java/resources/responses/methods/cancel/index.md 2026-05-18 22:01 UTC to 2026-05-19 06:34 UTC

1## Cancel a response

2 

3`Response responses().cancel(ResponseCancelParamsparams = ResponseCancelParams.none(), RequestOptionsrequestOptions = RequestOptions.none())`

4 

5**post** `/responses/{response_id}/cancel`

6 

7Cancels a model response with the given ID. Only responses created with

8the `background` parameter set to `true` can be cancelled.

9[Learn more](https://platform.openai.com/docs/guides/background).

10 

11### Parameters

12 

13- `ResponseCancelParams params`

14 

15 - `Optional<String> responseId`

16 

17### Returns

18 

19- `class Response:`

20 

21 - `String id`

22 

23 Unique identifier for this Response.

24 

25 - `double createdAt`

26 

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

28 

29 - `Optional<ResponseError> error`

30 

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

32 

33 - `Code code`

34 

35 The error code for the response.

36 

37 - `SERVER_ERROR("server_error")`

38 

39 - `RATE_LIMIT_EXCEEDED("rate_limit_exceeded")`

40 

41 - `INVALID_PROMPT("invalid_prompt")`

42 

43 - `VECTOR_STORE_TIMEOUT("vector_store_timeout")`

44 

45 - `INVALID_IMAGE("invalid_image")`

46 

47 - `INVALID_IMAGE_FORMAT("invalid_image_format")`

48 

49 - `INVALID_BASE64_IMAGE("invalid_base64_image")`

50 

51 - `INVALID_IMAGE_URL("invalid_image_url")`

52 

53 - `IMAGE_TOO_LARGE("image_too_large")`

54 

55 - `IMAGE_TOO_SMALL("image_too_small")`

56 

57 - `IMAGE_PARSE_ERROR("image_parse_error")`

58 

59 - `IMAGE_CONTENT_POLICY_VIOLATION("image_content_policy_violation")`

60 

61 - `INVALID_IMAGE_MODE("invalid_image_mode")`

62 

63 - `IMAGE_FILE_TOO_LARGE("image_file_too_large")`

64 

65 - `UNSUPPORTED_IMAGE_MEDIA_TYPE("unsupported_image_media_type")`

66 

67 - `EMPTY_IMAGE_FILE("empty_image_file")`

68 

69 - `FAILED_TO_DOWNLOAD_IMAGE("failed_to_download_image")`

70 

71 - `IMAGE_FILE_NOT_FOUND("image_file_not_found")`

72 

73 - `String message`

74 

75 A human-readable description of the error.

76 

77 - `Optional<IncompleteDetails> incompleteDetails`

78 

79 Details about why the response is incomplete.

80 

81 - `Optional<Reason> reason`

82 

83 The reason why the response is incomplete.

84 

85 - `MAX_OUTPUT_TOKENS("max_output_tokens")`

86 

87 - `CONTENT_FILTER("content_filter")`

88 

89 - `Optional<Instructions> instructions`

90 

91 A system (or developer) message inserted into the model's context.

92 

93 When using along with `previous_response_id`, the instructions from a previous

94 response will not be carried over to the next response. This makes it simple

95 to swap out system (or developer) messages in new responses.

96 

97 - `String`

98 

99 - `List<ResponseInputItem>`

100 

101 - `class EasyInputMessage:`

102 

103 A message input to the model with a role indicating instruction following

104 hierarchy. Instructions given with the `developer` or `system` role take

105 precedence over instructions given with the `user` role. Messages with the

106 `assistant` role are presumed to have been generated by the model in previous

107 interactions.

108 

109 - `Content content`

110 

111 Text, image, or audio input to the model, used to generate a response.

112 Can also contain previous assistant responses.

113 

114 - `String`

115 

116 - `List<ResponseInputContent>`

117 

118 - `class ResponseInputText:`

119 

120 A text input to the model.

121 

122 - `String text`

123 

124 The text input to the model.

125 

126 - `JsonValue; type "input_text"constant`

127 

128 The type of the input item. Always `input_text`.

129 

130 - `INPUT_TEXT("input_text")`

131 

132 - `class ResponseInputImage:`

133 

134 An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision).

135 

136 - `Detail detail`

137 

138 The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`.

139 

140 - `LOW("low")`

141 

142 - `HIGH("high")`

143 

144 - `AUTO("auto")`

145 

146 - `ORIGINAL("original")`

147 

148 - `JsonValue; type "input_image"constant`

149 

150 The type of the input item. Always `input_image`.

151 

152 - `INPUT_IMAGE("input_image")`

153 

154 - `Optional<String> fileId`

155 

156 The ID of the file to be sent to the model.

157 

158 - `Optional<String> imageUrl`

159 

160 The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.

161 

162 - `class ResponseInputFile:`

163 

164 A file input to the model.

165 

166 - `JsonValue; type "input_file"constant`

167 

168 The type of the input item. Always `input_file`.

169 

170 - `INPUT_FILE("input_file")`

171 

172 - `Optional<Detail> detail`

173 

174 The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`.

175 

176 - `LOW("low")`

177 

178 - `HIGH("high")`

179 

180 - `Optional<String> fileData`

181 

182 The content of the file to be sent to the model.

183 

184 - `Optional<String> fileId`

185 

186 The ID of the file to be sent to the model.

187 

188 - `Optional<String> fileUrl`

189 

190 The URL of the file to be sent to the model.

191 

192 - `Optional<String> filename`

193 

194 The name of the file to be sent to the model.

195 

196 - `Role role`

197 

198 The role of the message input. One of `user`, `assistant`, `system`, or

199 `developer`.

200 

201 - `USER("user")`

202 

203 - `ASSISTANT("assistant")`

204 

205 - `SYSTEM("system")`

206 

207 - `DEVELOPER("developer")`

208 

209 - `Optional<Phase> phase`

210 

211 Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`).

212 For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend

213 phase on all assistant messages — dropping it can degrade performance. Not used for user messages.

214 

215 - `COMMENTARY("commentary")`

216 

217 - `FINAL_ANSWER("final_answer")`

218 

219 - `Optional<Type> type`

220 

221 The type of the message input. Always `message`.

222 

223 - `MESSAGE("message")`

224 

225 - `Message`

226 

227 - `List<ResponseInputContent> content`

228 

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

230 types.

231 

232 - `class ResponseInputText:`

233 

234 A text input to the model.

235 

236 - `class ResponseInputImage:`

237 

238 An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision).

239 

240 - `class ResponseInputFile:`

241 

242 A file input to the model.

243 

244 - `Role role`

245 

246 The role of the message input. One of `user`, `system`, or `developer`.

247 

248 - `USER("user")`

249 

250 - `SYSTEM("system")`

251 

252 - `DEVELOPER("developer")`

253 

254 - `Optional<Status> status`

255 

256 The status of item. One of `in_progress`, `completed`, or

257 `incomplete`. Populated when items are returned via API.

258 

259 - `IN_PROGRESS("in_progress")`

260 

261 - `COMPLETED("completed")`

262 

263 - `INCOMPLETE("incomplete")`

264 

265 - `Optional<Type> type`

266 

267 The type of the message input. Always set to `message`.

268 

269 - `MESSAGE("message")`

270 

271 - `class ResponseOutputMessage:`

272 

273 An output message from the model.

274 

275 - `String id`

276 

277 The unique ID of the output message.

278 

279 - `List<Content> content`

280 

281 The content of the output message.

282 

283 - `class ResponseOutputText:`

284 

285 A text output from the model.

286 

287 - `List<Annotation> annotations`

288 

289 The annotations of the text output.

290 

291 - `class FileCitation:`

292 

293 A citation to a file.

294 

295 - `String fileId`

296 

297 The ID of the file.

298 

299 - `String filename`

300 

301 The filename of the file cited.

302 

303 - `long index`

304 

305 The index of the file in the list of files.

306 

307 - `JsonValue; type "file_citation"constant`

308 

309 The type of the file citation. Always `file_citation`.

310 

311 - `FILE_CITATION("file_citation")`

312 

313 - `class UrlCitation:`

314 

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

316 

317 - `long endIndex`

318 

319 The index of the last character of the URL citation in the message.

320 

321 - `long startIndex`

322 

323 The index of the first character of the URL citation in the message.

324 

325 - `String title`

326 

327 The title of the web resource.

328 

329 - `JsonValue; type "url_citation"constant`

330 

331 The type of the URL citation. Always `url_citation`.

332 

333 - `URL_CITATION("url_citation")`

334 

335 - `String url`

336 

337 The URL of the web resource.

338 

339 - `class ContainerFileCitation:`

340 

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

342 

343 - `String containerId`

344 

345 The ID of the container file.

346 

347 - `long endIndex`

348 

349 The index of the last character of the container file citation in the message.

350 

351 - `String fileId`

352 

353 The ID of the file.

354 

355 - `String filename`

356 

357 The filename of the container file cited.

358 

359 - `long startIndex`

360 

361 The index of the first character of the container file citation in the message.

362 

363 - `JsonValue; type "container_file_citation"constant`

364 

365 The type of the container file citation. Always `container_file_citation`.

366 

367 - `CONTAINER_FILE_CITATION("container_file_citation")`

368 

369 - `class FilePath:`

370 

371 A path to a file.

372 

373 - `String fileId`

374 

375 The ID of the file.

376 

377 - `long index`

378 

379 The index of the file in the list of files.

380 

381 - `JsonValue; type "file_path"constant`

382 

383 The type of the file path. Always `file_path`.

384 

385 - `FILE_PATH("file_path")`

386 

387 - `String text`

388 

389 The text output from the model.

390 

391 - `JsonValue; type "output_text"constant`

392 

393 The type of the output text. Always `output_text`.

394 

395 - `OUTPUT_TEXT("output_text")`

396 

397 - `Optional<List<Logprob>> logprobs`

398 

399 - `String token`

400 

401 - `List<long> bytes`

402 

403 - `double logprob`

404 

405 - `List<TopLogprob> topLogprobs`

406 

407 - `String token`

408 

409 - `List<long> bytes`

410 

411 - `double logprob`

412 

413 - `class ResponseOutputRefusal:`

414 

415 A refusal from the model.

416 

417 - `String refusal`

418 

419 The refusal explanation from the model.

420 

421 - `JsonValue; type "refusal"constant`

422 

423 The type of the refusal. Always `refusal`.

424 

425 - `REFUSAL("refusal")`

426 

427 - `JsonValue; role "assistant"constant`

428 

429 The role of the output message. Always `assistant`.

430 

431 - `ASSISTANT("assistant")`

432 

433 - `Status status`

434 

435 The status of the message input. One of `in_progress`, `completed`, or

436 `incomplete`. Populated when input items are returned via API.

437 

438 - `IN_PROGRESS("in_progress")`

439 

440 - `COMPLETED("completed")`

441 

442 - `INCOMPLETE("incomplete")`

443 

444 - `JsonValue; type "message"constant`

445 

446 The type of the output message. Always `message`.

447 

448 - `MESSAGE("message")`

449 

450 - `Optional<Phase> phase`

451 

452 Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`).

453 For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend

454 phase on all assistant messages — dropping it can degrade performance. Not used for user messages.

455 

456 - `COMMENTARY("commentary")`

457 

458 - `FINAL_ANSWER("final_answer")`

459 

460 - `class ResponseFileSearchToolCall:`

461 

462 The results of a file search tool call. See the

463 [file search guide](https://platform.openai.com/docs/guides/tools-file-search) for more information.

464 

465 - `String id`

466 

467 The unique ID of the file search tool call.

468 

469 - `List<String> queries`

470 

471 The queries used to search for files.

472 

473 - `Status status`

474 

475 The status of the file search tool call. One of `in_progress`,

476 `searching`, `incomplete` or `failed`,

477 

478 - `IN_PROGRESS("in_progress")`

479 

480 - `SEARCHING("searching")`

481 

482 - `COMPLETED("completed")`

483 

484 - `INCOMPLETE("incomplete")`

485 

486 - `FAILED("failed")`

487 

488 - `JsonValue; type "file_search_call"constant`

489 

490 The type of the file search tool call. Always `file_search_call`.

491 

492 - `FILE_SEARCH_CALL("file_search_call")`

493 

494 - `Optional<List<Result>> results`

495 

496 The results of the file search tool call.

497 

498 - `Optional<Attributes> attributes`

499 

500 Set of 16 key-value pairs that can be attached to an object. This can be

501 useful for storing additional information about the object in a structured

502 format, and querying for objects via API or the dashboard. Keys are strings

503 with a maximum length of 64 characters. Values are strings with a maximum

504 length of 512 characters, booleans, or numbers.

505 

506 - `String`

507 

508 - `double`

509 

510 - `boolean`

511 

512 - `Optional<String> fileId`

513 

514 The unique ID of the file.

515 

516 - `Optional<String> filename`

517 

518 The name of the file.

519 

520 - `Optional<Double> score`

521 

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

523 

524 - `Optional<String> text`

525 

526 The text that was retrieved from the file.

527 

528 - `class ResponseComputerToolCall:`

529 

530 A tool call to a computer use tool. See the

531 [computer use guide](https://platform.openai.com/docs/guides/tools-computer-use) for more information.

532 

533 - `String id`

534 

535 The unique ID of the computer call.

536 

537 - `String callId`

538 

539 An identifier used when responding to the tool call with output.

540 

541 - `List<PendingSafetyCheck> pendingSafetyChecks`

542 

543 The pending safety checks for the computer call.

544 

545 - `String id`

546 

547 The ID of the pending safety check.

548 

549 - `Optional<String> code`

550 

551 The type of the pending safety check.

552 

553 - `Optional<String> message`

554 

555 Details about the pending safety check.

556 

557 - `Status status`

558 

559 The status of the item. One of `in_progress`, `completed`, or

560 `incomplete`. Populated when items are returned via API.

561 

562 - `IN_PROGRESS("in_progress")`

563 

564 - `COMPLETED("completed")`

565 

566 - `INCOMPLETE("incomplete")`

567 

568 - `Type type`

569 

570 The type of the computer call. Always `computer_call`.

571 

572 - `COMPUTER_CALL("computer_call")`

573 

574 - `Optional<Action> action`

575 

576 A click action.

577 

578 - `class Click:`

579 

580 A click action.

581 

582 - `Button button`

583 

584 Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`.

585 

586 - `LEFT("left")`

587 

588 - `RIGHT("right")`

589 

590 - `WHEEL("wheel")`

591 

592 - `BACK("back")`

593 

594 - `FORWARD("forward")`

595 

596 - `JsonValue; type "click"constant`

597 

598 Specifies the event type. For a click action, this property is always `click`.

599 

600 - `CLICK("click")`

601 

602 - `long x`

603 

604 The x-coordinate where the click occurred.

605 

606 - `long y`

607 

608 The y-coordinate where the click occurred.

609 

610 - `Optional<List<String>> keys`

611 

612 The keys being held while clicking.

613 

614 - `class DoubleClick:`

615 

616 A double click action.

617 

618 - `Optional<List<String>> keys`

619 

620 The keys being held while double-clicking.

621 

622 - `JsonValue; type "double_click"constant`

623 

624 Specifies the event type. For a double click action, this property is always set to `double_click`.

625 

626 - `DOUBLE_CLICK("double_click")`

627 

628 - `long x`

629 

630 The x-coordinate where the double click occurred.

631 

632 - `long y`

633 

634 The y-coordinate where the double click occurred.

635 

636 - `class Drag:`

637 

638 A drag action.

639 

640 - `List<Path> path`

641 

642 An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg

643 

644 ```

645 [

646 { x: 100, y: 200 },

647 { x: 200, y: 300 }

648 ]

649 ```

650 

651 - `long x`

652 

653 The x-coordinate.

654 

655 - `long y`

656 

657 The y-coordinate.

658 

659 - `JsonValue; type "drag"constant`

660 

661 Specifies the event type. For a drag action, this property is always set to `drag`.

662 

663 - `DRAG("drag")`

664 

665 - `Optional<List<String>> keys`

666 

667 The keys being held while dragging the mouse.

668 

669 - `class Keypress:`

670 

671 A collection of keypresses the model would like to perform.

672 

673 - `List<String> keys`

674 

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

676 

677 - `JsonValue; type "keypress"constant`

678 

679 Specifies the event type. For a keypress action, this property is always set to `keypress`.

680 

681 - `KEYPRESS("keypress")`

682 

683 - `class Move:`

684 

685 A mouse move action.

686 

687 - `JsonValue; type "move"constant`

688 

689 Specifies the event type. For a move action, this property is always set to `move`.

690 

691 - `MOVE("move")`

692 

693 - `long x`

694 

695 The x-coordinate to move to.

696 

697 - `long y`

698 

699 The y-coordinate to move to.

700 

701 - `Optional<List<String>> keys`

702 

703 The keys being held while moving the mouse.

704 

705 - `JsonValue;`

706 

707 - `JsonValue; type "screenshot"constant`

708 

709 Specifies the event type. For a screenshot action, this property is always set to `screenshot`.

710 

711 - `SCREENSHOT("screenshot")`

712 

713 - `class Scroll:`

714 

715 A scroll action.

716 

717 - `long scrollX`

718 

719 The horizontal scroll distance.

720 

721 - `long scrollY`

722 

723 The vertical scroll distance.

724 

725 - `JsonValue; type "scroll"constant`

726 

727 Specifies the event type. For a scroll action, this property is always set to `scroll`.

728 

729 - `SCROLL("scroll")`

730 

731 - `long x`

732 

733 The x-coordinate where the scroll occurred.

734 

735 - `long y`

736 

737 The y-coordinate where the scroll occurred.

738 

739 - `Optional<List<String>> keys`

740 

741 The keys being held while scrolling.

742 

743 - `class Type:`

744 

745 An action to type in text.

746 

747 - `String text`

748 

749 The text to type.

750 

751 - `JsonValue; type "type"constant`

752 

753 Specifies the event type. For a type action, this property is always set to `type`.

754 

755 - `TYPE("type")`

756 

757 - `JsonValue;`

758 

759 - `JsonValue; type "wait"constant`

760 

761 Specifies the event type. For a wait action, this property is always set to `wait`.

762 

763 - `WAIT("wait")`

764 

765 - `Optional<List<ComputerAction>> actions`

766 

767 Flattened batched actions for `computer_use`. Each action includes an

768 `type` discriminator and action-specific fields.

769 

770 - `Click`

771 

772 - `Button button`

773 

774 Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`.

775 

776 - `LEFT("left")`

777 

778 - `RIGHT("right")`

779 

780 - `WHEEL("wheel")`

781 

782 - `BACK("back")`

783 

784 - `FORWARD("forward")`

785 

786 - `JsonValue; type "click"constant`

787 

788 Specifies the event type. For a click action, this property is always `click`.

789 

790 - `CLICK("click")`

791 

792 - `long x`

793 

794 The x-coordinate where the click occurred.

795 

796 - `long y`

797 

798 The y-coordinate where the click occurred.

799 

800 - `Optional<List<String>> keys`

801 

802 The keys being held while clicking.

803 

804 - `DoubleClick`

805 

806 - `Optional<List<String>> keys`

807 

808 The keys being held while double-clicking.

809 

810 - `JsonValue; type "double_click"constant`

811 

812 Specifies the event type. For a double click action, this property is always set to `double_click`.

813 

814 - `DOUBLE_CLICK("double_click")`

815 

816 - `long x`

817 

818 The x-coordinate where the double click occurred.

819 

820 - `long y`

821 

822 The y-coordinate where the double click occurred.

823 

824 - `Drag`

825 

826 - `List<Path> path`

827 

828 An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg

829 

830 ```

831 [

832 { x: 100, y: 200 },

833 { x: 200, y: 300 }

834 ]

835 ```

836 

837 - `long x`

838 

839 The x-coordinate.

840 

841 - `long y`

842 

843 The y-coordinate.

844 

845 - `JsonValue; type "drag"constant`

846 

847 Specifies the event type. For a drag action, this property is always set to `drag`.

848 

849 - `DRAG("drag")`

850 

851 - `Optional<List<String>> keys`

852 

853 The keys being held while dragging the mouse.

854 

855 - `Keypress`

856 

857 - `List<String> keys`

858 

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

860 

861 - `JsonValue; type "keypress"constant`

862 

863 Specifies the event type. For a keypress action, this property is always set to `keypress`.

864 

865 - `KEYPRESS("keypress")`

866 

867 - `Move`

868 

869 - `JsonValue; type "move"constant`

870 

871 Specifies the event type. For a move action, this property is always set to `move`.

872 

873 - `MOVE("move")`

874 

875 - `long x`

876 

877 The x-coordinate to move to.

878 

879 - `long y`

880 

881 The y-coordinate to move to.

882 

883 - `Optional<List<String>> keys`

884 

885 The keys being held while moving the mouse.

886 

887 - `JsonValue;`

888 

889 - `JsonValue; type "screenshot"constant`

890 

891 Specifies the event type. For a screenshot action, this property is always set to `screenshot`.

892 

893 - `SCREENSHOT("screenshot")`

894 

895 - `Scroll`

896 

897 - `long scrollX`

898 

899 The horizontal scroll distance.

900 

901 - `long scrollY`

902 

903 The vertical scroll distance.

904 

905 - `JsonValue; type "scroll"constant`

906 

907 Specifies the event type. For a scroll action, this property is always set to `scroll`.

908 

909 - `SCROLL("scroll")`

910 

911 - `long x`

912 

913 The x-coordinate where the scroll occurred.

914 

915 - `long y`

916 

917 The y-coordinate where the scroll occurred.

918 

919 - `Optional<List<String>> keys`

920 

921 The keys being held while scrolling.

922 

923 - `Type`

924 

925 - `String text`

926 

927 The text to type.

928 

929 - `JsonValue; type "type"constant`

930 

931 Specifies the event type. For a type action, this property is always set to `type`.

932 

933 - `TYPE("type")`

934 

935 - `JsonValue;`

936 

937 - `JsonValue; type "wait"constant`

938 

939 Specifies the event type. For a wait action, this property is always set to `wait`.

940 

941 - `WAIT("wait")`

942 

943 - `ComputerCallOutput`

944 

945 - `String callId`

946 

947 The ID of the computer tool call that produced the output.

948 

949 - `ResponseComputerToolCallOutputScreenshot output`

950 

951 A computer screenshot image used with the computer use tool.

952 

953 - `JsonValue; type "computer_screenshot"constant`

954 

955 Specifies the event type. For a computer screenshot, this property is

956 always set to `computer_screenshot`.

957 

958 - `COMPUTER_SCREENSHOT("computer_screenshot")`

959 

960 - `Optional<String> fileId`

961 

962 The identifier of an uploaded file that contains the screenshot.

963 

964 - `Optional<String> imageUrl`

965 

966 The URL of the screenshot image.

967 

968 - `JsonValue; type "computer_call_output"constant`

969 

970 The type of the computer tool call output. Always `computer_call_output`.

971 

972 - `COMPUTER_CALL_OUTPUT("computer_call_output")`

973 

974 - `Optional<String> id`

975 

976 The ID of the computer tool call output.

977 

978 - `Optional<List<AcknowledgedSafetyCheck>> acknowledgedSafetyChecks`

979 

980 The safety checks reported by the API that have been acknowledged by the developer.

981 

982 - `String id`

983 

984 The ID of the pending safety check.

985 

986 - `Optional<String> code`

987 

988 The type of the pending safety check.

989 

990 - `Optional<String> message`

991 

992 Details about the pending safety check.

993 

994 - `Optional<Status> status`

995 

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

997 

998 - `IN_PROGRESS("in_progress")`

999 

1000 - `COMPLETED("completed")`

1001 

1002 - `INCOMPLETE("incomplete")`

1003 

1004 - `class ResponseFunctionWebSearch:`

1005 

1006 The results of a web search tool call. See the

1007 [web search guide](https://platform.openai.com/docs/guides/tools-web-search) for more information.

1008 

1009 - `String id`

1010 

1011 The unique ID of the web search tool call.

1012 

1013 - `Action action`

1014 

1015 An object describing the specific action taken in this web search call.

1016 Includes details on how the model used the web (search, open_page, find_in_page).

1017 

1018 - `class Search:`

1019 

1020 Action type "search" - Performs a web search query.

1021 

1022 - `String query`

1023 

1024 [DEPRECATED] The search query.

1025 

1026 - `JsonValue; type "search"constant`

1027 

1028 The action type.

1029 

1030 - `SEARCH("search")`

1031 

1032 - `Optional<List<String>> queries`

1033 

1034 The search queries.

1035 

1036 - `Optional<List<Source>> sources`

1037 

1038 The sources used in the search.

1039 

1040 - `JsonValue; type "url"constant`

1041 

1042 The type of source. Always `url`.

1043 

1044 - `URL("url")`

1045 

1046 - `String url`

1047 

1048 The URL of the source.

1049 

1050 - `class OpenPage:`

1051 

1052 Action type "open_page" - Opens a specific URL from search results.

1053 

1054 - `JsonValue; type "open_page"constant`

1055 

1056 The action type.

1057 

1058 - `OPEN_PAGE("open_page")`

1059 

1060 - `Optional<String> url`

1061 

1062 The URL opened by the model.

1063 

1064 - `class FindInPage:`

1065 

1066 Action type "find_in_page": Searches for a pattern within a loaded page.

1067 

1068 - `String pattern`

1069 

1070 The pattern or text to search for within the page.

1071 

1072 - `JsonValue; type "find_in_page"constant`

1073 

1074 The action type.

1075 

1076 - `FIND_IN_PAGE("find_in_page")`

1077 

1078 - `String url`

1079 

1080 The URL of the page searched for the pattern.

1081 

1082 - `Status status`

1083 

1084 The status of the web search tool call.

1085 

1086 - `IN_PROGRESS("in_progress")`

1087 

1088 - `SEARCHING("searching")`

1089 

1090 - `COMPLETED("completed")`

1091 

1092 - `FAILED("failed")`

1093 

1094 - `JsonValue; type "web_search_call"constant`

1095 

1096 The type of the web search tool call. Always `web_search_call`.

1097 

1098 - `WEB_SEARCH_CALL("web_search_call")`

1099 

1100 - `class ResponseFunctionToolCall:`

1101 

1102 A tool call to run a function. See the

1103 [function calling guide](https://platform.openai.com/docs/guides/function-calling) for more information.

1104 

1105 - `String arguments`

1106 

1107 A JSON string of the arguments to pass to the function.

1108 

1109 - `String callId`

1110 

1111 The unique ID of the function tool call generated by the model.

1112 

1113 - `String name`

1114 

1115 The name of the function to run.

1116 

1117 - `JsonValue; type "function_call"constant`

1118 

1119 The type of the function tool call. Always `function_call`.

1120 

1121 - `FUNCTION_CALL("function_call")`

1122 

1123 - `Optional<String> id`

1124 

1125 The unique ID of the function tool call.

1126 

1127 - `Optional<String> namespace`

1128 

1129 The namespace of the function to run.

1130 

1131 - `Optional<Status> status`

1132 

1133 The status of the item. One of `in_progress`, `completed`, or

1134 `incomplete`. Populated when items are returned via API.

1135 

1136 - `IN_PROGRESS("in_progress")`

1137 

1138 - `COMPLETED("completed")`

1139 

1140 - `INCOMPLETE("incomplete")`

1141 

1142 - `FunctionCallOutput`

1143 

1144 - `String callId`

1145 

1146 The unique ID of the function tool call generated by the model.

1147 

1148 - `Output output`

1149 

1150 Text, image, or file output of the function tool call.

1151 

1152 - `String`

1153 

1154 - `List<ResponseFunctionCallOutputItem>`

1155 

1156 - `class ResponseInputTextContent:`

1157 

1158 A text input to the model.

1159 

1160 - `String text`

1161 

1162 The text input to the model.

1163 

1164 - `JsonValue; type "input_text"constant`

1165 

1166 The type of the input item. Always `input_text`.

1167 

1168 - `INPUT_TEXT("input_text")`

1169 

1170 - `class ResponseInputImageContent:`

1171 

1172 An image input to the model. Learn about [image inputs](https://platform.openai.com/docs/guides/vision)

1173 

1174 - `JsonValue; type "input_image"constant`

1175 

1176 The type of the input item. Always `input_image`.

1177 

1178 - `INPUT_IMAGE("input_image")`

1179 

1180 - `Optional<Detail> detail`

1181 

1182 The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`.

1183 

1184 - `LOW("low")`

1185 

1186 - `HIGH("high")`

1187 

1188 - `AUTO("auto")`

1189 

1190 - `ORIGINAL("original")`

1191 

1192 - `Optional<String> fileId`

1193 

1194 The ID of the file to be sent to the model.

1195 

1196 - `Optional<String> imageUrl`

1197 

1198 The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.

1199 

1200 - `class ResponseInputFileContent:`

1201 

1202 A file input to the model.

1203 

1204 - `JsonValue; type "input_file"constant`

1205 

1206 The type of the input item. Always `input_file`.

1207 

1208 - `INPUT_FILE("input_file")`

1209 

1210 - `Optional<Detail> detail`

1211 

1212 The detail level of the file to be sent to the model. Use `low` for the default rendering behavior, or `high` to render the file at higher quality. Defaults to `low`.

1213 

1214 - `LOW("low")`

1215 

1216 - `HIGH("high")`

1217 

1218 - `Optional<String> fileData`

1219 

1220 The base64-encoded data of the file to be sent to the model.

1221 

1222 - `Optional<String> fileId`

1223 

1224 The ID of the file to be sent to the model.

1225 

1226 - `Optional<String> fileUrl`

1227 

1228 The URL of the file to be sent to the model.

1229 

1230 - `Optional<String> filename`

1231 

1232 The name of the file to be sent to the model.

1233 

1234 - `JsonValue; type "function_call_output"constant`

1235 

1236 The type of the function tool call output. Always `function_call_output`.

1237 

1238 - `FUNCTION_CALL_OUTPUT("function_call_output")`

1239 

1240 - `Optional<String> id`

1241 

1242 The unique ID of the function tool call output. Populated when this item is returned via API.

1243 

1244 - `Optional<Status> status`

1245 

1246 The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API.

1247 

1248 - `IN_PROGRESS("in_progress")`

1249 

1250 - `COMPLETED("completed")`

1251 

1252 - `INCOMPLETE("incomplete")`

1253 

1254 - `ToolSearchCall`

1255 

1256 - `JsonValue arguments`

1257 

1258 The arguments supplied to the tool search call.

1259 

1260 - `JsonValue; type "tool_search_call"constant`

1261 

1262 The item type. Always `tool_search_call`.

1263 

1264 - `TOOL_SEARCH_CALL("tool_search_call")`

1265 

1266 - `Optional<String> id`

1267 

1268 The unique ID of this tool search call.

1269 

1270 - `Optional<String> callId`

1271 

1272 The unique ID of the tool search call generated by the model.

1273 

1274 - `Optional<Execution> execution`

1275 

1276 Whether tool search was executed by the server or by the client.

1277 

1278 - `SERVER("server")`

1279 

1280 - `CLIENT("client")`

1281 

1282 - `Optional<Status> status`

1283 

1284 The status of the tool search call.

1285 

1286 - `IN_PROGRESS("in_progress")`

1287 

1288 - `COMPLETED("completed")`

1289 

1290 - `INCOMPLETE("incomplete")`

1291 

1292 - `class ResponseToolSearchOutputItemParam:`

1293 

1294 - `List<Tool> tools`

1295 

1296 The loaded tool definitions returned by the tool search output.

1297 

1298 - `class FunctionTool:`

1299 

1300 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).

1301 

1302 - `String name`

1303 

1304 The name of the function to call.

1305 

1306 - `Optional<Parameters> parameters`

1307 

1308 A JSON schema object describing the parameters of the function.

1309 

1310 - `Optional<Boolean> strict`

1311 

1312 Whether to enforce strict parameter validation. Default `true`.

1313 

1314 - `JsonValue; type "function"constant`

1315 

1316 The type of the function tool. Always `function`.

1317 

1318 - `FUNCTION("function")`

1319 

1320 - `Optional<Boolean> deferLoading`

1321 

1322 Whether this function is deferred and loaded via tool search.

1323 

1324 - `Optional<String> description`

1325 

1326 A description of the function. Used by the model to determine whether or not to call the function.

1327 

1328 - `class FileSearchTool:`

1329 

1330 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).

1331 

1332 - `JsonValue; type "file_search"constant`

1333 

1334 The type of the file search tool. Always `file_search`.

1335 

1336 - `FILE_SEARCH("file_search")`

1337 

1338 - `List<String> vectorStoreIds`

1339 

1340 The IDs of the vector stores to search.

1341 

1342 - `Optional<Filters> filters`

1343 

1344 A filter to apply.

1345 

1346 - `class ComparisonFilter:`

1347 

1348 A filter used to compare a specified attribute key to a given value using a defined comparison operation.

1349 

1350 - `String key`

1351 

1352 The key to compare against the value.

1353 

1354 - `Type type`

1355 

1356 Specifies the comparison operator: `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin`.

1357 

1358 - `eq`: equals

1359 - `ne`: not equal

1360 - `gt`: greater than

1361 - `gte`: greater than or equal

1362 - `lt`: less than

1363 - `lte`: less than or equal

1364 - `in`: in

1365 - `nin`: not in

1366 

1367 - `EQ("eq")`

1368 

1369 - `NE("ne")`

1370 

1371 - `GT("gt")`

1372 

1373 - `GTE("gte")`

1374 

1375 - `LT("lt")`

1376 

1377 - `LTE("lte")`

1378 

1379 - `IN("in")`

1380 

1381 - `NIN("nin")`

1382 

1383 - `Value value`

1384 

1385 The value to compare against the attribute key; supports string, number, or boolean types.

1386 

1387 - `String`

1388 

1389 - `double`

1390 

1391 - `boolean`

1392 

1393 - `List<ComparisonFilterValueItem>`

1394 

1395 - `String`

1396 

1397 - `double`

1398 

1399 - `class CompoundFilter:`

1400 

1401 Combine multiple filters using `and` or `or`.

1402 

1403 - `List<Filter> filters`

1404 

1405 Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`.

1406 

1407 - `class ComparisonFilter:`

1408 

1409 A filter used to compare a specified attribute key to a given value using a defined comparison operation.

1410 

1411 - `JsonValue`

1412 

1413 - `Type type`

1414 

1415 Type of operation: `and` or `or`.

1416 

1417 - `AND("and")`

1418 

1419 - `OR("or")`

1420 

1421 - `Optional<Long> maxNumResults`

1422 

1423 The maximum number of results to return. This number should be between 1 and 50 inclusive.

1424 

1425 - `Optional<RankingOptions> rankingOptions`

1426 

1427 Ranking options for search.

1428 

1429 - `Optional<HybridSearch> hybridSearch`

1430 

1431 Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.

1432 

1433 - `double embeddingWeight`

1434 

1435 The weight of the embedding in the reciprocal ranking fusion.

1436 

1437 - `double textWeight`

1438 

1439 The weight of the text in the reciprocal ranking fusion.

1440 

1441 - `Optional<Ranker> ranker`

1442 

1443 The ranker to use for the file search.

1444 

1445 - `AUTO("auto")`

1446 

1447 - `DEFAULT_2024_11_15("default-2024-11-15")`

1448 

1449 - `Optional<Double> scoreThreshold`

1450 

1451 The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.

1452 

1453 - `class ComputerTool:`

1454 

1455 A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use).

1456 

1457 - `JsonValue; type "computer"constant`

1458 

1459 The type of the computer tool. Always `computer`.

1460 

1461 - `COMPUTER("computer")`

1462 

1463 - `class ComputerUsePreviewTool:`

1464 

1465 A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use).

1466 

1467 - `long displayHeight`

1468 

1469 The height of the computer display.

1470 

1471 - `long displayWidth`

1472 

1473 The width of the computer display.

1474 

1475 - `Environment environment`

1476 

1477 The type of computer environment to control.

1478 

1479 - `WINDOWS("windows")`

1480 

1481 - `MAC("mac")`

1482 

1483 - `LINUX("linux")`

1484 

1485 - `UBUNTU("ubuntu")`

1486 

1487 - `BROWSER("browser")`

1488 

1489 - `JsonValue; type "computer_use_preview"constant`

1490 

1491 The type of the computer use tool. Always `computer_use_preview`.

1492 

1493 - `COMPUTER_USE_PREVIEW("computer_use_preview")`

1494 

1495 - `class WebSearchTool:`

1496 

1497 Search the Internet for sources related to the prompt. Learn more about the

1498 [web search tool](https://platform.openai.com/docs/guides/tools-web-search).

1499 

1500 - `Type type`

1501 

1502 The type of the web search tool. One of `web_search` or `web_search_2025_08_26`.

1503 

1504 - `WEB_SEARCH("web_search")`

1505 

1506 - `WEB_SEARCH_2025_08_26("web_search_2025_08_26")`

1507 

1508 - `Optional<Filters> filters`

1509 

1510 Filters for the search.

1511 

1512 - `Optional<List<String>> allowedDomains`

1513 

1514 Allowed domains for the search. If not provided, all domains are allowed.

1515 Subdomains of the provided domains are allowed as well.

1516 

1517 Example: `["pubmed.ncbi.nlm.nih.gov"]`

1518 

1519 - `Optional<SearchContextSize> searchContextSize`

1520 

1521 High level guidance for the amount of context window space to use for the search. One of `low`, `medium`, or `high`. `medium` is the default.

1522 

1523 - `LOW("low")`

1524 

1525 - `MEDIUM("medium")`

1526 

1527 - `HIGH("high")`

1528 

1529 - `Optional<UserLocation> userLocation`

1530 

1531 The approximate location of the user.

1532 

1533 - `Optional<String> city`

1534 

1535 Free text input for the city of the user, e.g. `San Francisco`.

1536 

1537 - `Optional<String> country`

1538 

1539 The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`.

1540 

1541 - `Optional<String> region`

1542 

1543 Free text input for the region of the user, e.g. `California`.

1544 

1545 - `Optional<String> timezone`

1546 

1547 The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`.

1548 

1549 - `Optional<Type> type`

1550 

1551 The type of location approximation. Always `approximate`.

1552 

1553 - `APPROXIMATE("approximate")`

1554 

1555 - `Mcp`

1556 

1557 - `String serverLabel`

1558 

1559 A label for this MCP server, used to identify it in tool calls.

1560 

1561 - `JsonValue; type "mcp"constant`

1562 

1563 The type of the MCP tool. Always `mcp`.

1564 

1565 - `MCP("mcp")`

1566 

1567 - `Optional<AllowedTools> allowedTools`

1568 

1569 List of allowed tool names or a filter object.

1570 

1571 - `List<String>`

1572 

1573 - `class McpToolFilter:`

1574 

1575 A filter object to specify which tools are allowed.

1576 

1577 - `Optional<Boolean> readOnly`

1578 

1579 Indicates whether or not a tool modifies data or is read-only. If an

1580 MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint),

1581 it will match this filter.

1582 

1583 - `Optional<List<String>> toolNames`

1584 

1585 List of allowed tool names.

1586 

1587 - `Optional<String> authorization`

1588 

1589 An OAuth access token that can be used with a remote MCP server, either

1590 with a custom MCP server URL or a service connector. Your application

1591 must handle the OAuth authorization flow and provide the token here.

1592 

1593 - `Optional<ConnectorId> connectorId`

1594 

1595 Identifier for service connectors, like those available in ChatGPT. One of

1596 `server_url` or `connector_id` must be provided. Learn more about service

1597 connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors).

1598 

1599 Currently supported `connector_id` values are:

1600 

1601 - Dropbox: `connector_dropbox`

1602 - Gmail: `connector_gmail`

1603 - Google Calendar: `connector_googlecalendar`

1604 - Google Drive: `connector_googledrive`

1605 - Microsoft Teams: `connector_microsoftteams`

1606 - Outlook Calendar: `connector_outlookcalendar`

1607 - Outlook Email: `connector_outlookemail`

1608 - SharePoint: `connector_sharepoint`

1609 

1610 - `CONNECTOR_DROPBOX("connector_dropbox")`

1611 

1612 - `CONNECTOR_GMAIL("connector_gmail")`

1613 

1614 - `CONNECTOR_GOOGLECALENDAR("connector_googlecalendar")`

1615 

1616 - `CONNECTOR_GOOGLEDRIVE("connector_googledrive")`

1617 

1618 - `CONNECTOR_MICROSOFTTEAMS("connector_microsoftteams")`

1619 

1620 - `CONNECTOR_OUTLOOKCALENDAR("connector_outlookcalendar")`

1621 

1622 - `CONNECTOR_OUTLOOKEMAIL("connector_outlookemail")`

1623 

1624 - `CONNECTOR_SHAREPOINT("connector_sharepoint")`

1625 

1626 - `Optional<Boolean> deferLoading`

1627 

1628 Whether this MCP tool is deferred and discovered via tool search.

1629 

1630 - `Optional<Headers> headers`

1631 

1632 Optional HTTP headers to send to the MCP server. Use for authentication

1633 or other purposes.

1634 

1635 - `Optional<RequireApproval> requireApproval`

1636 

1637 Specify which of the MCP server's tools require approval.

1638 

1639 - `class McpToolApprovalFilter:`

1640 

1641 Specify which of the MCP server's tools require approval. Can be

1642 `always`, `never`, or a filter object associated with tools

1643 that require approval.

1644 

1645 - `Optional<Always> always`

1646 

1647 A filter object to specify which tools are allowed.

1648 

1649 - `Optional<Boolean> readOnly`

1650 

1651 Indicates whether or not a tool modifies data or is read-only. If an

1652 MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint),

1653 it will match this filter.

1654 

1655 - `Optional<List<String>> toolNames`

1656 

1657 List of allowed tool names.

1658 

1659 - `Optional<Never> never`

1660 

1661 A filter object to specify which tools are allowed.

1662 

1663 - `Optional<Boolean> readOnly`

1664 

1665 Indicates whether or not a tool modifies data or is read-only. If an

1666 MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint),

1667 it will match this filter.

1668 

1669 - `Optional<List<String>> toolNames`

1670 

1671 List of allowed tool names.

1672 

1673 - `enum McpToolApprovalSetting:`

1674 

1675 Specify a single approval policy for all tools. One of `always` or

1676 `never`. When set to `always`, all tools will require approval. When

1677 set to `never`, all tools will not require approval.

1678 

1679 - `ALWAYS("always")`

1680 

1681 - `NEVER("never")`

1682 

1683 - `Optional<String> serverDescription`

1684 

1685 Optional description of the MCP server, used to provide more context.

1686 

1687 - `Optional<String> serverUrl`

1688 

1689 The URL for the MCP server. One of `server_url` or `connector_id` must be

1690 provided.

1691 

1692 - `CodeInterpreter`

1693 

1694 - `Container container`

1695 

1696 The code interpreter container. Can be a container ID or an object that

1697 specifies uploaded file IDs to make available to your code, along with an

1698 optional `memory_limit` setting.

1699 

1700 - `String`

1701 

1702 - `class CodeInterpreterToolAuto:`

1703 

1704 Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.

1705 

1706 - `JsonValue; type "auto"constant`

1707 

1708 Always `auto`.

1709 

1710 - `AUTO("auto")`

1711 

1712 - `Optional<List<String>> fileIds`

1713 

1714 An optional list of uploaded files to make available to your code.

1715 

1716 - `Optional<MemoryLimit> memoryLimit`

1717 

1718 The memory limit for the code interpreter container.

1719 

1720 - `_1G("1g")`

1721 

1722 - `_4G("4g")`

1723 

1724 - `_16G("16g")`

1725 

1726 - `_64G("64g")`

1727 

1728 - `Optional<NetworkPolicy> networkPolicy`

1729 

1730 Network access policy for the container.

1731 

1732 - `class ContainerNetworkPolicyDisabled:`

1733 

1734 - `JsonValue; type "disabled"constant`

1735 

1736 Disable outbound network access. Always `disabled`.

1737 

1738 - `DISABLED("disabled")`

1739 

1740 - `class ContainerNetworkPolicyAllowlist:`

1741 

1742 - `List<String> allowedDomains`

1743 

1744 A list of allowed domains when type is `allowlist`.

1745 

1746 - `JsonValue; type "allowlist"constant`

1747 

1748 Allow outbound network access only to specified domains. Always `allowlist`.

1749 

1750 - `ALLOWLIST("allowlist")`

1751 

1752 - `Optional<List<ContainerNetworkPolicyDomainSecret>> domainSecrets`

1753 

1754 Optional domain-scoped secrets for allowlisted domains.

1755 

1756 - `String domain`

1757 

1758 The domain associated with the secret.

1759 

1760 - `String name`

1761 

1762 The name of the secret to inject for the domain.

1763 

1764 - `String value`

1765 

1766 The secret value to inject for the domain.

1767 

1768 - `JsonValue; type "code_interpreter"constant`

1769 

1770 The type of the code interpreter tool. Always `code_interpreter`.

1771 

1772 - `CODE_INTERPRETER("code_interpreter")`

1773 

1774 - `ImageGeneration`

1775 

1776 - `JsonValue; type "image_generation"constant`

1777 

1778 The type of the image generation tool. Always `image_generation`.

1779 

1780 - `IMAGE_GENERATION("image_generation")`

1781 

1782 - `Optional<Action> action`

1783 

1784 Whether to generate a new image or edit an existing image. Default: `auto`.

1785 

1786 - `GENERATE("generate")`

1787 

1788 - `EDIT("edit")`

1789 

1790 - `AUTO("auto")`

1791 

1792 - `Optional<Background> background`

1793 

1794 Allows to set transparency for the background of the generated image(s).

1795 This parameter is only supported for GPT image models that support

1796 transparent backgrounds. Must be one of `transparent`, `opaque`, or

1797 `auto` (default value). When `auto` is used, the model will

1798 automatically determine the best background for the image.

1799 

1800 `gpt-image-2` and `gpt-image-2-2026-04-21` do not support

1801 transparent backgrounds. Requests with `background` set to

1802 `transparent` will return an error for these models; use `opaque` or

1803 `auto` instead.

1804 

1805 If `transparent`, the output format needs to support transparency,

1806 so it should be set to either `png` (default value) or `webp`.

1807 

1808 - `TRANSPARENT("transparent")`

1809 

1810 - `OPAQUE("opaque")`

1811 

1812 - `AUTO("auto")`

1813 

1814 - `Optional<InputFidelity> inputFidelity`

1815 

1816 Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`.

1817 

1818 - `HIGH("high")`

1819 

1820 - `LOW("low")`

1821 

1822 - `Optional<InputImageMask> inputImageMask`

1823 

1824 Optional mask for inpainting. Contains `image_url`

1825 (string, optional) and `file_id` (string, optional).

1826 

1827 - `Optional<String> fileId`

1828 

1829 File ID for the mask image.

1830 

1831 - `Optional<String> imageUrl`

1832 

1833 Base64-encoded mask image.

1834 

1835 - `Optional<Model> model`

1836 

1837 The image generation model to use. Default: `gpt-image-1`.

1838 

1839 - `GPT_IMAGE_1("gpt-image-1")`

1840 

1841 - `GPT_IMAGE_1_MINI("gpt-image-1-mini")`

1842 

1843 - `GPT_IMAGE_2("gpt-image-2")`

1844 

1845 - `GPT_IMAGE_2_2026_04_21("gpt-image-2-2026-04-21")`

1846 

1847 - `GPT_IMAGE_1_5("gpt-image-1.5")`

1848 

1849 - `CHATGPT_IMAGE_LATEST("chatgpt-image-latest")`

1850 

1851 - `Optional<Moderation> moderation`

1852 

1853 Moderation level for the generated image. Default: `auto`.

1854 

1855 - `AUTO("auto")`

1856 

1857 - `LOW("low")`

1858 

1859 - `Optional<Long> outputCompression`

1860 

1861 Compression level for the output image. Default: 100.

1862 

1863 - `Optional<OutputFormat> outputFormat`

1864 

1865 The output format of the generated image. One of `png`, `webp`, or

1866 `jpeg`. Default: `png`.

1867 

1868 - `PNG("png")`

1869 

1870 - `WEBP("webp")`

1871 

1872 - `JPEG("jpeg")`

1873 

1874 - `Optional<Long> partialImages`

1875 

1876 Number of partial images to generate in streaming mode, from 0 (default value) to 3.

1877 

1878 - `Optional<Quality> quality`

1879 

1880 The quality of the generated image. One of `low`, `medium`, `high`,

1881 or `auto`. Default: `auto`.

1882 

1883 - `LOW("low")`

1884 

1885 - `MEDIUM("medium")`

1886 

1887 - `HIGH("high")`

1888 

1889 - `AUTO("auto")`

1890 

1891 - `Optional<Size> size`

1892 

1893 The size of the generated images. For `gpt-image-2` and `gpt-image-2-2026-04-21`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`.

1894 

1895 - `_1024X1024("1024x1024")`

1896 

1897 - `_1024X1536("1024x1536")`

1898 

1899 - `_1536X1024("1536x1024")`

1900 

1901 - `AUTO("auto")`

1902 

1903 - `JsonValue;`

1904 

1905 - `JsonValue; type "local_shell"constant`

1906 

1907 The type of the local shell tool. Always `local_shell`.

1908 

1909 - `LOCAL_SHELL("local_shell")`

1910 

1911 - `class FunctionShellTool:`

1912 

1913 A tool that allows the model to execute shell commands.

1914 

1915 - `JsonValue; type "shell"constant`

1916 

1917 The type of the shell tool. Always `shell`.

1918 

1919 - `SHELL("shell")`

1920 

1921 - `Optional<Environment> environment`

1922 

1923 - `class ContainerAuto:`

1924 

1925 - `JsonValue; type "container_auto"constant`

1926 

1927 Automatically creates a container for this request

1928 

1929 - `CONTAINER_AUTO("container_auto")`

1930 

1931 - `Optional<List<String>> fileIds`

1932 

1933 An optional list of uploaded files to make available to your code.

1934 

1935 - `Optional<MemoryLimit> memoryLimit`

1936 

1937 The memory limit for the container.

1938 

1939 - `_1G("1g")`

1940 

1941 - `_4G("4g")`

1942 

1943 - `_16G("16g")`

1944 

1945 - `_64G("64g")`

1946 

1947 - `Optional<NetworkPolicy> networkPolicy`

1948 

1949 Network access policy for the container.

1950 

1951 - `class ContainerNetworkPolicyDisabled:`

1952 

1953 - `class ContainerNetworkPolicyAllowlist:`

1954 

1955 - `Optional<List<Skill>> skills`

1956 

1957 An optional list of skills referenced by id or inline data.

1958 

1959 - `class SkillReference:`

1960 

1961 - `String skillId`

1962 

1963 The ID of the referenced skill.

1964 

1965 - `JsonValue; type "skill_reference"constant`

1966 

1967 References a skill created with the /v1/skills endpoint.

1968 

1969 - `SKILL_REFERENCE("skill_reference")`

1970 

1971 - `Optional<String> version`

1972 

1973 Optional skill version. Use a positive integer or 'latest'. Omit for default.

1974 

1975 - `class InlineSkill:`

1976 

1977 - `String description`

1978 

1979 The description of the skill.

1980 

1981 - `String name`

1982 

1983 The name of the skill.

1984 

1985 - `InlineSkillSource source`

1986 

1987 Inline skill payload

1988 

1989 - `String data`

1990 

1991 Base64-encoded skill zip bundle.

1992 

1993 - `JsonValue; mediaType "application/zip"constant`

1994 

1995 The media type of the inline skill payload. Must be `application/zip`.

1996