openai.com/docs/api-reference/responses/compact). - `id: string` - `encrypted_content: string` - `type: "compaction"` - `"compaction"` - `created_by?: string` ### Response Compaction Item Param - `ResponseCompactionItemParam` A compaction item generated by the [`v1/responses/compact` API](https://platform.openai.com/docs/api-reference/responses/compact). - `encrypted_content: string` - `type: "compaction"` - `"compaction"` - `id?: string` ### Response Computer Tool Call Output Screenshot - `ResponseComputerToolCallOutputScreenshot` A computer screenshot image used with the computer use tool. - `type: "computer_screenshot"` - `"computer_screenshot"` - `file_id?: string` - `image_url?: string` ### Response Function Shell Tool Call - `ResponseFunctionShellToolCall` A tool call that executes one or more shell commands in a managed environment. - `id: string` - `action: Action` The shell commands and limits that describe how to run the tool call. - `commands: Array` - `max_output_length?: number` - `timeout_ms?: number` - `call_id: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "shell_call"` - `"shell_call"` - `created_by?: string` - `environment?: ResponseLocalEnvironment | ResponseContainerReference` Represents the use of a local environment to perform shell actions. - `ResponseLocalEnvironment` Represents the use of a local environment to perform shell actions. - `type: "local"` - `"local"` - `ResponseContainerReference` Represents a container created with /v1/containers. - `container_id: string` - `type: "container_reference"` - `"container_reference"` ### Response Function Shell Tool Call Output - `ResponseFunctionShellToolCallOutput` The output of a shell tool call that was emitted. - `id: string` - `call_id: string` - `output: Array` - `outcome: OutputOutcomeTimeout | OutputOutcomeExit` Indicates that the shell call exceeded its configured time limit. - `OutputOutcomeTimeout` Indicates that the shell call exceeded its configured time limit. - `type: "timeout"` - `"timeout"` - `OutputOutcomeExit` Indicates that the shell commands finished and returned an exit code. - `exit_code: number` - `type: "exit"` - `"exit"` - `stderr: string` - `stdout: string` - `created_by?: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "shell_call_output"` - `"shell_call_output"` - `created_by?: string` - `max_output_length?: number` ### Shell Call - `ShellCall` A tool representing a request to execute one or more shell commands. - `action: Action` The shell commands and limits that describe how to run the tool call. - `commands: Array` - `max_output_length?: number` - `timeout_ms?: number` - `call_id: string` - `type: "shell_call"` - `"shell_call"` - `id?: string` - `environment?: LocalEnvironment | ContainerReference` - `LocalEnvironment` - `type: "local"` - `"local"` - `skills?: Array` - `description: string` - `name: string` - `path: string` - `ContainerReference` - `container_id: string` - `type: "container_reference"` - `"container_reference"` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` ### Shell Call Output - `ShellCallOutput` The streamed output items emitted by a shell tool call. - `call_id: string` - `output: Array` - `outcome: OutcomeTimeout | OutcomeExit` Indicates that the shell call exceeded its configured time limit. - `OutcomeTimeout` Indicates that the shell call exceeded its configured time limit. - `type: "timeout"` - `"timeout"` - `OutcomeExit` Indicates that the shell commands finished and returned an exit code. - `exit_code: number` - `type: "exit"` - `"exit"` - `stderr: string` - `stdout: string` - `type: "shell_call_output"` - `"shell_call_output"` - `id?: string` - `max_output_length?: number` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` ### Tool Choice Allowed - `ToolChoiceAllowed` Constrains the tools available to the model to a pre-defined set. - `mode: "auto" | "required"` - `"auto"` - `"required"` - `tools: Array>` - `type: "allowed_tools"` - `"allowed_tools"` ### Tool Choice Apply Patch - `ToolChoiceApplyPatch` Forces the model to call the apply_patch tool when executing a tool call. - `type: "apply_patch"` - `"apply_patch"` ### Tool Choice Custom - `ToolChoiceCustom` Use this option to force the model to call a specific custom tool. - `name: string` - `type: "custom"` - `"custom"` ### Tool Choice Function - `ToolChoiceFunction` Use this option to force the model to call a specific function. - `name: string` - `type: "function"` - `"function"` ### Tool Choice Mcp - `ToolChoiceMcp` Use this option to force the model to call a specific tool on a remote MCP server. - `server_label: string` - `type: "mcp"` - `"mcp"` - `name?: string` ### Tool Choice Shell - `ToolChoiceShell` Forces the model to call the shell tool when a tool call is required. - `type: "shell"` - `"shell"` ### Tool Choice Types - `ToolChoiceTypes` Indicates that the model should use a built-in tool to generate a response. [Learn more about built-in tools](https://platform.openai.com/docs/guides/tools). - `type: "file_search" | "web_search_preview" | "computer_use_preview" | 3 more` - `"file_search"` - `"web_search_preview"` - `"computer_use_preview"` - `"web_search_preview_2025_03_11"` - `"image_generation"` - `"code_interpreter"` ### Web Search Preview Tool - `WebSearchPreviewTool` This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search). - `type: "web_search_preview" | "web_search_preview_2025_03_11"` - `"web_search_preview"` - `"web_search_preview_2025_03_11"` - `search_context_size?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `user_location?: UserLocation` The user's location. - `type: "approximate"` - `"approximate"` - `city?: string` - `country?: string` - `region?: string` - `timezone?: string` ### Web Search Tool - `WebSearchTool` Search the Internet for sources related to the prompt. Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search). - `type: "web_search" | "web_search_2025_08_26"` - `"web_search"` - `"web_search_2025_08_26"` - `filters?: Filters` Filters for the search. - `allowed_domains?: Array` - `search_context_size?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `user_location?: UserLocation` The approximate location of the user. - `city?: string` - `country?: string` - `region?: string` - `timezone?: string` - `type?: "approximate"` - `"approximate"` ### Response Create Response - `ResponseCreateResponse = OpenAIResponse | ResponseAudioDeltaEvent | ResponseAudioDoneEvent | 52 more` Emitted when there is a partial audio response. - `OpenAIResponse` - `id: string` - `created_at: number` - `model: "gpt-5.2" | "gpt-5.2-2025-12-11" | "gpt-5.2-chat-latest" | 83 more | (string & {})` - `"gpt-5.2" | "gpt-5.2-2025-12-11" | "gpt-5.2-chat-latest" | 83 more` - `"gpt-5.2"` - `"gpt-5.2-2025-12-11"` - `"gpt-5.2-chat-latest"` - `"gpt-5.2-pro"` - `"gpt-5.2-pro-2025-12-11"` - `"gpt-5.1"` - `"gpt-5.1-2025-11-13"` - `"gpt-5.1-codex"` - `"gpt-5.1-mini"` - `"gpt-5.1-chat-latest"` - `"gpt-5"` - `"gpt-5-mini"` - `"gpt-5-nano"` - `"gpt-5-2025-08-07"` - `"gpt-5-mini-2025-08-07"` - `"gpt-5-nano-2025-08-07"` - `"gpt-5-chat-latest"` - `"gpt-4.1"` - `"gpt-4.1-mini"` - `"gpt-4.1-nano"` - `"gpt-4.1-2025-04-14"` - `"gpt-4.1-mini-2025-04-14"` - `"gpt-4.1-nano-2025-04-14"` - `"o4-mini"` - `"o4-mini-2025-04-16"` - `"o3"` - `"o3-2025-04-16"` - `"o3-mini"` - `"o3-mini-2025-01-31"` - `"o1"` - `"o1-2024-12-17"` - `"o1-preview"` - `"o1-preview-2024-09-12"` - `"o1-mini"` - `"o1-mini-2024-09-12"` - `"gpt-4o"` - `"gpt-4o-2024-11-20"` - `"gpt-4o-2024-08-06"` - `"gpt-4o-2024-05-13"` - `"gpt-4o-audio-preview"` - `"gpt-4o-audio-preview-2024-10-01"` - `"gpt-4o-audio-preview-2024-12-17"` - `"gpt-4o-audio-preview-2025-06-03"` - `"gpt-4o-mini-audio-preview"` - `"gpt-4o-mini-audio-preview-2024-12-17"` - `"gpt-4o-search-preview"` - `"gpt-4o-mini-search-preview"` - `"gpt-4o-search-preview-2025-03-11"` - `"gpt-4o-mini-search-preview-2025-03-11"` - `"chatgpt-4o-latest"` - `"codex-mini-latest"` - `"gpt-4o-mini"` - `"gpt-4o-mini-2024-07-18"` - `"gpt-4-turbo"` - `"gpt-4-turbo-2024-04-09"` - `"gpt-4-0125-preview"` - `"gpt-4-turbo-preview"` - `"gpt-4-1106-preview"` - `"gpt-4-vision-preview"` - `"gpt-4"` - `"gpt-4-0314"` - `"gpt-4-0613"` - `"gpt-4-32k"` - `"gpt-4-32k-0314"` - `"gpt-4-32k-0613"` - `"gpt-3.5-turbo"` - `"gpt-3.5-turbo-16k"` - `"gpt-3.5-turbo-0301"` - `"gpt-3.5-turbo-0613"` - `"gpt-3.5-turbo-1106"` - `"gpt-3.5-turbo-0125"` - `"gpt-3.5-turbo-16k-0613"` - `"o1-pro"` - `"o1-pro-2025-03-19"` - `"o3-pro"` - `"o3-pro-2025-06-10"` - `"o3-deep-research"` - `"o3-deep-research-2025-06-26"` - `"o4-mini-deep-research"` - `"o4-mini-deep-research-2025-06-26"` - `"computer-use-preview"` - `"computer-use-preview-2025-03-11"` - `"gpt-5-codex"` - `"gpt-5-pro"` - `"gpt-5-pro-2025-10-06"` - `"gpt-5.1-codex-max"` - `(string & {})` - `object: "response"` - `"response"` - `output: Array` - `OpenAIResponseOutputMessage` An output message from the model. - `id: string` - `content: Array` - `OpenAIResponseOutputText` A text output from the model. - `annotations: Array` - `AnnotationFileCitation` A citation to a file. - `file_id: string` - `filename: string` - `index: number` - `type: "file_citation"` - `"file_citation"` - `OpenAITypesResponsesResponseOutputTextAnnotationURLCitation` A citation for a web resource used to generate a model response. - `end_index: number` - `start_index: number` - `title: string` - `type: "url_citation"` - `"url_citation"` - `url: string` - `AnnotationContainerFileCitation` A citation for a container file used to generate a model response. - `container_id: string` - `end_index: number` - `file_id: string` - `filename: string` - `start_index: number` - `type: "container_file_citation"` - `"container_file_citation"` - `AnnotationFilePath` A path to a file. - `file_id: string` - `index: number` - `type: "file_path"` - `"file_path"` - `text: string` - `type: "output_text"` - `"output_text"` - `logprobs?: Array` - `token: string` - `bytes: Array` - `logprob: number` - `top_logprobs: Array` - `token: string` - `bytes: Array` - `logprob: number` - `OpenAIResponseOutputRefusal` A refusal from the model. - `refusal: string` - `type: "refusal"` - `"refusal"` - `role: "assistant"` - `"assistant"` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "message"` - `"message"` - `phase?: "commentary" | "final_answer"` - `"commentary"` - `"final_answer"` - `OpenAIResponseFileSearchToolCall` The results of a file search tool call. See the [file search guide](https://platform.openai.com/docs/guides/tools-file-search) for more information. - `id: string` - `queries: Array` - `status: "in_progress" | "searching" | "completed" | 2 more` - `"in_progress"` - `"searching"` - `"completed"` - `"incomplete"` - `"failed"` - `type: "file_search_call"` - `"file_search_call"` - `results?: Array` - `attributes?: Record` - `string` - `number` - `boolean` - `file_id?: string` - `filename?: string` - `score?: number` - `text?: string` - `OpenAIResponseFunctionToolCall` A tool call to run a function. See the [function calling guide](https://platform.openai.com/docs/guides/function-calling) for more information. - `arguments: string` - `call_id: string` - `name: string` - `type: "function_call"` - `"function_call"` - `id?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `OpenAIResponseFunctionWebSearch` The results of a web search tool call. See the [web search guide](https://platform.openai.com/docs/guides/tools-web-search) for more information. - `id: string` - `action: OpenAITypesResponsesResponseFunctionWebSearchActionSearch | OpenAITypesResponsesResponseFunctionWebSearchActionOpenPage | ActionFind` Action type "search" - Performs a web search query. - `OpenAITypesResponsesResponseFunctionWebSearchActionSearch` Action type "search" - Performs a web search query. - `query: string` - `type: "search"` - `"search"` - `queries?: Array` - `sources?: Array` - `type: "url"` - `"url"` - `url: string` - `OpenAITypesResponsesResponseFunctionWebSearchActionOpenPage` Action type "open_page" - Opens a specific URL from search results. - `type: "open_page"` - `"open_page"` - `url?: string` - `ActionFind` Action type "find_in_page": Searches for a pattern within a loaded page. - `pattern: string` - `type: "find_in_page"` - `"find_in_page"` - `url: string` - `status: "in_progress" | "searching" | "completed" | "failed"` - `"in_progress"` - `"searching"` - `"completed"` - `"failed"` - `type: "web_search_call"` - `"web_search_call"` - `OpenAIResponseComputerToolCall` A tool call to a computer use tool. See the [computer use guide](https://platform.openai.com/docs/guides/tools-computer-use) for more information. - `id: string` - `action: ActionClick | ActionDoubleClick | ActionDrag | 6 more` A click action. - `ActionClick` A click action. - `button: "left" | "right" | "wheel" | 2 more` - `"left"` - `"right"` - `"wheel"` - `"back"` - `"forward"` - `type: "click"` - `"click"` - `x: number` - `y: number` - `ActionDoubleClick` A double click action. - `type: "double_click"` - `"double_click"` - `x: number` - `y: number` - `ActionDrag` A drag action. - `path: Array` - `x: number` - `y: number` - `type: "drag"` - `"drag"` - `ActionKeypress` A collection of keypresses the model would like to perform. - `keys: Array` - `type: "keypress"` - `"keypress"` - `ActionMove` A mouse move action. - `type: "move"` - `"move"` - `x: number` - `y: number` - `ActionScreenshot` A screenshot action. - `type: "screenshot"` - `"screenshot"` - `ActionScroll` A scroll action. - `scroll_x: number` - `scroll_y: number` - `type: "scroll"` - `"scroll"` - `x: number` - `y: number` - `ActionType` An action to type in text. - `text: string` - `type: "type"` - `"type"` - `ActionWait` A wait action. - `type: "wait"` - `"wait"` - `call_id: string` - `pending_safety_checks: Array` - `id: string` - `code?: string` - `message?: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "computer_call"` - `"computer_call"` - `OpenAIResponseReasoningItem` 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](https://platform.openai.com/docs/guides/conversation-state). - `id: string` - `summary: Array` - `text: string` - `type: "summary_text"` - `"summary_text"` - `type: "reasoning"` - `"reasoning"` - `content?: Array` - `text: string` - `type: "reasoning_text"` - `"reasoning_text"` - `encrypted_content?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `ResponseCompactionItem` A compaction item generated by the [`v1/responses/compact` API](https://platform.openai.com/docs/api-reference/responses/compact). - `id: string` - `encrypted_content: string` - `type: "compaction"` - `"compaction"` - `created_by?: string` - `OpenAITypesResponsesResponseOutputItemImageGenerationCall` An image generation request made by the model. - `id: string` - `status: "in_progress" | "completed" | "generating" | "failed"` - `"in_progress"` - `"completed"` - `"generating"` - `"failed"` - `type: "image_generation_call"` - `"image_generation_call"` - `result?: string` - `OpenAIResponseCodeInterpreterToolCall` A tool call to run code. - `id: string` - `container_id: string` - `status: "in_progress" | "completed" | "incomplete" | 2 more` - `"in_progress"` - `"completed"` - `"incomplete"` - `"interpreting"` - `"failed"` - `type: "code_interpreter_call"` - `"code_interpreter_call"` - `code?: string` - `outputs?: Array` - `OutputLogs` The logs output from the code interpreter. - `logs: string` - `type: "logs"` - `"logs"` - `OutputImage` The image output from the code interpreter. - `type: "image"` - `"image"` - `url: string` - `OpenAITypesResponsesResponseOutputItemLocalShellCall` A tool call to run a command on the local shell. - `id: string` - `action: Action` Execute a shell command on the server. - `command: Array` - `env: Record` - `type: "exec"` - `"exec"` - `timeout_ms?: number` - `user?: string` - `working_directory?: string` - `call_id: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "local_shell_call"` - `"local_shell_call"` - `ResponseFunctionShellToolCall` A tool call that executes one or more shell commands in a managed environment. - `id: string` - `action: Action` The shell commands and limits that describe how to run the tool call. - `commands: Array` - `max_output_length?: number` - `timeout_ms?: number` - `call_id: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "shell_call"` - `"shell_call"` - `created_by?: string` - `environment?: ResponseLocalEnvironment | ResponseContainerReference` Represents the use of a local environment to perform shell actions. - `ResponseLocalEnvironment` Represents the use of a local environment to perform shell actions. - `type: "local"` - `"local"` - `ResponseContainerReference` Represents a container created with /v1/containers. - `container_id: string` - `type: "container_reference"` - `"container_reference"` - `ResponseFunctionShellToolCallOutput` The output of a shell tool call that was emitted. - `id: string` - `call_id: string` - `output: Array` - `outcome: OutputOutcomeTimeout | OutputOutcomeExit` Indicates that the shell call exceeded its configured time limit. - `OutputOutcomeTimeout` Indicates that the shell call exceeded its configured time limit. - `type: "timeout"` - `"timeout"` - `OutputOutcomeExit` Indicates that the shell commands finished and returned an exit code. - `exit_code: number` - `type: "exit"` - `"exit"` - `stderr: string` - `stdout: string` - `created_by?: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "shell_call_output"` - `"shell_call_output"` - `created_by?: string` - `max_output_length?: number` - `ResponseApplyPatchToolCall` A tool call that applies file diffs by creating, deleting, or updating files. - `id: string` - `call_id: string` - `operation: OperationCreateFile | OperationDeleteFile | OperationUpdateFile` Instruction describing how to create a file via the apply_patch tool. - `OperationCreateFile` Instruction describing how to create a file via the apply_patch tool. - `diff: string` - `path: string` - `type: "create_file"` - `"create_file"` - `OperationDeleteFile` Instruction describing how to delete a file via the apply_patch tool. - `path: string` - `type: "delete_file"` - `"delete_file"` - `OperationUpdateFile` Instruction describing how to update a file via the apply_patch tool. - `diff: string` - `path: string` - `type: "update_file"` - `"update_file"` - `status: "in_progress" | "completed"` - `"in_progress"` - `"completed"` - `type: "apply_patch_call"` - `"apply_patch_call"` - `created_by?: string` - `ResponseApplyPatchToolCallOutput` The output emitted by an apply patch tool call. - `id: string` - `call_id: string` - `status: "completed" | "failed"` - `"completed"` - `"failed"` - `type: "apply_patch_call_output"` - `"apply_patch_call_output"` - `created_by?: string` - `output?: string` - `OpenAITypesResponsesResponseOutputItemMcpCall` An invocation of a tool on an MCP server. - `id: string` - `arguments: string` - `name: string` - `server_label: string` - `type: "mcp_call"` - `"mcp_call"` - `approval_request_id?: string` - `error?: string` - `output?: string` - `status?: "in_progress" | "completed" | "incomplete" | 2 more` - `"in_progress"` - `"completed"` - `"incomplete"` - `"calling"` - `"failed"` - `OpenAITypesResponsesResponseOutputItemMcpListTools` A list of tools available on an MCP server. - `id: string` - `server_label: string` - `tools: Array` - `input_schema: unknown` - `name: string` - `annotations?: unknown` - `description?: string` - `type: "mcp_list_tools"` - `"mcp_list_tools"` - `error?: string` - `McpApprovalRequest` A request for human approval of a tool invocation. - `id: string` - `arguments: string` - `name: string` - `server_label: string` - `type: "mcp_approval_request"` - `"mcp_approval_request"` - `OpenAIResponseCustomToolCall` A call to a custom tool created by the model. - `call_id: string` - `input: string` - `name: string` - `type: "custom_tool_call"` - `"custom_tool_call"` - `id?: string` - `parallel_tool_calls: boolean` - `tool_choice: "none" | "auto" | "required" | ToolChoiceAllowed | ToolChoiceTypes | 5 more` Constrains the tools available to the model to a pre-defined set. - `"none" | "auto" | "required"` - `"none"` - `"auto"` - `"required"` - `ToolChoiceAllowed` Constrains the tools available to the model to a pre-defined set. - `mode: "auto" | "required"` - `"auto"` - `"required"` - `tools: Array>` - `type: "allowed_tools"` - `"allowed_tools"` - `ToolChoiceTypes` Indicates that the model should use a built-in tool to generate a response. [Learn more about built-in tools](https://platform.openai.com/docs/guides/tools). - `type: "file_search" | "web_search_preview" | "computer_use_preview" | 3 more` - `"file_search"` - `"web_search_preview"` - `"computer_use_preview"` - `"web_search_preview_2025_03_11"` - `"image_generation"` - `"code_interpreter"` - `ToolChoiceFunction` Use this option to force the model to call a specific function. - `name: string` - `type: "function"` - `"function"` - `ToolChoiceMcp` Use this option to force the model to call a specific tool on a remote MCP server. - `server_label: string` - `type: "mcp"` - `"mcp"` - `name?: string` - `ToolChoiceCustom` Use this option to force the model to call a specific custom tool. - `name: string` - `type: "custom"` - `"custom"` - `ToolChoiceApplyPatch` Forces the model to call the apply_patch tool when executing a tool call. - `type: "apply_patch"` - `"apply_patch"` - `ToolChoiceShell` Forces the model to call the shell tool when a tool call is required. - `type: "shell"` - `"shell"` - `tools: Array` - `FunctionTool` Defines a function in your own code the model can choose to call. Learn more about [function calling](https://platform.openai.com/docs/guides/function-calling). - `name: string` - `type: "function"` - `"function"` - `description?: string` - `parameters?: Record` - `strict?: boolean` - `FileSearchTool` A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](https://platform.openai.com/docs/guides/tools-file-search). - `type: "file_search"` - `"file_search"` - `vector_store_ids: Array` - `filters?: ComparisonFilter | CompoundFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `ComparisonFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `key: string` - `type: "eq" | "ne" | "gt" | 3 more` - `"eq"` - `"ne"` - `"gt"` - `"gte"` - `"lt"` - `"lte"` - `value: string | number | boolean | Array` - `string` - `number` - `boolean` - `Array` - `string` - `number` - `CompoundFilter` Combine multiple filters using `and` or `or`. - `filters: Array` - `ComparisonFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `key: string` - `type: "eq" | "ne" | "gt" | 3 more` - `"eq"` - `"ne"` - `"gt"` - `"gte"` - `"lt"` - `"lte"` - `value: string | number | boolean | Array` - `string` - `number` - `boolean` - `Array` - `string` - `number` - `unknown` - `type: "and" | "or"` - `"and"` - `"or"` - `max_num_results?: number` - `ranking_options?: RankingOptions` Ranking options for search. - `hybrid_search?: HybridSearch` Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled. - `embedding_weight: number` - `text_weight: number` - `ranker?: "auto" | "default-2024-11-15"` - `"auto"` - `"default-2024-11-15"` - `score_threshold?: number` - `ComputerTool` A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use). - `display_height: number` - `display_width: number` - `environment: "windows" | "mac" | "linux" | 2 more` - `"windows"` - `"mac"` - `"linux"` - `"ubuntu"` - `"browser"` - `type: "computer_use_preview"` - `"computer_use_preview"` - `WebSearchTool` Search the Internet for sources related to the prompt. Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search). - `type: "web_search" | "web_search_2025_08_26"` - `"web_search"` - `"web_search_2025_08_26"` - `filters?: Filters` Filters for the search. - `allowed_domains?: Array` - `search_context_size?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `user_location?: UserLocation` The approximate location of the user. - `city?: string` - `country?: string` - `region?: string` - `timezone?: string` - `type?: "approximate"` - `"approximate"` - `Mcp` Give the model access to additional tools via remote Model Context Protocol (MCP) servers. [Learn more about MCP](https://platform.openai.com/docs/guides/tools-remote-mcp). - `server_label: string` - `type: "mcp"` - `"mcp"` - `allowed_tools?: Array | McpAllowedToolsMcpToolFilter` A filter object to specify which tools are allowed. - `Array` - `McpAllowedToolsMcpToolFilter` A filter object to specify which tools are allowed. - `read_only?: boolean` - `tool_names?: Array` - `authorization?: string` - `connector_id?: "connector_dropbox" | "connector_gmail" | "connector_googlecalendar" | 5 more` - `"connector_dropbox"` - `"connector_gmail"` - `"connector_googlecalendar"` - `"connector_googledrive"` - `"connector_microsoftteams"` - `"connector_outlookcalendar"` - `"connector_outlookemail"` - `"connector_sharepoint"` - `headers?: Record` - `require_approval?: McpRequireApprovalMcpToolApprovalFilter | "always" | "never"` Specify which of the MCP server's tools require approval. Can be `always`, `never`, or a filter object associated with tools that require approval. - `McpRequireApprovalMcpToolApprovalFilter` Specify which of the MCP server's tools require approval. Can be `always`, `never`, or a filter object associated with tools that require approval. - `always?: Always` A filter object to specify which tools are allowed. - `read_only?: boolean` - `tool_names?: Array` - `never?: Never` A filter object to specify which tools are allowed. - `read_only?: boolean` - `tool_names?: Array` - `"always" | "never"` - `"always"` - `"never"` - `server_description?: string` - `server_url?: string` - `CodeInterpreter` A tool that runs Python code to help generate a response to a prompt. - `container: string | CodeInterpreterContainerCodeInterpreterToolAuto` Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on. - `string` - `CodeInterpreterContainerCodeInterpreterToolAuto` Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on. - `type: "auto"` - `"auto"` - `file_ids?: Array` - `memory_limit?: "1g" | "4g" | "16g" | "64g"` - `"1g"` - `"4g"` - `"16g"` - `"64g"` - `network_policy?: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` - `ContainerNetworkPolicyDisabled` - `type: "disabled"` - `"disabled"` - `ContainerNetworkPolicyAllowlist` - `allowed_domains: Array` - `type: "allowlist"` - `"allowlist"` - `domain_secrets?: Array` - `domain: string` - `name: string` - `value: string` - `type: "code_interpreter"` - `"code_interpreter"` - `ImageGeneration` A tool that generates images using the GPT image models. - `type: "image_generation"` - `"image_generation"` - `action?: "generate" | "edit" | "auto"` - `"generate"` - `"edit"` - `"auto"` - `background?: "transparent" | "opaque" | "auto"` - `"transparent"` - `"opaque"` - `"auto"` - `input_fidelity?: "high" | "low"` - `"high"` - `"low"` - `input_image_mask?: InputImageMask` Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional). - `file_id?: string` - `image_url?: string` - `model?: (string & {}) | "gpt-image-1" | "gpt-image-1-mini" | "gpt-image-1.5"` - `(string & {})` - `"gpt-image-1" | "gpt-image-1-mini" | "gpt-image-1.5"` - `"gpt-image-1"` - `"gpt-image-1-mini"` - `"gpt-image-1.5"` - `moderation?: "auto" | "low"` - `"auto"` - `"low"` - `output_compression?: number` - `output_format?: "png" | "webp" | "jpeg"` - `"png"` - `"webp"` - `"jpeg"` - `partial_images?: number` - `quality?: "low" | "medium" | "high" | "auto"` - `"low"` - `"medium"` - `"high"` - `"auto"` - `size?: "1024x1024" | "1024x1536" | "1536x1024" | "auto"` - `"1024x1024"` - `"1024x1536"` - `"1536x1024"` - `"auto"` - `LocalShell` A tool that allows the model to execute shell commands in a local environment. - `type: "local_shell"` - `"local_shell"` - `FunctionShellTool` A tool that allows the model to execute shell commands. - `type: "shell"` - `"shell"` - `environment?: ContainerAuto | LocalEnvironment | ContainerReference` - `ContainerAuto` - `type: "container_auto"` - `"container_auto"` - `file_ids?: Array` - `memory_limit?: "1g" | "4g" | "16g" | "64g"` - `"1g"` - `"4g"` - `"16g"` - `"64g"` - `network_policy?: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` - `ContainerNetworkPolicyDisabled` - `ContainerNetworkPolicyAllowlist` - `skills?: Array` - `SkillReference` - `skill_id: string` - `type: "skill_reference"` - `"skill_reference"` - `version?: string` - `InlineSkill` - `description: string` - `name: string` - `source: Source` Inline skill payload - `data: string` - `media_type: "application/zip"` - `"application/zip"` - `type: "base64"` - `"base64"` - `type: "inline"` - `"inline"` - `LocalEnvironment` - `type: "local"` - `"local"` - `skills?: Array` - `description: string` - `name: string` - `path: string` - `ContainerReference` - `container_id: string` - `type: "container_reference"` - `"container_reference"` - `CustomTool` A custom tool that processes input using a specified format. Learn more about [custom tools](https://platform.openai.com/docs/guides/function-calling#custom-tools) - `name: string` - `type: "custom"` - `"custom"` - `description?: string` - `format?: Text | Grammar` Unconstrained free-form text. - `Text` Unconstrained free-form text. - `type: "text"` - `"text"` - `Grammar` A grammar defined by the user. - `definition: string` - `syntax: "lark" | "regex"` - `"lark"` - `"regex"` - `type: "grammar"` - `"grammar"` - `WebSearchPreviewTool` This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search). - `type: "web_search_preview" | "web_search_preview_2025_03_11"` - `"web_search_preview"` - `"web_search_preview_2025_03_11"` - `search_context_size?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `user_location?: UserLocation` The user's location. - `type: "approximate"` - `"approximate"` - `city?: string` - `country?: string` - `region?: string` - `timezone?: string` - `ApplyPatchTool` Allows the assistant to create, delete, or update files using unified diffs. - `type: "apply_patch"` - `"apply_patch"` - `background?: boolean` - `completed_at?: number` - `conversation?: Conversation` The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation. - `id: string` - `error?: OpenAIResponseError` An error object returned when the model fails to generate a Response. - `code: "server_error" | "rate_limit_exceeded" | "invalid_prompt" | 15 more` - `"server_error"` - `"rate_limit_exceeded"` - `"invalid_prompt"` - `"vector_store_timeout"` - `"invalid_image"` - `"invalid_image_format"` - `"invalid_base64_image"` - `"invalid_image_url"` - `"image_too_large"` - `"image_too_small"` - `"image_parse_error"` - `"image_content_policy_violation"` - `"invalid_image_mode"` - `"image_file_too_large"` - `"unsupported_image_media_type"` - `"empty_image_file"` - `"failed_to_download_image"` - `"image_file_not_found"` - `message: string` - `incomplete_details?: IncompleteDetails` Details about why the response is incomplete. - `reason?: "max_output_tokens" | "content_filter"` - `"max_output_tokens"` - `"content_filter"` - `instructions?: string | Array` - `string` - `Array` - `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. - `content: string | Array` - `string` - `Array` - `OpenAIResponseInputText` A text input to the model. - `text: string` - `type: "input_text"` - `"input_text"` - `OpenAIResponseInputImage` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `detail: "low" | "high" | "auto"` - `"low"` - `"high"` - `"auto"` - `type: "input_image"` - `"input_image"` - `file_id?: string` - `image_url?: string` - `OpenAIResponseInputFile` A file input to the model. - `type: "input_file"` - `"input_file"` - `file_data?: string` - `file_id?: string` - `file_url?: string` - `filename?: string` - `role: "user" | "assistant" | "system" | "developer"` - `"user"` - `"assistant"` - `"system"` - `"developer"` - `phase?: "commentary" | "final_answer"` - `"commentary"` - `"final_answer"` - `type?: "message"` - `"message"` - `OpenAITypesResponsesResponseInputItemMessage` 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. - `content: Array` - `OpenAIResponseInputText` A text input to the model. - `OpenAIResponseInputImage` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `OpenAIResponseInputFile` A file input to the model. - `role: "user" | "system" | "developer"` - `"user"` - `"system"` - `"developer"` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type?: "message"` - `"message"` - `OpenAIResponseOutputMessage` An output message from the model. - `OpenAIResponseFileSearchToolCall` The results of a file search tool call. See the [file search guide](https://platform.openai.com/docs/guides/tools-file-search) for more information. - `OpenAIResponseComputerToolCall` A tool call to a computer use tool. See the [computer use guide](https://platform.openai.com/docs/guides/tools-computer-use) for more information. - `OpenAITypesResponsesResponseInputItemComputerCallOutput` The output of a computer tool call. - `call_id: string` - `output: ResponseComputerToolCallOutputScreenshot` A computer screenshot image used with the computer use tool. - `type: "computer_screenshot"` - `"computer_screenshot"` - `file_id?: string` - `image_url?: string` - `type: "computer_call_output"` - `"computer_call_output"` - `id?: string` - `acknowledged_safety_checks?: Array` - `id: string` - `code?: string` - `message?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `OpenAIResponseFunctionWebSearch` The results of a web search tool call. See the [web search guide](https://platform.openai.com/docs/guides/tools-web-search) for more information. - `OpenAIResponseFunctionToolCall` A tool call to run a function. See the [function calling guide](https://platform.openai.com/docs/guides/function-calling) for more information. - `OpenAITypesResponsesResponseInputItemFunctionCallOutput` The output of a function tool call. - `call_id: string` - `output: string | Array` - `string` - `Array` - `ResponseInputTextContent` A text input to the model. - `text: string` - `type: "input_text"` - `"input_text"` - `ResponseInputImageContent` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision) - `type: "input_image"` - `"input_image"` - `detail?: "low" | "high" | "auto"` - `"low"` - `"high"` - `"auto"` - `file_id?: string` - `image_url?: string` - `ResponseInputFileContent` A file input to the model. - `type: "input_file"` - `"input_file"` - `file_data?: string` - `file_id?: string` - `file_url?: string` - `filename?: string` - `type: "function_call_output"` - `"function_call_output"` - `id?: string` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `OpenAIResponseReasoningItem` 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](https://platform.openai.com/docs/guides/conversation-state). - `ResponseCompactionItemParam` A compaction item generated by the [`v1/responses/compact` API](https://platform.openai.com/docs/api-reference/responses/compact). - `encrypted_content: string` - `type: "compaction"` - `"compaction"` - `id?: string` - `OpenAITypesResponsesResponseInputItemImageGenerationCall` An image generation request made by the model. - `id: string` - `status: "in_progress" | "completed" | "generating" | "failed"` - `"in_progress"` - `"completed"` - `"generating"` - `"failed"` - `type: "image_generation_call"` - `"image_generation_call"` - `result?: string` - `OpenAIResponseCodeInterpreterToolCall` A tool call to run code. - `OpenAITypesResponsesResponseInputItemLocalShellCall` A tool call to run a command on the local shell. - `id: string` - `action: Action` Execute a shell command on the server. - `command: Array` - `env: Record` - `type: "exec"` - `"exec"` - `timeout_ms?: number` - `user?: string` - `working_directory?: string` - `call_id: string` - `status: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "local_shell_call"` - `"local_shell_call"` - `OpenAITypesResponsesResponseInputItemLocalShellCallOutput` The output of a local shell tool call. - `id: string` - `output: string` - `type: "local_shell_call_output"` - `"local_shell_call_output"` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `ShellCall` A tool representing a request to execute one or more shell commands. - `action: Action` The shell commands and limits that describe how to run the tool call. - `commands: Array` - `max_output_length?: number` - `timeout_ms?: number` - `call_id: string` - `type: "shell_call"` - `"shell_call"` - `id?: string` - `environment?: LocalEnvironment | ContainerReference` - `LocalEnvironment` - `ContainerReference` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `ShellCallOutput` The streamed output items emitted by a shell tool call. - `call_id: string` - `output: Array` - `outcome: OutcomeTimeout | OutcomeExit` Indicates that the shell call exceeded its configured time limit. - `OutcomeTimeout` Indicates that the shell call exceeded its configured time limit. - `type: "timeout"` - `"timeout"` - `OutcomeExit` Indicates that the shell commands finished and returned an exit code. - `exit_code: number` - `type: "exit"` - `"exit"` - `stderr: string` - `stdout: string` - `type: "shell_call_output"` - `"shell_call_output"` - `id?: string` - `max_output_length?: number` - `status?: "in_progress" | "completed" | "incomplete"` - `"in_progress"` - `"completed"` - `"incomplete"` - `ApplyPatchCall` A tool call representing a request to create, delete, or update files using diff patches. - `call_id: string` - `operation: ApplyPatchCallOperationCreateFile | ApplyPatchCallOperationDeleteFile | ApplyPatchCallOperationUpdateFile` Instruction for creating a new file via the apply_patch tool. - `ApplyPatchCallOperationCreateFile` Instruction for creating a new file via the apply_patch tool. - `diff: string` - `path: string` - `type: "create_file"` - `"create_file"` - `ApplyPatchCallOperationDeleteFile` Instruction for deleting an existing file via the apply_patch tool. - `path: string` - `type: "delete_file"` - `"delete_file"` - `ApplyPatchCallOperationUpdateFile` Instruction for updating an existing file via the apply_patch tool. - `diff: string` - `path: string` - `type: "update_file"` - `"update_file"` - `status: "in_progress" | "completed"` - `"in_progress"` - `"completed"` - `type: "apply_patch_call"` - `"apply_patch_call"` - `id?: string` - `ApplyPatchCallOutput` The streamed output emitted by an apply patch tool call. - `call_id: string` - `status: "completed" | "failed"` - `"completed"` - `"failed"` - `type: "apply_patch_call_output"` - `"apply_patch_call_output"` - `id?: string` - `output?: string` - `OpenAITypesResponsesResponseInputItemMcpListTools` A list of tools available on an MCP server. - `id: string` - `server_label: string` - `tools: Array` - `input_schema: unknown` - `name: string` - `annotations?: unknown` - `description?: string` - `type: "mcp_list_tools"` - `"mcp_list_tools"` - `error?: string` - `McpApprovalRequest` A request for human approval of a tool invocation. - `OpenAITypesResponsesResponseInputItemMcpApprovalResponse` A response to an MCP approval request. - `approval_request_id: string` - `approve: boolean` - `type: "mcp_approval_response"` - `"mcp_approval_response"` - `id?: string` - `reason?: string` - `OpenAITypesResponsesResponseInputItemMcpCall` An invocation of a tool on an MCP server. - `id: string` - `arguments: string` - `name: string` - `server_label: string` - `type: "mcp_call"` - `"mcp_call"` - `approval_request_id?: string` - `error?: string` - `output?: string` - `status?: "in_progress" | "completed" | "incomplete" | 2 more` - `"in_progress"` - `"completed"` - `"incomplete"` - `"calling"` - `"failed"` - `OpenAIResponseCustomToolCallOutput` The output of a custom tool call from your code, being sent back to the model. - `call_id: string` - `output: string | Array` - `string` - `Array` - `OpenAIResponseInputText` A text input to the model. - `OpenAIResponseInputImage` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `OpenAIResponseInputFile` A file input to the model. - `type: "custom_tool_call_output"` - `"custom_tool_call_output"` - `id?: string` - `OpenAIResponseCustomToolCall` A call to a custom tool created by the model. - `OpenAITypesResponsesResponseInputItemItemReference` An internal identifier for an item to reference. - `id: string` - `type?: "item_reference"` - `"item_reference"` - `max_output_tokens?: number` - `max_tool_calls?: number` - `metadata?: Record` - `previous_response_id?: string` - `prompt?: OpenAIResponsePrompt` Reference to a prompt template and its variables. [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). - `id: string` - `variables?: Record` - `string` - `OpenAIResponseInputText` A text input to the model. - `OpenAIResponseInputImage` An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision). - `OpenAIResponseInputFile` A file input to the model. - `version?: string` - `prompt_cache_key?: string` - `prompt_cache_retention?: "in-memory" | "24h"` - `"in-memory"` - `"24h"` - `reasoning?: Reasoning` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - `effort?: "none" | "minimal" | "low" | 3 more` - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `generate_summary?: "auto" | "concise" | "detailed"` - `"auto"` - `"concise"` - `"detailed"` - `summary?: "auto" | "concise" | "detailed"` - `"auto"` - `"concise"` - `"detailed"` - `safety_identifier?: string` - `service_tier?: "auto" | "default" | "flex" | 2 more` - `"auto"` - `"default"` - `"flex"` - `"scale"` - `"priority"` - `status?: "completed" | "failed" | "in_progress" | 3 more` - `"completed"` - `"failed"` - `"in_progress"` - `"cancelled"` - `"queued"` - `"incomplete"` - `temperature?: number` - `text?: OpenAIResponseTextConfig` Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - [Text inputs and outputs](https://platform.openai.com/docs/guides/text) - [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs) - `format?: ResponseFormatText | ResponseFormatTextJsonSchemaConfig | ResponseFormatJsonObject` Default response format. Used to generate text responses. - `ResponseFormatText` Default response format. Used to generate text responses. - `type: "text"` - `"text"` - `ResponseFormatTextJsonSchemaConfig` JSON Schema response format. Used to generate structured JSON responses. Learn more about [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs). - `name: string` - `schema: Record` - `type: "json_schema"` - `"json_schema"` - `description?: string` - `strict?: boolean` - `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. - `type: "json_object"` - `"json_object"` - `verbosity?: "low" | "medium" | "high"` - `"low"` - `"medium"` - `"high"` - `top_logprobs?: number` - `top_p?: number` - `truncation?: "auto" | "disabled"` - `"auto"` - `"disabled"` - `usage?: OpenAIResponseUsage` Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used. - `input_tokens: number` - `input_tokens_details: InputTokensDetails` A detailed breakdown of the input tokens. - `cached_tokens: number` - `output_tokens: number` - `output_tokens_details: OutputTokensDetails` A detailed breakdown of the output tokens. - `reasoning_tokens: number` - `total_tokens: number` - `user?: string` - `ResponseAudioDeltaEvent` Emitted when there is a partial audio response. - `delta: string` - `sequence_number: number` - `type: "response.audio.delta"` - `"response.audio.delta"` - `ResponseAudioDoneEvent` Emitted when the audio response is complete. - `sequence_number: number` - `type: "response.audio.done"` - `"response.audio.done"` - `ResponseAudioTranscriptDeltaEvent` Emitted when there is a partial transcript of audio. - `delta: string` - `sequence_number: number` - `type: "response.audio.transcript.delta"` - `"response.audio.transcript.delta"` - `ResponseAudioTranscriptDoneEvent` Emitted when the full audio transcript is completed. - `sequence_number: number` - `type: "response.audio.transcript.done"` - `"response.audio.transcript.done"` - `ResponseCodeInterpreterCallCodeDeltaEvent` Emitted when a partial code snippet is streamed by the code interpreter. - `delta: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.code_interpreter_call_code.delta"` - `"response.code_interpreter_call_code.delta"` - `ResponseCodeInterpreterCallCodeDoneEvent` Emitted when the code snippet is finalized by the code interpreter. - `code: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.code_interpreter_call_code.done"` - `"response.code_interpreter_call_code.done"` - `ResponseCodeInterpreterCallCompletedEvent` Emitted when the code interpreter call is completed. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.code_interpreter_call.completed"` - `"response.code_interpreter_call.completed"` - `ResponseCodeInterpreterCallInProgressEvent` Emitted when a code interpreter call is in progress. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.code_interpreter_call.in_progress"` - `"response.code_interpreter_call.in_progress"` - `ResponseCodeInterpreterCallInterpretingEvent` Emitted when the code interpreter is actively interpreting the code snippet. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.code_interpreter_call.interpreting"` - `"response.code_interpreter_call.interpreting"` - `ResponseCompletedEvent` Emitted when the model response is complete. - `response: OpenAIResponse` - `sequence_number: number` - `type: "response.completed"` - `"response.completed"` - `ResponseContentPartAddedEvent` Emitted when a new content part is added. - `content_index: number` - `item_id: string` - `output_index: number` - `part: OpenAIResponseOutputText | OpenAIResponseOutputRefusal | PartReasoningText` A text output from the model. - `OpenAIResponseOutputText` A text output from the model. - `OpenAIResponseOutputRefusal` A refusal from the model. - `PartReasoningText` Reasoning text from the model. - `text: string` - `type: "reasoning_text"` - `"reasoning_text"` - `sequence_number: number` - `type: "response.content_part.added"` - `"response.content_part.added"` - `ResponseContentPartDoneEvent` Emitted when a content part is done. - `content_index: number` - `item_id: string` - `output_index: number` - `part: OpenAIResponseOutputText | OpenAIResponseOutputRefusal | PartReasoningText` A text output from the model. - `OpenAIResponseOutputText` A text output from the model. - `OpenAIResponseOutputRefusal` A refusal from the model. - `PartReasoningText` Reasoning text from the model. - `sequence_number: number` - `type: "response.content_part.done"` - `"response.content_part.done"` - `ResponseCreatedEvent` An event that is emitted when a response is created. - `response: OpenAIResponse` - `sequence_number: number` - `type: "response.created"` - `"response.created"` - `ResponseErrorEvent` Emitted when an error occurs. - `message: string` - `sequence_number: number` - `type: "error"` - `"error"` - `code?: string` - `param?: string` - `ResponseFileSearchCallCompletedEvent` Emitted when a file search call is completed (results found). - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.file_search_call.completed"` - `"response.file_search_call.completed"` - `ResponseFileSearchCallInProgressEvent` Emitted when a file search call is initiated. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.file_search_call.in_progress"` - `"response.file_search_call.in_progress"` - `ResponseFileSearchCallSearchingEvent` Emitted when a file search is currently searching. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.file_search_call.searching"` - `"response.file_search_call.searching"` - `ResponseFunctionCallArgumentsDeltaEvent` Emitted when there is a partial function-call arguments delta. - `delta: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.function_call_arguments.delta"` - `"response.function_call_arguments.delta"` - `ResponseFunctionCallArgumentsDoneEvent` Emitted when function-call arguments are finalized. - `arguments: string` - `item_id: string` - `name: string` - `output_index: number` - `sequence_number: number` - `type: "response.function_call_arguments.done"` - `"response.function_call_arguments.done"` - `ResponseInProgressEvent` Emitted when the response is in progress. - `response: OpenAIResponse` - `sequence_number: number` - `type: "response.in_progress"` - `"response.in_progress"` - `ResponseFailedEvent` An event that is emitted when a response fails. - `response: OpenAIResponse` - `sequence_number: number` - `type: "response.failed"` - `"response.failed"` - `ResponseIncompleteEvent` An event that is emitted when a response finishes as incomplete. - `response: OpenAIResponse` - `sequence_number: number` - `type: "response.incomplete"` - `"response.incomplete"` - `ResponseOutputItemAddedEvent` Emitted when a new output item is added. - `item: OpenAIResponseOutputMessage | OpenAIResponseFileSearchToolCall | OpenAIResponseFunctionToolCall | 15 more` An output message from the model. - `OpenAIResponseOutputMessage` An output message from the model. - `OpenAIResponseFileSearchToolCall` The results of a file search tool call. See the [file search guide](https://platform.openai.com/docs/guides/tools-file-search) for more information. - `OpenAIResponseFunctionToolCall` A tool call to run a function. See the [function calling guide](https://platform.openai.com/docs/guides/function-calling) for more information. - `OpenAIResponseFunctionWebSearch` The results of a web search tool call. See the [web search guide](https://platform.openai.com/docs/guides/tools-web-search) for more information. - `OpenAIResponseComputerToolCall` A tool call to a computer use tool. See the [computer use guide](https://platform.openai.com/docs/guides/tools-computer-use) for more information. - `OpenAIResponseReasoningItem` 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](https://platform.openai.com/docs/guides/conversation-state). - `ResponseCompactionItem` A compaction item generated by the [`v1/responses/compact` API](https://platform.openai.com/docs/api-reference/responses/compact). - `OpenAITypesResponsesResponseOutputItemImageGenerationCall` An image generation request made by the model. - `OpenAIResponseCodeInterpreterToolCall` A tool call to run code. - `OpenAITypesResponsesResponseOutputItemLocalShellCall` A tool call to run a command on the local shell. - `ResponseFunctionShellToolCall` A tool call that executes one or more shell commands in a managed environment. - `ResponseFunctionShellToolCallOutput` The output of a shell tool call that was emitted. - `ResponseApplyPatchToolCall` A tool call that applies file diffs by creating, deleting, or updating files. - `ResponseApplyPatchToolCallOutput` The output emitted by an apply patch tool call. - `OpenAITypesResponsesResponseOutputItemMcpCall` An invocation of a tool on an MCP server. - `OpenAITypesResponsesResponseOutputItemMcpListTools` A list of tools available on an MCP server. - `McpApprovalRequest` A request for human approval of a tool invocation. - `OpenAIResponseCustomToolCall` A call to a custom tool created by the model. - `output_index: number` - `sequence_number: number` - `type: "response.output_item.added"` - `"response.output_item.added"` - `ResponseOutputItemDoneEvent` Emitted when an output item is marked done. - `item: OpenAIResponseOutputMessage | OpenAIResponseFileSearchToolCall | OpenAIResponseFunctionToolCall | 15 more` An output message from the model. - `OpenAIResponseOutputMessage` An output message from the model. - `OpenAIResponseFileSearchToolCall` The results of a file search tool call. See the [file search guide](https://platform.openai.com/docs/guides/tools-file-search) for more information. - `OpenAIResponseFunctionToolCall` A tool call to run a function. See the [function calling guide](https://platform.openai.com/docs/guides/function-calling) for more information. - `OpenAIResponseFunctionWebSearch` The results of a web search tool call. See the [web search guide](https://platform.openai.com/docs/guides/tools-web-search) for more information. - `OpenAIResponseComputerToolCall` A tool call to a computer use tool. See the [computer use guide](https://platform.openai.com/docs/guides/tools-computer-use) for more information. - `OpenAIResponseReasoningItem` 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](https://platform.openai.com/docs/guides/conversation-state). - `ResponseCompactionItem` A compaction item generated by the [`v1/responses/compact` API](https://platform.openai.com/docs/api-reference/responses/compact). - `OpenAITypesResponsesResponseOutputItemImageGenerationCall` An image generation request made by the model. - `OpenAIResponseCodeInterpreterToolCall` A tool call to run code. - `OpenAITypesResponsesResponseOutputItemLocalShellCall` A tool call to run a command on the local shell. - `ResponseFunctionShellToolCall` A tool call that executes one or more shell commands in a managed environment. - `ResponseFunctionShellToolCallOutput` The output of a shell tool call that was emitted. - `ResponseApplyPatchToolCall` A tool call that applies file diffs by creating, deleting, or updating files. - `ResponseApplyPatchToolCallOutput` The output emitted by an apply patch tool call. - `OpenAITypesResponsesResponseOutputItemMcpCall` An invocation of a tool on an MCP server. - `OpenAITypesResponsesResponseOutputItemMcpListTools` A list of tools available on an MCP server. - `McpApprovalRequest` A request for human approval of a tool invocation. - `OpenAIResponseCustomToolCall` A call to a custom tool created by the model. - `output_index: number` - `sequence_number: number` - `type: "response.output_item.done"` - `"response.output_item.done"` - `ResponseReasoningSummaryPartAddedEvent` Emitted when a new reasoning summary part is added. - `item_id: string` - `output_index: number` - `part: Part` The summary part that was added. - `text: string` - `type: "summary_text"` - `"summary_text"` - `sequence_number: number` - `summary_index: number` - `type: "response.reasoning_summary_part.added"` - `"response.reasoning_summary_part.added"` - `ResponseReasoningSummaryPartDoneEvent` Emitted when a reasoning summary part is completed. - `item_id: string` - `output_index: number` - `part: Part` The completed summary part. - `text: string` - `type: "summary_text"` - `"summary_text"` - `sequence_number: number` - `summary_index: number` - `type: "response.reasoning_summary_part.done"` - `"response.reasoning_summary_part.done"` - `ResponseReasoningSummaryTextDeltaEvent` Emitted when a delta is added to a reasoning summary text. - `delta: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `summary_index: number` - `type: "response.reasoning_summary_text.delta"` - `"response.reasoning_summary_text.delta"` - `ResponseReasoningSummaryTextDoneEvent` Emitted when a reasoning summary text is completed. - `item_id: string` - `output_index: number` - `sequence_number: number` - `summary_index: number` - `text: string` - `type: "response.reasoning_summary_text.done"` - `"response.reasoning_summary_text.done"` - `ResponseReasoningTextDeltaEvent` Emitted when a delta is added to a reasoning text. - `content_index: number` - `delta: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.reasoning_text.delta"` - `"response.reasoning_text.delta"` - `ResponseReasoningTextDoneEvent` Emitted when a reasoning text is completed. - `content_index: number` - `item_id: string` - `output_index: number` - `sequence_number: number` - `text: string` - `type: "response.reasoning_text.done"` - `"response.reasoning_text.done"` - `ResponseRefusalDeltaEvent` Emitted when there is a partial refusal text. - `content_index: number` - `delta: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.refusal.delta"` - `"response.refusal.delta"` - `ResponseRefusalDoneEvent` Emitted when refusal text is finalized. - `content_index: number` - `item_id: string` - `output_index: number` - `refusal: string` - `sequence_number: number` - `type: "response.refusal.done"` - `"response.refusal.done"` - `ResponseTextDeltaEvent` Emitted when there is an additional text delta. - `content_index: number` - `delta: string` - `item_id: string` - `logprobs: Array` - `token: string` - `logprob: number` - `top_logprobs?: Array` - `token?: string` - `logprob?: number` - `output_index: number` - `sequence_number: number` - `type: "response.output_text.delta"` - `"response.output_text.delta"` - `ResponseTextDoneEvent` Emitted when text content is finalized. - `content_index: number` - `item_id: string` - `logprobs: Array` - `token: string` - `logprob: number` - `top_logprobs?: Array` - `token?: string` - `logprob?: number` - `output_index: number` - `sequence_number: number` - `text: string` - `type: "response.output_text.done"` - `"response.output_text.done"` - `ResponseWebSearchCallCompletedEvent` Emitted when a web search call is completed. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.web_search_call.completed"` - `"response.web_search_call.completed"` - `ResponseWebSearchCallInProgressEvent` Emitted when a web search call is initiated. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.web_search_call.in_progress"` - `"response.web_search_call.in_progress"` - `ResponseWebSearchCallSearchingEvent` Emitted when a web search call is executing. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.web_search_call.searching"` - `"response.web_search_call.searching"` - `ResponseImageGenCallCompletedEvent` Emitted when an image generation tool call has completed and the final image is available. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.image_generation_call.completed"` - `"response.image_generation_call.completed"` - `ResponseImageGenCallGeneratingEvent` Emitted when an image generation tool call is actively generating an image (intermediate state). - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.image_generation_call.generating"` - `"response.image_generation_call.generating"` - `ResponseImageGenCallInProgressEvent` Emitted when an image generation tool call is in progress. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.image_generation_call.in_progress"` - `"response.image_generation_call.in_progress"` - `ResponseImageGenCallPartialImageEvent` Emitted when a partial image is available during image generation streaming. - `item_id: string` - `output_index: number` - `partial_image_b64: string` - `partial_image_index: number` - `sequence_number: number` - `type: "response.image_generation_call.partial_image"` - `"response.image_generation_call.partial_image"` - `ResponseMcpCallArgumentsDeltaEvent` Emitted when there is a delta (partial update) to the arguments of an MCP tool call. - `delta: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.mcp_call_arguments.delta"` - `"response.mcp_call_arguments.delta"` - `ResponseMcpCallArgumentsDoneEvent` Emitted when the arguments for an MCP tool call are finalized. - `arguments: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.mcp_call_arguments.done"` - `"response.mcp_call_arguments.done"` - `ResponseMcpCallCompletedEvent` Emitted when an MCP tool call has completed successfully. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.mcp_call.completed"` - `"response.mcp_call.completed"` - `ResponseMcpCallFailedEvent` Emitted when an MCP tool call has failed. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.mcp_call.failed"` - `"response.mcp_call.failed"` - `ResponseMcpCallInProgressEvent` Emitted when an MCP tool call is in progress. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.mcp_call.in_progress"` - `"response.mcp_call.in_progress"` - `ResponseMcpListToolsCompletedEvent` Emitted when the list of available MCP tools has been successfully retrieved. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.mcp_list_tools.completed"` - `"response.mcp_list_tools.completed"` - `ResponseMcpListToolsFailedEvent` Emitted when the attempt to list available MCP tools has failed. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.mcp_list_tools.failed"` - `"response.mcp_list_tools.failed"` - `ResponseMcpListToolsInProgressEvent` Emitted when the system is in the process of retrieving the list of available MCP tools. - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.mcp_list_tools.in_progress"` - `"response.mcp_list_tools.in_progress"` - `ResponseOutputTextAnnotationAddedEvent` Emitted when an annotation is added to output text content. - `annotation: unknown` - `annotation_index: number` - `content_index: number` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.output_text.annotation.added"` - `"response.output_text.annotation.added"` - `ResponseQueuedEvent` Emitted when a response is queued and waiting to be processed. - `response: OpenAIResponse` - `sequence_number: number` - `type: "response.queued"` - `"response.queued"` - `ResponseCustomToolCallInputDeltaEvent` Event representing a delta (partial update) to the input of a custom tool call. - `delta: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.custom_tool_call_input.delta"` - `"response.custom_tool_call_input.delta"` - `ResponseCustomToolCallInputDoneEvent` Event indicating that input for a custom tool call is complete. - `input: string` - `item_id: string` - `output_index: number` - `sequence_number: number` - `type: "response.custom_tool_call_input.done"` - `"response.custom_tool_call_input.done"` - `GenericResponseEvent` - `type: string`