Reference 2026-06-02 06:51 UTC to 2026-06-04 06:52 UTC

743 743 

744 - `"audio"`744 - `"audio"`

745 745 

746- `moderation: optional object { model }`

747 

748 Configuration for running moderation on the request input and generated output.

749 

750 - `model: string`

751 

752 The moderation model to use for moderated completions, e.g. 'omni-moderation-latest'.

753 

746- `n: optional number`754- `n: optional number`

747 755 

748 How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs.756 How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs.

1274 1282 

1275### Returns1283### Returns

1276 1284 

1277- `ChatCompletion object { id, choices, created, 5 more }`1285- `ChatCompletion object { id, choices, created, 6 more }`

1278 1286 

1279 Represents a chat completion response returned by model, based on the provided input.1287 Represents a chat completion response returned by model, based on the provided input.

1280 1288 

1292 `length` if the maximum number of tokens specified in the request was reached,1300 `length` if the maximum number of tokens specified in the request was reached,

1293 `content_filter` if content was omitted due to a flag from our content filters,1301 `content_filter` if content was omitted due to a flag from our content filters,

1294 `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function.1302 `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function.

1303 Read the [Model Spec](https://model-spec.openai.com/2025-12-18.html) for more.

1295 1304 

1296 - `"stop"`1305 - `"stop"`

1297 1306 

1518 1527 

1519 - `"chat.completion"`1528 - `"chat.completion"`

1520 1529 

1530 - `moderation: optional object { input, output }`

1531 

1532 Moderation results for the request input and generated output, if moderated

1533 completions were requested.

1534 

1535 - `input: object { model, results, type } or object { code, message, type }`

1536 

1537 Moderation for the request input.

1538 

1539 - `ModerationResults object { model, results, type }`

1540 

1541 Successful moderation results for the request input or generated output.

1542 

1543 - `model: string`

1544 

1545 The moderation model used to generate the results.

1546 

1547 - `results: array of object { categories, category_applied_input_types, category_scores, 3 more }`

1548 

1549 A list of moderation results.

1550 

1551 - `categories: map[boolean]`

1552 

1553 A dictionary of moderation categories to booleans, True if the input is flagged under this category.

1554 

1555 - `category_applied_input_types: map[array of "text" or "image"]`

1556 

1557 Which modalities of input are reflected by the score for each category.

1558 

1559 - `"text"`

1560 

1561 - `"image"`

1562 

1563 - `category_scores: map[number]`

1564 

1565 A dictionary of moderation categories to scores.

1566 

1567 - `flagged: boolean`

1568 

1569 A boolean indicating whether the content was flagged by any category.

1570 

1571 - `model: string`

1572 

1573 The moderation model that produced this result.

1574 

1575 - `type: "moderation_result"`

1576 

1577 The object type, which was always `moderation_result` for successful moderation results.

1578 

1579 - `"moderation_result"`

1580 

1581 - `type: "moderation_results"`

1582 

1583 The object type, which is always `moderation_results`.

1584 

1585 - `"moderation_results"`

1586 

1587 - `Error object { code, message, type }`

1588 

1589 An error produced while attempting moderation.

1590 

1591 - `code: string`

1592 

1593 The error code.

1594 

1595 - `message: string`

1596 

1597 The error message.

1598 

1599 - `type: "error"`

1600 

1601 The object type, which is always `error`.

1602 

1603 - `"error"`

1604 

1605 - `output: object { model, results, type } or object { code, message, type }`

1606 

1607 Moderation for the generated output.

1608 

1609 - `ModerationResults object { model, results, type }`

1610 

1611 Successful moderation results for the request input or generated output.

1612 

1613 - `model: string`

1614 

1615 The moderation model used to generate the results.

1616 

1617 - `results: array of object { categories, category_applied_input_types, category_scores, 3 more }`

1618 

1619 A list of moderation results.

1620 

1621 - `categories: map[boolean]`

1622 

1623 A dictionary of moderation categories to booleans, True if the input is flagged under this category.

1624 

1625 - `category_applied_input_types: map[array of "text" or "image"]`

1626 

1627 Which modalities of input are reflected by the score for each category.

1628 

1629 - `"text"`

1630 

1631 - `"image"`

1632 

1633 - `category_scores: map[number]`

1634 

1635 A dictionary of moderation categories to scores.

1636 

1637 - `flagged: boolean`

1638 

1639 A boolean indicating whether the content was flagged by any category.

1640 

1641 - `model: string`

1642 

1643 The moderation model that produced this result.

1644 

1645 - `type: "moderation_result"`

1646 

1647 The object type, which was always `moderation_result` for successful moderation results.

1648 

1649 - `"moderation_result"`

1650 

1651 - `type: "moderation_results"`

1652 

1653 The object type, which is always `moderation_results`.

1654 

1655 - `"moderation_results"`

1656 

1657 - `Error object { code, message, type }`

1658 

1659 An error produced while attempting moderation.

1660 

1661 - `code: string`

1662 

1663 The error code.

1664 

1665 - `message: string`

1666 

1667 The error message.

1668 

1669 - `type: "error"`

1670 

1671 The object type, which is always `error`.

1672 

1673 - `"error"`

1674 

1521 - `service_tier: optional "auto" or "default" or "flex" or 2 more`1675 - `service_tier: optional "auto" or "default" or "flex" or 2 more`

1522 1676 

1523 Specifies the processing type used for serving the request.1677 Specifies the processing type used for serving the request.

1709 "created": 0,1863 "created": 0,

1710 "model": "model",1864 "model": "model",

1711 "object": "chat.completion",1865 "object": "chat.completion",

1866 "moderation": {

1867 "input": {

1868 "model": "model",

1869 "results": [

1870 {

1871 "categories": {

1872 "foo": true

1873 },

1874 "category_applied_input_types": {

1875 "foo": [

1876 "text"

1877 ]

1878 },

1879 "category_scores": {

1880 "foo": 0

1881 },

1882 "flagged": true,

1883 "model": "model",

1884 "type": "moderation_result"

1885 }

1886 ],

1887 "type": "moderation_results"

1888 },

1889 "output": {

1890 "model": "model",

1891 "results": [

1892 {

1893 "categories": {

1894 "foo": true

1895 },

1896 "category_applied_input_types": {

1897 "foo": [

1898 "text"

1899 ]

1900 },

1901 "category_scores": {

1902 "foo": 0

1903 },

1904 "flagged": true,

1905 "model": "model",

1906 "type": "moderation_result"

1907 }

1908 ],

1909 "type": "moderation_results"

1910 }

1911 },

1712 "service_tier": "auto",1912 "service_tier": "auto",

1713 "system_fingerprint": "system_fingerprint",1913 "system_fingerprint": "system_fingerprint",

1714 "usage": {1914 "usage": {

2244 `length` if the maximum number of tokens specified in the request was reached,2444 `length` if the maximum number of tokens specified in the request was reached,

2245 `content_filter` if content was omitted due to a flag from our content filters,2445 `content_filter` if content was omitted due to a flag from our content filters,

2246 `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function.2446 `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function.

2447 Read the [Model Spec](https://model-spec.openai.com/2025-12-18.html) for more.

2247 2448 

2248 - `"stop"`2449 - `"stop"`

2249 2450 

2470 2671 

2471 - `"chat.completion"`2672 - `"chat.completion"`

2472 2673 

2674 - `moderation: optional object { input, output }`

2675 

2676 Moderation results for the request input and generated output, if moderated

2677 completions were requested.

2678 

2679 - `input: object { model, results, type } or object { code, message, type }`

2680 

2681 Moderation for the request input.

2682 

2683 - `ModerationResults object { model, results, type }`

2684 

2685 Successful moderation results for the request input or generated output.

2686 

2687 - `model: string`

2688 

2689 The moderation model used to generate the results.

2690 

2691 - `results: array of object { categories, category_applied_input_types, category_scores, 3 more }`

2692 

2693 A list of moderation results.

2694 

2695 - `categories: map[boolean]`

2696 

2697 A dictionary of moderation categories to booleans, True if the input is flagged under this category.

2698 

2699 - `category_applied_input_types: map[array of "text" or "image"]`

2700 

2701 Which modalities of input are reflected by the score for each category.

2702 

2703 - `"text"`

2704 

2705 - `"image"`

2706 

2707 - `category_scores: map[number]`

2708 

2709 A dictionary of moderation categories to scores.

2710 

2711 - `flagged: boolean`

2712 

2713 A boolean indicating whether the content was flagged by any category.

2714 

2715 - `model: string`

2716 

2717 The moderation model that produced this result.

2718 

2719 - `type: "moderation_result"`

2720 

2721 The object type, which was always `moderation_result` for successful moderation results.

2722 

2723 - `"moderation_result"`

2724 

2725 - `type: "moderation_results"`

2726 

2727 The object type, which is always `moderation_results`.

2728 

2729 - `"moderation_results"`

2730 

2731 - `Error object { code, message, type }`

2732 

2733 An error produced while attempting moderation.

2734 

2735 - `code: string`

2736 

2737 The error code.

2738 

2739 - `message: string`

2740 

2741 The error message.

2742 

2743 - `type: "error"`

2744 

2745 The object type, which is always `error`.

2746 

2747 - `"error"`

2748 

2749 - `output: object { model, results, type } or object { code, message, type }`

2750 

2751 Moderation for the generated output.

2752 

2753 - `ModerationResults object { model, results, type }`

2754 

2755 Successful moderation results for the request input or generated output.

2756 

2757 - `model: string`

2758 

2759 The moderation model used to generate the results.

2760 

2761 - `results: array of object { categories, category_applied_input_types, category_scores, 3 more }`

2762 

2763 A list of moderation results.

2764 

2765 - `categories: map[boolean]`

2766 

2767 A dictionary of moderation categories to booleans, True if the input is flagged under this category.

2768 

2769 - `category_applied_input_types: map[array of "text" or "image"]`

2770 

2771 Which modalities of input are reflected by the score for each category.

2772 

2773 - `"text"`

2774 

2775 - `"image"`

2776 

2777 - `category_scores: map[number]`

2778 

2779 A dictionary of moderation categories to scores.

2780 

2781 - `flagged: boolean`

2782 

2783 A boolean indicating whether the content was flagged by any category.

2784 

2785 - `model: string`

2786 

2787 The moderation model that produced this result.

2788 

2789 - `type: "moderation_result"`

2790 

2791 The object type, which was always `moderation_result` for successful moderation results.

2792 

2793 - `"moderation_result"`

2794 

2795 - `type: "moderation_results"`

2796 

2797 The object type, which is always `moderation_results`.

2798 

2799 - `"moderation_results"`

2800 

2801 - `Error object { code, message, type }`

2802 

2803 An error produced while attempting moderation.

2804 

2805 - `code: string`

2806 

2807 The error code.

2808 

2809 - `message: string`

2810 

2811 The error message.

2812 

2813 - `type: "error"`

2814 

2815 The object type, which is always `error`.

2816 

2817 - `"error"`

2818 

2473 - `service_tier: optional "auto" or "default" or "flex" or 2 more`2819 - `service_tier: optional "auto" or "default" or "flex" or 2 more`

2474 2820 

2475 Specifies the processing type used for serving the request.2821 Specifies the processing type used for serving the request.

2665 "created": 0,3011 "created": 0,

2666 "model": "model",3012 "model": "model",

2667 "object": "chat.completion",3013 "object": "chat.completion",

3014 "moderation": {

3015 "input": {

3016 "model": "model",

3017 "results": [

3018 {

3019 "categories": {

3020 "foo": true

3021 },

3022 "category_applied_input_types": {

3023 "foo": [

3024 "text"

3025 ]

3026 },

3027 "category_scores": {

3028 "foo": 0

3029 },

3030 "flagged": true,

3031 "model": "model",

3032 "type": "moderation_result"

3033 }

3034 ],

3035 "type": "moderation_results"

3036 },

3037 "output": {

3038 "model": "model",

3039 "results": [

3040 {

3041 "categories": {

3042 "foo": true

3043 },

3044 "category_applied_input_types": {

3045 "foo": [

3046 "text"

3047 ]

3048 },

3049 "category_scores": {

3050 "foo": 0

3051 },

3052 "flagged": true,

3053 "model": "model",

3054 "type": "moderation_result"

3055 }

3056 ],

3057 "type": "moderation_results"

3058 }

3059 },

2668 "service_tier": "auto",3060 "service_tier": "auto",

2669 "system_fingerprint": "system_fingerprint",3061 "system_fingerprint": "system_fingerprint",

2670 "usage": {3062 "usage": {

2762 3154 

2763### Returns3155### Returns

2764 3156 

2765- `ChatCompletion object { id, choices, created, 5 more }`3157- `ChatCompletion object { id, choices, created, 6 more }`

2766 3158 

2767 Represents a chat completion response returned by model, based on the provided input.3159 Represents a chat completion response returned by model, based on the provided input.

2768 3160 

2780 `length` if the maximum number of tokens specified in the request was reached,3172 `length` if the maximum number of tokens specified in the request was reached,

2781 `content_filter` if content was omitted due to a flag from our content filters,3173 `content_filter` if content was omitted due to a flag from our content filters,

2782 `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function.3174 `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function.

3175 Read the [Model Spec](https://model-spec.openai.com/2025-12-18.html) for more.

2783 3176 

2784 - `"stop"`3177 - `"stop"`

2785 3178 

3006 3399 

3007 - `"chat.completion"`3400 - `"chat.completion"`

3008 3401 

3009 - `service_tier: optional "auto" or "default" or "flex" or 2 more`3402 - `moderation: optional object { input, output }`

3010 3403 

3011 Specifies the processing type used for serving the request.3404 Moderation results for the request input and generated output, if moderated

3405 completions were requested.

3012 3406 

3013 - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.3407 - `input: object { model, results, type } or object { code, message, type }`

3014 - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.

3015 - If set to '[flex](/docs/guides/flex-processing)' or '[priority](https://openai.com/api-priority-processing/)', then the request will be processed with the corresponding service tier.

3016 - When not set, the default behavior is 'auto'.

3017 3408 

3018 When the `service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.3409 Moderation for the request input.

3019 3410 

3020 - `"auto"`3411 - `ModerationResults object { model, results, type }`

3021 3412 

3022 - `"default"`3413 Successful moderation results for the request input or generated output.

3023 3414 

3024 - `"flex"`3415 - `model: string`

3025 3416 

3026 - `"scale"`3417 The moderation model used to generate the results.

3027 3418 

3028 - `"priority"`3419 - `results: array of object { categories, category_applied_input_types, category_scores, 3 more }`

3029 3420 

3030 - `system_fingerprint: optional string`3421 A list of moderation results.

3031 3422 

3032 This fingerprint represents the backend configuration that the model runs with.3423 - `categories: map[boolean]`

3033 3424 

3034 Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism.3425 A dictionary of moderation categories to booleans, True if the input is flagged under this category.

3035 3426 

3036 - `usage: optional CompletionUsage`3427 - `category_applied_input_types: map[array of "text" or "image"]`

3037 3428 

3038 Usage statistics for the completion request.3429 Which modalities of input are reflected by the score for each category.

3039 3430 

3040 - `completion_tokens: number`3431 - `"text"`

3041 3432 

3042 Number of tokens in the generated completion.3433 - `"image"`

3043 3434 

3044 - `prompt_tokens: number`3435 - `category_scores: map[number]`

3045 3436 

3046 Number of tokens in the prompt.3437 A dictionary of moderation categories to scores.

3047 3438 

3048 - `total_tokens: number`3439 - `flagged: boolean`

3049 3440 

3050 Total number of tokens used in the request (prompt + completion).3441 A boolean indicating whether the content was flagged by any category.

3051 3442 

3052 - `completion_tokens_details: optional object { accepted_prediction_tokens, audio_tokens, reasoning_tokens, rejected_prediction_tokens }`3443 - `model: string`

3053 3444 

3054 Breakdown of tokens used in a completion.3445 The moderation model that produced this result.

3055 3446 

3056 - `accepted_prediction_tokens: optional number`3447 - `type: "moderation_result"`

3057 3448 

3058 When using Predicted Outputs, the number of tokens in the3449 The object type, which was always `moderation_result` for successful moderation results.

3059 prediction that appeared in the completion.

3060 3450 

3061 - `audio_tokens: optional number`3451 - `"moderation_result"`

3062 3452 

3063 Audio input tokens generated by the model.3453 - `type: "moderation_results"`

3064 3454 

3065 - `reasoning_tokens: optional number`3455 The object type, which is always `moderation_results`.

3066 3456 

3067 Tokens generated by the model for reasoning.3457 - `"moderation_results"`

3068 3458 

3069 - `rejected_prediction_tokens: optional number`3459 - `Error object { code, message, type }`

3070 3460 

3071 When using Predicted Outputs, the number of tokens in the3461 An error produced while attempting moderation.

3072 prediction that did not appear in the completion. However, like

3073 reasoning tokens, these tokens are still counted in the total

3074 completion tokens for purposes of billing, output, and context window

3075 limits.

3076 3462 

3077 - `prompt_tokens_details: optional object { audio_tokens, cached_tokens }`3463 - `code: string`

3078 3464 

3079 Breakdown of tokens used in the prompt.3465 The error code.

3080 3466 

3081 - `audio_tokens: optional number`3467 - `message: string`

3082 3468 

3083 Audio input tokens present in the prompt.3469 The error message.

3084 3470 

3085 - `cached_tokens: optional number`3471 - `type: "error"`

3086 3472 

3087 Cached tokens present in the prompt.3473 The object type, which is always `error`.

3088 3474 

3089### Example3475 - `"error"`

3090 3476 

3091```http3477 - `output: object { model, results, type } or object { code, message, type }`

3092curl https://api.openai.com/v1/chat/completions/$COMPLETION_ID \

3093 -H "Authorization: Bearer $OPENAI_API_KEY"

3094```

3095 3478 

3096#### Response3479 Moderation for the generated output.

3480 

3481 - `ModerationResults object { model, results, type }`

3482 

3483 Successful moderation results for the request input or generated output.

3484 

3485 - `model: string`

3486 

3487 The moderation model used to generate the results.

3488 

3489 - `results: array of object { categories, category_applied_input_types, category_scores, 3 more }`

3490 

3491 A list of moderation results.

3492 

3493 - `categories: map[boolean]`

3494 

3495 A dictionary of moderation categories to booleans, True if the input is flagged under this category.

3496 

3497 - `category_applied_input_types: map[array of "text" or "image"]`

3498 

3499 Which modalities of input are reflected by the score for each category.

3500 

3501 - `"text"`

3502 

3503 - `"image"`

3504 

3505 - `category_scores: map[number]`

3506 

3507 A dictionary of moderation categories to scores.

3508 

3509 - `flagged: boolean`

3510 

3511 A boolean indicating whether the content was flagged by any category.

3512 

3513 - `model: string`

3514 

3515 The moderation model that produced this result.

3516 

3517 - `type: "moderation_result"`

3518 

3519 The object type, which was always `moderation_result` for successful moderation results.

3520 

3521 - `"moderation_result"`

3522 

3523 - `type: "moderation_results"`

3524 

3525 The object type, which is always `moderation_results`.

3526 

3527 - `"moderation_results"`

3528 

3529 - `Error object { code, message, type }`

3530 

3531 An error produced while attempting moderation.

3532 

3533 - `code: string`

3534 

3535 The error code.

3536 

3537 - `message: string`

3538 

3539 The error message.

3540 

3541 - `type: "error"`

3542 

3543 The object type, which is always `error`.

3544 

3545 - `"error"`

3546 

3547 - `service_tier: optional "auto" or "default" or "flex" or 2 more`

3548 

3549 Specifies the processing type used for serving the request.

3550 

3551 - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.

3552 - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.

3553 - If set to '[flex](/docs/guides/flex-processing)' or '[priority](https://openai.com/api-priority-processing/)', then the request will be processed with the corresponding service tier.

3554 - When not set, the default behavior is 'auto'.

3555 

3556 When the `service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.

3557 

3558 - `"auto"`

3559 

3560 - `"default"`

3561 

3562 - `"flex"`

3563 

3564 - `"scale"`

3565 

3566 - `"priority"`

3567 

3568 - `system_fingerprint: optional string`

3569 

3570 This fingerprint represents the backend configuration that the model runs with.

3571 

3572 Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism.

3573 

3574 - `usage: optional CompletionUsage`

3575 

3576 Usage statistics for the completion request.

3577 

3578 - `completion_tokens: number`

3579 

3580 Number of tokens in the generated completion.

3581 

3582 - `prompt_tokens: number`

3583 

3584 Number of tokens in the prompt.

3585 

3586 - `total_tokens: number`

3587 

3588 Total number of tokens used in the request (prompt + completion).

3589 

3590 - `completion_tokens_details: optional object { accepted_prediction_tokens, audio_tokens, reasoning_tokens, rejected_prediction_tokens }`

3591 

3592 Breakdown of tokens used in a completion.

3593 

3594 - `accepted_prediction_tokens: optional number`

3595 

3596 When using Predicted Outputs, the number of tokens in the

3597 prediction that appeared in the completion.

3598 

3599 - `audio_tokens: optional number`

3600 

3601 Audio input tokens generated by the model.

3602 

3603 - `reasoning_tokens: optional number`

3604 

3605 Tokens generated by the model for reasoning.

3606 

3607 - `rejected_prediction_tokens: optional number`

3608 

3609 When using Predicted Outputs, the number of tokens in the

3610 prediction that did not appear in the completion. However, like

3611 reasoning tokens, these tokens are still counted in the total

3612 completion tokens for purposes of billing, output, and context window

3613 limits.

3614 

3615 - `prompt_tokens_details: optional object { audio_tokens, cached_tokens }`

3616 

3617 Breakdown of tokens used in the prompt.

3618 

3619 - `audio_tokens: optional number`

3620 

3621 Audio input tokens present in the prompt.

3622 

3623 - `cached_tokens: optional number`

3624 

3625 Cached tokens present in the prompt.

3626 

3627### Example

3628 

3629```http

3630curl https://api.openai.com/v1/chat/completions/$COMPLETION_ID \

3631 -H "Authorization: Bearer $OPENAI_API_KEY"

3632```

3633 

3634#### Response

3097 3635 

3098```json3636```json

3099{3637{

3181 "created": 0,3719 "created": 0,

3182 "model": "model",3720 "model": "model",

3183 "object": "chat.completion",3721 "object": "chat.completion",

3722 "moderation": {

3723 "input": {

3724 "model": "model",

3725 "results": [

3726 {

3727 "categories": {

3728 "foo": true

3729 },

3730 "category_applied_input_types": {

3731 "foo": [

3732 "text"

3733 ]

3734 },

3735 "category_scores": {

3736 "foo": 0

3737 },

3738 "flagged": true,

3739 "model": "model",

3740 "type": "moderation_result"

3741 }

3742 ],

3743 "type": "moderation_results"

3744 },

3745 "output": {

3746 "model": "model",

3747 "results": [

3748 {

3749 "categories": {

3750 "foo": true

3751 },

3752 "category_applied_input_types": {

3753 "foo": [

3754 "text"

3755 ]

3756 },

3757 "category_scores": {

3758 "foo": 0

3759 },

3760 "flagged": true,

3761 "model": "model",

3762 "type": "moderation_result"

3763 }

3764 ],

3765 "type": "moderation_results"

3766 }

3767 },

3184 "service_tier": "auto",3768 "service_tier": "auto",

3185 "system_fingerprint": "system_fingerprint",3769 "system_fingerprint": "system_fingerprint",

3186 "usage": {3770 "usage": {

3276 3860 

3277### Returns3861### Returns

3278 3862 

3279- `ChatCompletion object { id, choices, created, 5 more }`3863- `ChatCompletion object { id, choices, created, 6 more }`

3280 3864 

3281 Represents a chat completion response returned by model, based on the provided input.3865 Represents a chat completion response returned by model, based on the provided input.

3282 3866 

3294 `length` if the maximum number of tokens specified in the request was reached,3878 `length` if the maximum number of tokens specified in the request was reached,

3295 `content_filter` if content was omitted due to a flag from our content filters,3879 `content_filter` if content was omitted due to a flag from our content filters,

3296 `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function.3880 `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function.

3881 Read the [Model Spec](https://model-spec.openai.com/2025-12-18.html) for more.

3297 3882 

3298 - `"stop"`3883 - `"stop"`

3299 3884 

3520 4105 

3521 - `"chat.completion"`4106 - `"chat.completion"`

3522 4107 

4108 - `moderation: optional object { input, output }`

4109 

4110 Moderation results for the request input and generated output, if moderated

4111 completions were requested.

4112 

4113 - `input: object { model, results, type } or object { code, message, type }`

4114 

4115 Moderation for the request input.

4116 

4117 - `ModerationResults object { model, results, type }`

4118 

4119 Successful moderation results for the request input or generated output.

4120 

4121 - `model: string`

4122 

4123 The moderation model used to generate the results.

4124 

4125 - `results: array of object { categories, category_applied_input_types, category_scores, 3 more }`

4126 

4127 A list of moderation results.

4128 

4129 - `categories: map[boolean]`

4130 

4131 A dictionary of moderation categories to booleans, True if the input is flagged under this category.

4132 

4133 - `category_applied_input_types: map[array of "text" or "image"]`

4134 

4135 Which modalities of input are reflected by the score for each category.

4136 

4137 - `"text"`

4138 

4139 - `"image"`

4140 

4141 - `category_scores: map[number]`

4142 

4143 A dictionary of moderation categories to scores.

4144 

4145 - `flagged: boolean`

4146 

4147 A boolean indicating whether the content was flagged by any category.

4148 

4149 - `model: string`

4150 

4151 The moderation model that produced this result.

4152 

4153 - `type: "moderation_result"`

4154 

4155 The object type, which was always `moderation_result` for successful moderation results.

4156 

4157 - `"moderation_result"`

4158 

4159 - `type: "moderation_results"`

4160 

4161 The object type, which is always `moderation_results`.

4162 

4163 - `"moderation_results"`

4164 

4165 - `Error object { code, message, type }`

4166 

4167 An error produced while attempting moderation.

4168 

4169 - `code: string`

4170 

4171 The error code.

4172 

4173 - `message: string`

4174 

4175 The error message.

4176 

4177 - `type: "error"`

4178 

4179 The object type, which is always `error`.

4180 

4181 - `"error"`

4182 

4183 - `output: object { model, results, type } or object { code, message, type }`

4184 

4185 Moderation for the generated output.

4186 

4187 - `ModerationResults object { model, results, type }`

4188 

4189 Successful moderation results for the request input or generated output.

4190 

4191 - `model: string`

4192 

4193 The moderation model used to generate the results.

4194 

4195 - `results: array of object { categories, category_applied_input_types, category_scores, 3 more }`

4196 

4197 A list of moderation results.

4198 

4199 - `categories: map[boolean]`

4200 

4201 A dictionary of moderation categories to booleans, True if the input is flagged under this category.

4202 

4203 - `category_applied_input_types: map[array of "text" or "image"]`

4204 

4205 Which modalities of input are reflected by the score for each category.

4206 

4207 - `"text"`

4208 

4209 - `"image"`

4210 

4211 - `category_scores: map[number]`

4212 

4213 A dictionary of moderation categories to scores.

4214 

4215 - `flagged: boolean`

4216 

4217 A boolean indicating whether the content was flagged by any category.

4218 

4219 - `model: string`

4220 

4221 The moderation model that produced this result.

4222 

4223 - `type: "moderation_result"`

4224 

4225 The object type, which was always `moderation_result` for successful moderation results.

4226 

4227 - `"moderation_result"`

4228 

4229 - `type: "moderation_results"`

4230 

4231 The object type, which is always `moderation_results`.

4232 

4233 - `"moderation_results"`

4234 

4235 - `Error object { code, message, type }`

4236 

4237 An error produced while attempting moderation.

4238 

4239 - `code: string`

4240 

4241 The error code.

4242 

4243 - `message: string`

4244 

4245 The error message.

4246 

4247 - `type: "error"`

4248 

4249 The object type, which is always `error`.

4250 

4251 - `"error"`

4252 

3523 - `service_tier: optional "auto" or "default" or "flex" or 2 more`4253 - `service_tier: optional "auto" or "default" or "flex" or 2 more`

3524 4254 

3525 Specifies the processing type used for serving the request.4255 Specifies the processing type used for serving the request.

3701 "created": 0,4431 "created": 0,

3702 "model": "model",4432 "model": "model",

3703 "object": "chat.completion",4433 "object": "chat.completion",

4434 "moderation": {

4435 "input": {

4436 "model": "model",

4437 "results": [

4438 {

4439 "categories": {

4440 "foo": true

4441 },

4442 "category_applied_input_types": {

4443 "foo": [

4444 "text"

4445 ]

4446 },

4447 "category_scores": {

4448 "foo": 0

4449 },

4450 "flagged": true,

4451 "model": "model",

4452 "type": "moderation_result"

4453 }

4454 ],

4455 "type": "moderation_results"

4456 },

4457 "output": {

4458 "model": "model",

4459 "results": [

4460 {

4461 "categories": {

4462 "foo": true

4463 },

4464 "category_applied_input_types": {

4465 "foo": [

4466 "text"

4467 ]

4468 },

4469 "category_scores": {

4470 "foo": 0

4471 },

4472 "flagged": true,

4473 "model": "model",

4474 "type": "moderation_result"

4475 }

4476 ],

4477 "type": "moderation_results"

4478 }

4479 },

3704 "service_tier": "auto",4480 "service_tier": "auto",

3705 "system_fingerprint": "system_fingerprint",4481 "system_fingerprint": "system_fingerprint",

3706 "usage": {4482 "usage": {

3843 4619 

3844### Chat Completion4620### Chat Completion

3845 4621 

3846- `ChatCompletion object { id, choices, created, 5 more }`4622- `ChatCompletion object { id, choices, created, 6 more }`

3847 4623 

3848 Represents a chat completion response returned by model, based on the provided input.4624 Represents a chat completion response returned by model, based on the provided input.

3849 4625 

3861 `length` if the maximum number of tokens specified in the request was reached,4637 `length` if the maximum number of tokens specified in the request was reached,

3862 `content_filter` if content was omitted due to a flag from our content filters,4638 `content_filter` if content was omitted due to a flag from our content filters,

3863 `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function.4639 `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function.

4640 Read the [Model Spec](https://model-spec.openai.com/2025-12-18.html) for more.

3864 4641 

3865 - `"stop"`4642 - `"stop"`

3866 4643 

4087 4864 

4088 - `"chat.completion"`4865 - `"chat.completion"`

4089 4866 

4867 - `moderation: optional object { input, output }`

4868 

4869 Moderation results for the request input and generated output, if moderated

4870 completions were requested.

4871 

4872 - `input: object { model, results, type } or object { code, message, type }`

4873 

4874 Moderation for the request input.

4875 

4876 - `ModerationResults object { model, results, type }`

4877 

4878 Successful moderation results for the request input or generated output.

4879 

4880 - `model: string`

4881 

4882 The moderation model used to generate the results.

4883 

4884 - `results: array of object { categories, category_applied_input_types, category_scores, 3 more }`

4885 

4886 A list of moderation results.

4887 

4888 - `categories: map[boolean]`

4889 

4890 A dictionary of moderation categories to booleans, True if the input is flagged under this category.

4891 

4892 - `category_applied_input_types: map[array of "text" or "image"]`

4893 

4894 Which modalities of input are reflected by the score for each category.

4895 

4896 - `"text"`

4897 

4898 - `"image"`

4899 

4900 - `category_scores: map[number]`

4901 

4902 A dictionary of moderation categories to scores.

4903 

4904 - `flagged: boolean`

4905 

4906 A boolean indicating whether the content was flagged by any category.

4907 

4908 - `model: string`

4909 

4910 The moderation model that produced this result.

4911 

4912 - `type: "moderation_result"`

4913 

4914 The object type, which was always `moderation_result` for successful moderation results.

4915 

4916 - `"moderation_result"`

4917 

4918 - `type: "moderation_results"`

4919 

4920 The object type, which is always `moderation_results`.

4921 

4922 - `"moderation_results"`

4923 

4924 - `Error object { code, message, type }`

4925 

4926 An error produced while attempting moderation.

4927 

4928 - `code: string`

4929 

4930 The error code.

4931 

4932 - `message: string`

4933 

4934 The error message.

4935 

4936 - `type: "error"`

4937 

4938 The object type, which is always `error`.

4939 

4940 - `"error"`

4941 

4942 - `output: object { model, results, type } or object { code, message, type }`

4943 

4944 Moderation for the generated output.

4945 

4946 - `ModerationResults object { model, results, type }`

4947 

4948 Successful moderation results for the request input or generated output.

4949 

4950 - `model: string`

4951 

4952 The moderation model used to generate the results.

4953 

4954 - `results: array of object { categories, category_applied_input_types, category_scores, 3 more }`

4955 

4956 A list of moderation results.

4957 

4958 - `categories: map[boolean]`

4959 

4960 A dictionary of moderation categories to booleans, True if the input is flagged under this category.

4961 

4962 - `category_applied_input_types: map[array of "text" or "image"]`

4963 

4964 Which modalities of input are reflected by the score for each category.

4965 

4966 - `"text"`

4967 

4968 - `"image"`

4969 

4970 - `category_scores: map[number]`

4971 

4972 A dictionary of moderation categories to scores.

4973 

4974 - `flagged: boolean`

4975 

4976 A boolean indicating whether the content was flagged by any category.

4977 

4978 - `model: string`

4979 

4980 The moderation model that produced this result.

4981 

4982 - `type: "moderation_result"`

4983 

4984 The object type, which was always `moderation_result` for successful moderation results.

4985 

4986 - `"moderation_result"`

4987 

4988 - `type: "moderation_results"`

4989 

4990 The object type, which is always `moderation_results`.

4991 

4992 - `"moderation_results"`

4993 

4994 - `Error object { code, message, type }`

4995 

4996 An error produced while attempting moderation.

4997 

4998 - `code: string`

4999 

5000 The error code.

5001 

5002 - `message: string`

5003 

5004 The error message.

5005 

5006 - `type: "error"`

5007 

5008 The object type, which is always `error`.

5009 

5010 - `"error"`

5011 

4090 - `service_tier: optional "auto" or "default" or "flex" or 2 more`5012 - `service_tier: optional "auto" or "default" or "flex" or 2 more`

4091 5013 

4092 Specifies the processing type used for serving the request.5014 Specifies the processing type used for serving the request.

4435 5357 

4436### Chat Completion Chunk5358### Chat Completion Chunk

4437 5359 

4438- `ChatCompletionChunk object { id, choices, created, 5 more }`5360- `ChatCompletionChunk object { id, choices, created, 6 more }`

4439 5361 

4440 Represents a streamed chunk of a chat completion response returned5362 Represents a streamed chunk of a chat completion response returned

4441 by the model, based on the provided input.5363 by the model, based on the provided input.

4603 5525 

4604 - `"chat.completion.chunk"`5526 - `"chat.completion.chunk"`

4605 5527 

5528 - `moderation: optional object { input, output }`

5529 

5530 Moderation results for the request input and generated output. Present

5531 on the moderation chunk when moderated completions are requested.

5532 

5533 - `input: object { model, results, type } or object { code, message, type }`

5534 

5535 Moderation for the request input.

5536 

5537 - `ModerationResults object { model, results, type }`

5538 

5539 Successful moderation results for the request input or generated output.

5540 

5541 - `model: string`

5542 

5543 The moderation model used to generate the results.

5544 

5545 - `results: array of object { categories, category_applied_input_types, category_scores, 3 more }`

5546 

5547 A list of moderation results.

5548 

5549 - `categories: map[boolean]`

5550 

5551 A dictionary of moderation categories to booleans, True if the input is flagged under this category.

5552 

5553 - `category_applied_input_types: map[array of "text" or "image"]`

5554 

5555 Which modalities of input are reflected by the score for each category.

5556 

5557 - `"text"`

5558 

5559 - `"image"`

5560 

5561 - `category_scores: map[number]`

5562 

5563 A dictionary of moderation categories to scores.

5564 

5565 - `flagged: boolean`

5566 

5567 A boolean indicating whether the content was flagged by any category.

5568 

5569 - `model: string`

5570 

5571 The moderation model that produced this result.

5572 

5573 - `type: "moderation_result"`

5574 

5575 The object type, which was always `moderation_result` for successful moderation results.

5576 

5577 - `"moderation_result"`

5578 

5579 - `type: "moderation_results"`

5580 

5581 The object type, which is always `moderation_results`.

5582 

5583 - `"moderation_results"`

5584 

5585 - `Error object { code, message, type }`

5586 

5587 An error produced while attempting moderation.

5588 

5589 - `code: string`

5590 

5591 The error code.

5592 

5593 - `message: string`

5594 

5595 The error message.

5596 

5597 - `type: "error"`

5598 

5599 The object type, which is always `error`.

5600 

5601 - `"error"`

5602 

5603 - `output: object { model, results, type } or object { code, message, type }`

5604 

5605 Moderation for the generated output.

5606 

5607 - `ModerationResults object { model, results, type }`

5608 

5609 Successful moderation results for the request input or generated output.

5610 

5611 - `model: string`

5612 

5613 The moderation model used to generate the results.

5614 

5615 - `results: array of object { categories, category_applied_input_types, category_scores, 3 more }`

5616 

5617 A list of moderation results.

5618 

5619 - `categories: map[boolean]`

5620 

5621 A dictionary of moderation categories to booleans, True if the input is flagged under this category.

5622 

5623 - `category_applied_input_types: map[array of "text" or "image"]`

5624 

5625 Which modalities of input are reflected by the score for each category.

5626 

5627 - `"text"`

5628 

5629 - `"image"`

5630 

5631 - `category_scores: map[number]`

5632 

5633 A dictionary of moderation categories to scores.

5634 

5635 - `flagged: boolean`

5636 

5637 A boolean indicating whether the content was flagged by any category.

5638 

5639 - `model: string`

5640 

5641 The moderation model that produced this result.

5642 

5643 - `type: "moderation_result"`

5644 

5645 The object type, which was always `moderation_result` for successful moderation results.

5646 

5647 - `"moderation_result"`

5648 

5649 - `type: "moderation_results"`

5650 

5651 The object type, which is always `moderation_results`.

5652 

5653 - `"moderation_results"`

5654 

5655 - `Error object { code, message, type }`

5656 

5657 An error produced while attempting moderation.

5658 

5659 - `code: string`

5660 

5661 The error code.

5662 

5663 - `message: string`

5664 

5665 The error message.

5666 

5667 - `type: "error"`

5668 

5669 The object type, which is always `error`.

5670 

5671 - `"error"`

5672 

4606 - `service_tier: optional "auto" or "default" or "flex" or 2 more`5673 - `service_tier: optional "auto" or "default" or "flex" or 2 more`

4607 5674 

4608 Specifies the processing type used for serving the request.5675 Specifies the processing type used for serving the request.

11 11 

12### Returns12### Returns

13 13 

14- `ChatCompletion object { id, choices, created, 5 more }`14- `ChatCompletion object { id, choices, created, 6 more }`

15 15 

16 Represents a chat completion response returned by model, based on the provided input.16 Represents a chat completion response returned by model, based on the provided input.

17 17 

29 `length` if the maximum number of tokens specified in the request was reached,29 `length` if the maximum number of tokens specified in the request was reached,

30 `content_filter` if content was omitted due to a flag from our content filters,30 `content_filter` if content was omitted due to a flag from our content filters,

31 `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function.31 `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function.

32 Read the [Model Spec](https://model-spec.openai.com/2025-12-18.html) for more.

32 33 

33 - `"stop"`34 - `"stop"`

34 35 

255 256 

256 - `"chat.completion"`257 - `"chat.completion"`

257 258 

259 - `moderation: optional object { input, output }`

260 

261 Moderation results for the request input and generated output, if moderated

262 completions were requested.

263 

264 - `input: object { model, results, type } or object { code, message, type }`

265 

266 Moderation for the request input.

267 

268 - `ModerationResults object { model, results, type }`

269 

270 Successful moderation results for the request input or generated output.

271 

272 - `model: string`

273 

274 The moderation model used to generate the results.

275 

276 - `results: array of object { categories, category_applied_input_types, category_scores, 3 more }`

277 

278 A list of moderation results.

279 

280 - `categories: map[boolean]`

281 

282 A dictionary of moderation categories to booleans, True if the input is flagged under this category.

283 

284 - `category_applied_input_types: map[array of "text" or "image"]`

285 

286 Which modalities of input are reflected by the score for each category.

287 

288 - `"text"`

289 

290 - `"image"`

291 

292 - `category_scores: map[number]`

293 

294 A dictionary of moderation categories to scores.

295 

296 - `flagged: boolean`

297 

298 A boolean indicating whether the content was flagged by any category.

299 

300 - `model: string`

301 

302 The moderation model that produced this result.

303 

304 - `type: "moderation_result"`

305 

306 The object type, which was always `moderation_result` for successful moderation results.

307 

308 - `"moderation_result"`

309 

310 - `type: "moderation_results"`

311 

312 The object type, which is always `moderation_results`.

313 

314 - `"moderation_results"`

315 

316 - `Error object { code, message, type }`

317 

318 An error produced while attempting moderation.

319 

320 - `code: string`

321 

322 The error code.

323 

324 - `message: string`

325 

326 The error message.

327 

328 - `type: "error"`

329 

330 The object type, which is always `error`.

331 

332 - `"error"`

333 

334 - `output: object { model, results, type } or object { code, message, type }`

335 

336 Moderation for the generated output.

337 

338 - `ModerationResults object { model, results, type }`

339 

340 Successful moderation results for the request input or generated output.

341 

342 - `model: string`

343 

344 The moderation model used to generate the results.

345 

346 - `results: array of object { categories, category_applied_input_types, category_scores, 3 more }`

347 

348 A list of moderation results.

349 

350 - `categories: map[boolean]`

351 

352 A dictionary of moderation categories to booleans, True if the input is flagged under this category.

353 

354 - `category_applied_input_types: map[array of "text" or "image"]`

355 

356 Which modalities of input are reflected by the score for each category.

357 

358 - `"text"`

359 

360 - `"image"`

361 

362 - `category_scores: map[number]`

363 

364 A dictionary of moderation categories to scores.

365 

366 - `flagged: boolean`

367 

368 A boolean indicating whether the content was flagged by any category.

369 

370 - `model: string`

371 

372 The moderation model that produced this result.

373 

374 - `type: "moderation_result"`

375 

376 The object type, which was always `moderation_result` for successful moderation results.

377 

378 - `"moderation_result"`

379 

380 - `type: "moderation_results"`

381 

382 The object type, which is always `moderation_results`.

383 

384 - `"moderation_results"`

385 

386 - `Error object { code, message, type }`

387 

388 An error produced while attempting moderation.

389 

390 - `code: string`

391 

392 The error code.

393 

394 - `message: string`

395 

396 The error message.

397 

398 - `type: "error"`

399 

400 The object type, which is always `error`.

401 

402 - `"error"`

403 

258 - `service_tier: optional "auto" or "default" or "flex" or 2 more`404 - `service_tier: optional "auto" or "default" or "flex" or 2 more`

259 405 

260 Specifies the processing type used for serving the request.406 Specifies the processing type used for serving the request.

430 "created": 0,576 "created": 0,

431 "model": "model",577 "model": "model",

432 "object": "chat.completion",578 "object": "chat.completion",

579 "moderation": {

580 "input": {

581 "model": "model",

582 "results": [

583 {

584 "categories": {

585 "foo": true

586 },

587 "category_applied_input_types": {

588 "foo": [

589 "text"

590 ]

591 },

592 "category_scores": {

593 "foo": 0

594 },

595 "flagged": true,

596 "model": "model",

597 "type": "moderation_result"

598 }

599 ],

600 "type": "moderation_results"

601 },

602 "output": {

603 "model": "model",

604 "results": [

605 {

606 "categories": {

607 "foo": true

608 },

609 "category_applied_input_types": {

610 "foo": [

611 "text"

612 ]

613 },

614 "category_scores": {

615 "foo": 0

616 },

617 "flagged": true,

618 "model": "model",

619 "type": "moderation_result"

620 }

621 ],

622 "type": "moderation_results"

623 }

624 },

433 "service_tier": "auto",625 "service_tier": "auto",

434 "system_fingerprint": "system_fingerprint",626 "system_fingerprint": "system_fingerprint",

435 "usage": {627 "usage": {

3878 3878 

3879 - `"gpt-5.1-codex-max"`3879 - `"gpt-5.1-codex-max"`

3880 3880 

3881- `moderation: optional object { model }`

3882 

3883 Configuration for running moderation on the input and output of this response.

3884 

3885 - `model: string`

3886 

3887 The moderation model to use for moderated completions, e.g. 'omni-moderation-latest'.

3888 

3881- `parallel_tool_calls: optional boolean`3889- `parallel_tool_calls: optional boolean`

3882 3890 

3883 Whether to allow the model to run tool calls in parallel.3891 Whether to allow the model to run tool calls in parallel.

5091 5099 

5092### Returns5100### Returns

5093 5101 

5094- `Response object { id, created_at, error, 30 more }`5102- `Response object { id, created_at, error, 31 more }`

5095 5103 

5096 - `id: string`5104 - `id: string`

5097 5105 

12616 12624 

12617 The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.12625 The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.

12618 12626 

12627 - `moderation: optional object { input, output }`

12628 

12629 Moderation results for the response input and output, if moderated completions were requested.

12630 

12631 - `input: object { categories, category_applied_input_types, category_scores, 3 more } or object { code, message, type }`

12632 

12633 Moderation for the response input.

12634 

12635 - `ModerationResult object { categories, category_applied_input_types, category_scores, 3 more }`

12636 

12637 A moderation result produced for the response input or output.

12638 

12639 - `categories: map[boolean]`

12640 

12641 A dictionary of moderation categories to booleans, True if the input is flagged under this category.

12642 

12643 - `category_applied_input_types: map[array of "text" or "image"]`

12644 

12645 Which modalities of input are reflected by the score for each category.

12646 

12647 - `"text"`

12648 

12649 - `"image"`

12650 

12651 - `category_scores: map[number]`

12652 

12653 A dictionary of moderation categories to scores.

12654 

12655 - `flagged: boolean`

12656 

12657 A boolean indicating whether the content was flagged by any category.

12658 

12659 - `model: string`

12660 

12661 The moderation model that produced this result.

12662 

12663 - `type: "moderation_result"`

12664 

12665 The object type, which was always `moderation_result` for successful moderation results.

12666 

12667 - `"moderation_result"`

12668 

12669 - `Error object { code, message, type }`

12670 

12671 An error produced while attempting moderation for the response input or output.

12672 

12673 - `code: string`

12674 

12675 The error code.

12676 

12677 - `message: string`

12678 

12679 The error message.

12680 

12681 - `type: "error"`

12682 

12683 The object type, which was always `error` for moderation failures.

12684 

12685 - `"error"`

12686 

12687 - `output: object { categories, category_applied_input_types, category_scores, 3 more } or object { code, message, type }`

12688 

12689 Moderation for the response output.

12690 

12691 - `ModerationResult object { categories, category_applied_input_types, category_scores, 3 more }`

12692 

12693 A moderation result produced for the response input or output.

12694 

12695 - `categories: map[boolean]`

12696 

12697 A dictionary of moderation categories to booleans, True if the input is flagged under this category.

12698 

12699 - `category_applied_input_types: map[array of "text" or "image"]`

12700 

12701 Which modalities of input are reflected by the score for each category.

12702 

12703 - `"text"`

12704 

12705 - `"image"`

12706 

12707 - `category_scores: map[number]`

12708 

12709 A dictionary of moderation categories to scores.

12710 

12711 - `flagged: boolean`

12712 

12713 A boolean indicating whether the content was flagged by any category.

12714 

12715 - `model: string`

12716 

12717 The moderation model that produced this result.

12718 

12719 - `type: "moderation_result"`

12720 

12721 The object type, which was always `moderation_result` for successful moderation results.

12722 

12723 - `"moderation_result"`

12724 

12725 - `Error object { code, message, type }`

12726 

12727 An error produced while attempting moderation for the response input or output.

12728 

12729 - `code: string`

12730 

12731 The error code.

12732 

12733 - `message: string`

12734 

12735 The error message.

12736 

12737 - `type: "error"`

12738 

12739 The object type, which was always `error` for moderation failures.

12740 

12741 - `"error"`

12742 

12619 - `output_text: optional string`12743 - `output_text: optional string`

12620 12744 

12621 SDK-only convenience property that contains the aggregated text output12745 SDK-only convenience property that contains the aggregated text output

13035 },13159 },

13036 "max_output_tokens": 0,13160 "max_output_tokens": 0,

13037 "max_tool_calls": 0,13161 "max_tool_calls": 0,

13162 "moderation": {

13163 "input": {

13164 "categories": {

13165 "foo": true

13166 },

13167 "category_applied_input_types": {

13168 "foo": [

13169 "text"

13170 ]

13171 },

13172 "category_scores": {

13173 "foo": 0

13174 },

13175 "flagged": true,

13176 "model": "model",

13177 "type": "moderation_result"

13178 },

13179 "output": {

13180 "categories": {

13181 "foo": true

13182 },

13183 "category_applied_input_types": {

13184 "foo": [

13185 "text"

13186 ]

13187 },

13188 "category_scores": {

13189 "foo": 0

13190 },

13191 "flagged": true,

13192 "model": "model",

13193 "type": "moderation_result"

13194 }

13195 },

13038 "output_text": "output_text",13196 "output_text": "output_text",

13039 "previous_response_id": "previous_response_id",13197 "previous_response_id": "previous_response_id",

13040 "prompt": {13198 "prompt": {

13888 14046 

13889### Returns14047### Returns

13890 14048 

13891- `Response object { id, created_at, error, 30 more }`14049- `Response object { id, created_at, error, 31 more }`