Moderations

Create moderation

client.Moderations.New(ctx, body) (*ModerationNewResponse, error)

post /moderations

Classifies if text and/or image inputs are potentially harmful. Learn more in the moderation guide.

Parameters

body ModerationNewParams
- Input param.Field[ModerationNewParamsInputUnion]
  
  Input (or inputs) to classify. Can be a single string, an array of strings, or an array of multi-modal input objects similar to other models.
  - string
  - type ModerationNewParamsInputArray []string
    
    An array of strings to classify for moderation.
  - type ModerationNewParamsInputModerationMultiModalArray []ModerationMultiModalInputUnion
    
    An array of multi-modal inputs to the moderation model.
    - type ModerationImageURLInput struct{…}
      
      An object describing an image to classify.
      - ImageURL ModerationImageURLInputImageURL
        
        Contains either an image URL or a data URL for a base64 encoded image.
        
        URL string
        
        Either a URL of the image or the base64 encoded image data.
      - Type ImageURL
        
        Always image_url.
        
        const ImageURLImageURL ImageURL = "image_url"
    - type ModerationTextInput struct{…}
      
      An object describing text to classify.
      - Text string
        
        A string of text to classify.
      - Type Text
        
        Always text.
        
        const TextText Text = "text"
- Model param.Field[ModerationModel]
  
  The content moderation model you would like to use. Learn more in the moderation guide, and learn about available models here.
  - string
  - type ModerationModel string
    - const ModerationModelOmniModerationLatest ModerationModel = "omni-moderation-latest"
    - const ModerationModelOmniModeration2024_09_26 ModerationModel = "omni-moderation-2024-09-26"
    - const ModerationModelTextModerationLatest ModerationModel = "text-moderation-latest"
    - const ModerationModelTextModerationStable ModerationModel = "text-moderation-stable"

Returns

type ModerationNewResponse struct{…}

Represents if a given text input is potentially harmful.
- ID string
  
  The unique identifier for the moderation request.
- Model string
  
  The model used to generate the moderation results.
- Results []Moderation
  
  A list of moderation objects.
  - Categories ModerationCategories
    
    A list of the categories, and whether they are flagged or not.
    - Harassment bool
      
      Content that expresses, incites, or promotes harassing language towards any target.
    - HarassmentThreatening bool
      
      Harassment content that also includes violence or serious harm towards any target.
    - Hate bool
      
      Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. Hateful content aimed at non-protected groups (e.g., chess players) is harassment.
    - HateThreatening bool
      
      Hateful content that also includes violence or serious harm towards the targeted group based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste.
    - Illicit bool
      
      Content that includes instructions or advice that facilitate the planning or execution of wrongdoing, or that gives advice or instruction on how to commit illicit acts. For example, "how to shoplift" would fit this category.
    - IllicitViolent bool
      
      Content that includes instructions or advice that facilitate the planning or execution of wrongdoing that also includes violence, or that gives advice or instruction on the procurement of any weapon.
    - SelfHarm bool
      
      Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.
    - SelfHarmInstructions bool
      
      Content that encourages performing acts of self-harm, such as suicide, cutting, and eating disorders, or that gives instructions or advice on how to commit such acts.
    - SelfHarmIntent bool
      
      Content where the speaker expresses that they are engaging or intend to engage in acts of self-harm, such as suicide, cutting, and eating disorders.
    - Sexual bool
      
      Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness).
    - SexualMinors bool
      
      Sexual content that includes an individual who is under 18 years old.
    - Violence bool
      
      Content that depicts death, violence, or physical injury.
    - ViolenceGraphic bool
      
      Content that depicts death, violence, or physical injury in graphic detail.
  - CategoryAppliedInputTypes ModerationCategoryAppliedInputTypes
    
    A list of the categories along with the input type(s) that the score applies to.
    - Harassment []string
      
      The applied input type(s) for the category 'harassment'.
      - const ModerationCategoryAppliedInputTypesHarassmentText ModerationCategoryAppliedInputTypesHarassment = "text"
    - HarassmentThreatening []string
      
      The applied input type(s) for the category 'harassment/threatening'.
      - const ModerationCategoryAppliedInputTypesHarassmentThreateningText ModerationCategoryAppliedInputTypesHarassmentThreatening = "text"
    - Hate []string
      
      The applied input type(s) for the category 'hate'.
      - const ModerationCategoryAppliedInputTypesHateText ModerationCategoryAppliedInputTypesHate = "text"
    - HateThreatening []string
      
      The applied input type(s) for the category 'hate/threatening'.
      - const ModerationCategoryAppliedInputTypesHateThreateningText ModerationCategoryAppliedInputTypesHateThreatening = "text"
    - Illicit []string
      
      The applied input type(s) for the category 'illicit'.
      - const ModerationCategoryAppliedInputTypesIllicitText ModerationCategoryAppliedInputTypesIllicit = "text"
    - IllicitViolent []string
      
      The applied input type(s) for the category 'illicit/violent'.
      - const ModerationCategoryAppliedInputTypesIllicitViolentText ModerationCategoryAppliedInputTypesIllicitViolent = "text"
    - SelfHarm []string
      
      The applied input type(s) for the category 'self-harm'.
      - const ModerationCategoryAppliedInputTypesSelfHarmText ModerationCategoryAppliedInputTypesSelfHarm = "text"
      - const ModerationCategoryAppliedInputTypesSelfHarmImage ModerationCategoryAppliedInputTypesSelfHarm = "image"
    - SelfHarmInstructions []string
      
      The applied input type(s) for the category 'self-harm/instructions'.
      - const ModerationCategoryAppliedInputTypesSelfHarmInstructionText ModerationCategoryAppliedInputTypesSelfHarmInstruction = "text"
      - const ModerationCategoryAppliedInputTypesSelfHarmInstructionImage ModerationCategoryAppliedInputTypesSelfHarmInstruction = "image"
    - SelfHarmIntent []string
      
      The applied input type(s) for the category 'self-harm/intent'.
      - const ModerationCategoryAppliedInputTypesSelfHarmIntentText ModerationCategoryAppliedInputTypesSelfHarmIntent = "text"
      - const ModerationCategoryAppliedInputTypesSelfHarmIntentImage ModerationCategoryAppliedInputTypesSelfHarmIntent = "image"
    - Sexual []string
      
      The applied input type(s) for the category 'sexual'.
      - const ModerationCategoryAppliedInputTypesSexualText ModerationCategoryAppliedInputTypesSexual = "text"
      - const ModerationCategoryAppliedInputTypesSexualImage ModerationCategoryAppliedInputTypesSexual = "image"
    - SexualMinors []string
      
      The applied input type(s) for the category 'sexual/minors'.
      - const ModerationCategoryAppliedInputTypesSexualMinorText ModerationCategoryAppliedInputTypesSexualMinor = "text"
    - Violence []string
      
      The applied input type(s) for the category 'violence'.
      - const ModerationCategoryAppliedInputTypesViolenceText ModerationCategoryAppliedInputTypesViolence = "text"
      - const ModerationCategoryAppliedInputTypesViolenceImage ModerationCategoryAppliedInputTypesViolence = "image"
    - ViolenceGraphic []string
      
      The applied input type(s) for the category 'violence/graphic'.
      - const ModerationCategoryAppliedInputTypesViolenceGraphicText ModerationCategoryAppliedInputTypesViolenceGraphic = "text"
      - const ModerationCategoryAppliedInputTypesViolenceGraphicImage ModerationCategoryAppliedInputTypesViolenceGraphic = "image"
  - CategoryScores ModerationCategoryScores
    
    A list of the categories along with their scores as predicted by model.
    - Harassment float64
      
      The score for the category 'harassment'.
    - HarassmentThreatening float64
      
      The score for the category 'harassment/threatening'.
    - Hate float64
      
      The score for the category 'hate'.
    - HateThreatening float64
      
      The score for the category 'hate/threatening'.
    - Illicit float64
      
      The score for the category 'illicit'.
    - IllicitViolent float64
      
      The score for the category 'illicit/violent'.
    - SelfHarm float64
      
      The score for the category 'self-harm'.
    - SelfHarmInstructions float64
      
      The score for the category 'self-harm/instructions'.
    - SelfHarmIntent float64
      
      The score for the category 'self-harm/intent'.
    - Sexual float64
      
      The score for the category 'sexual'.
    - SexualMinors float64
      
      The score for the category 'sexual/minors'.
    - Violence float64
      
      The score for the category 'violence'.
    - ViolenceGraphic float64
      
      The score for the category 'violence/graphic'.
  - Flagged bool
    
    Whether any of the below categories are flagged.

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  moderation, err := client.Moderations.New(context.TODO(), openai.ModerationNewParams{
    Input: openai.ModerationNewParamsInputUnion{
      OfString: openai.String("I want to kill them."),
    },
  })
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", moderation.ID)
}

Response

{
  "id": "id",
  "model": "model",
  "results": [
    {
      "categories": {
        "harassment": true,
        "harassment/threatening": true,
        "hate": true,
        "hate/threatening": true,
        "illicit": true,
        "illicit/violent": true,
        "self-harm": true,
        "self-harm/instructions": true,
        "self-harm/intent": true,
        "sexual": true,
        "sexual/minors": true,
        "violence": true,
        "violence/graphic": true
      },
      "category_applied_input_types": {
        "harassment": [
          "text"
        ],
        "harassment/threatening": [
          "text"
        ],
        "hate": [
          "text"
        ],
        "hate/threatening": [
          "text"
        ],
        "illicit": [
          "text"
        ],
        "illicit/violent": [
          "text"
        ],
        "self-harm": [
          "text"
        ],
        "self-harm/instructions": [
          "text"
        ],
        "self-harm/intent": [
          "text"
        ],
        "sexual": [
          "text"
        ],
        "sexual/minors": [
          "text"
        ],
        "violence": [
          "text"
        ],
        "violence/graphic": [
          "text"
        ]
      },
      "category_scores": {
        "harassment": 0,
        "harassment/threatening": 0,
        "hate": 0,
        "hate/threatening": 0,
        "illicit": 0,
        "illicit/violent": 0,
        "self-harm": 0,
        "self-harm/instructions": 0,
        "self-harm/intent": 0,
        "sexual": 0,
        "sexual/minors": 0,
        "violence": 0,
        "violence/graphic": 0
      },
      "flagged": true
    }
  ]
}

Domain Types

Moderation

type Moderation struct{…}
- Categories ModerationCategories
  
  A list of the categories, and whether they are flagged or not.
  - Harassment bool
    
    Content that expresses, incites, or promotes harassing language towards any target.
  - HarassmentThreatening bool
    
    Harassment content that also includes violence or serious harm towards any target.
  - Hate bool
    
    Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. Hateful content aimed at non-protected groups (e.g., chess players) is harassment.
  - HateThreatening bool
    
    Hateful content that also includes violence or serious harm towards the targeted group based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste.
  - Illicit bool
    
    Content that includes instructions or advice that facilitate the planning or execution of wrongdoing, or that gives advice or instruction on how to commit illicit acts. For example, "how to shoplift" would fit this category.
  - IllicitViolent bool
    
    Content that includes instructions or advice that facilitate the planning or execution of wrongdoing that also includes violence, or that gives advice or instruction on the procurement of any weapon.
  - SelfHarm bool
    
    Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.
  - SelfHarmInstructions bool
    
    Content that encourages performing acts of self-harm, such as suicide, cutting, and eating disorders, or that gives instructions or advice on how to commit such acts.
  - SelfHarmIntent bool
    
    Content where the speaker expresses that they are engaging or intend to engage in acts of self-harm, such as suicide, cutting, and eating disorders.
  - Sexual bool
    
    Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness).
  - SexualMinors bool
    
    Sexual content that includes an individual who is under 18 years old.
  - Violence bool
    
    Content that depicts death, violence, or physical injury.
  - ViolenceGraphic bool
    
    Content that depicts death, violence, or physical injury in graphic detail.
- CategoryAppliedInputTypes ModerationCategoryAppliedInputTypes
  
  A list of the categories along with the input type(s) that the score applies to.
  - Harassment []string
    
    The applied input type(s) for the category 'harassment'.
    - const ModerationCategoryAppliedInputTypesHarassmentText ModerationCategoryAppliedInputTypesHarassment = "text"
  - HarassmentThreatening []string
    
    The applied input type(s) for the category 'harassment/threatening'.
    - const ModerationCategoryAppliedInputTypesHarassmentThreateningText ModerationCategoryAppliedInputTypesHarassmentThreatening = "text"
  - Hate []string
    
    The applied input type(s) for the category 'hate'.
    - const ModerationCategoryAppliedInputTypesHateText ModerationCategoryAppliedInputTypesHate = "text"
  - HateThreatening []string
    
    The applied input type(s) for the category 'hate/threatening'.
    - const ModerationCategoryAppliedInputTypesHateThreateningText ModerationCategoryAppliedInputTypesHateThreatening = "text"
  - Illicit []string
    
    The applied input type(s) for the category 'illicit'.
    - const ModerationCategoryAppliedInputTypesIllicitText ModerationCategoryAppliedInputTypesIllicit = "text"
  - IllicitViolent []string
    
    The applied input type(s) for the category 'illicit/violent'.
    - const ModerationCategoryAppliedInputTypesIllicitViolentText ModerationCategoryAppliedInputTypesIllicitViolent = "text"
  - SelfHarm []string
    
    The applied input type(s) for the category 'self-harm'.
    - const ModerationCategoryAppliedInputTypesSelfHarmText ModerationCategoryAppliedInputTypesSelfHarm = "text"
    - const ModerationCategoryAppliedInputTypesSelfHarmImage ModerationCategoryAppliedInputTypesSelfHarm = "image"
  - SelfHarmInstructions []string
    
    The applied input type(s) for the category 'self-harm/instructions'.
    - const ModerationCategoryAppliedInputTypesSelfHarmInstructionText ModerationCategoryAppliedInputTypesSelfHarmInstruction = "text"
    - const ModerationCategoryAppliedInputTypesSelfHarmInstructionImage ModerationCategoryAppliedInputTypesSelfHarmInstruction = "image"
  - SelfHarmIntent []string
    
    The applied input type(s) for the category 'self-harm/intent'.
    - const ModerationCategoryAppliedInputTypesSelfHarmIntentText ModerationCategoryAppliedInputTypesSelfHarmIntent = "text"
    - const ModerationCategoryAppliedInputTypesSelfHarmIntentImage ModerationCategoryAppliedInputTypesSelfHarmIntent = "image"
  - Sexual []string
    
    The applied input type(s) for the category 'sexual'.
    - const ModerationCategoryAppliedInputTypesSexualText ModerationCategoryAppliedInputTypesSexual = "text"
    - const ModerationCategoryAppliedInputTypesSexualImage ModerationCategoryAppliedInputTypesSexual = "image"
  - SexualMinors []string
    
    The applied input type(s) for the category 'sexual/minors'.
    - const ModerationCategoryAppliedInputTypesSexualMinorText ModerationCategoryAppliedInputTypesSexualMinor = "text"
  - Violence []string
    
    The applied input type(s) for the category 'violence'.
    - const ModerationCategoryAppliedInputTypesViolenceText ModerationCategoryAppliedInputTypesViolence = "text"
    - const ModerationCategoryAppliedInputTypesViolenceImage ModerationCategoryAppliedInputTypesViolence = "image"
  - ViolenceGraphic []string
    
    The applied input type(s) for the category 'violence/graphic'.
    - const ModerationCategoryAppliedInputTypesViolenceGraphicText ModerationCategoryAppliedInputTypesViolenceGraphic = "text"
    - const ModerationCategoryAppliedInputTypesViolenceGraphicImage ModerationCategoryAppliedInputTypesViolenceGraphic = "image"
- CategoryScores ModerationCategoryScores
  
  A list of the categories along with their scores as predicted by model.
  - Harassment float64
    
    The score for the category 'harassment'.
  - HarassmentThreatening float64
    
    The score for the category 'harassment/threatening'.
  - Hate float64
    
    The score for the category 'hate'.
  - HateThreatening float64
    
    The score for the category 'hate/threatening'.
  - Illicit float64
    
    The score for the category 'illicit'.
  - IllicitViolent float64
    
    The score for the category 'illicit/violent'.
  - SelfHarm float64
    
    The score for the category 'self-harm'.
  - SelfHarmInstructions float64
    
    The score for the category 'self-harm/instructions'.
  - SelfHarmIntent float64
    
    The score for the category 'self-harm/intent'.
  - Sexual float64
    
    The score for the category 'sexual'.
  - SexualMinors float64
    
    The score for the category 'sexual/minors'.
  - Violence float64
    
    The score for the category 'violence'.
  - ViolenceGraphic float64
    
    The score for the category 'violence/graphic'.
- Flagged bool
  
  Whether any of the below categories are flagged.

Moderation Image URL Input

type ModerationImageURLInput struct{…}

An object describing an image to classify.
- ImageURL ModerationImageURLInputImageURL
  
  Contains either an image URL or a data URL for a base64 encoded image.
  - URL string
    
    Either a URL of the image or the base64 encoded image data.
- Type ImageURL
  
  Always image_url.
  - const ImageURLImageURL ImageURL = "image_url"

Moderation Model

type ModerationModel string
- const ModerationModelOmniModerationLatest ModerationModel = "omni-moderation-latest"
- const ModerationModelOmniModeration2024_09_26 ModerationModel = "omni-moderation-2024-09-26"
- const ModerationModelTextModerationLatest ModerationModel = "text-moderation-latest"
- const ModerationModelTextModerationStable ModerationModel = "text-moderation-stable"

type ModerationMultiModalInputUnion interface{…}

An object describing an image to classify.
- type ModerationImageURLInput struct{…}
  
  An object describing an image to classify.
  - ImageURL ModerationImageURLInputImageURL
    
    Contains either an image URL or a data URL for a base64 encoded image.
    - URL string
      
      Either a URL of the image or the base64 encoded image data.
  - Type ImageURL
    
    Always image_url.
    - const ImageURLImageURL ImageURL = "image_url"
- type ModerationTextInput struct{…}
  
  An object describing text to classify.
  - Text string
    
    A string of text to classify.
  - Type Text
    
    Always text.
    - const TextText Text = "text"

Moderation Text Input

type ModerationTextInput struct{…}

An object describing text to classify.
- Text string
  
  A string of text to classify.
- Type Text
  
  Always text.
  - const TextText Text = "text"

go/resources/moderations/index.md +100 −5

6 6

7**post** `/moderations`7**post** `/moderations`

8 8

~~9Create moderation~~9Classifies if text and/or image inputs are potentially harmful. Learn

10more in the [moderation guide](https://platform.openai.com/docs/guides/moderation).

10 11

11### Parameters12### Parameters

12 13

23 24

24 An array of strings to classify for moderation.25 An array of strings to classify for moderation.

25 26

~~26 - `type ModerationNewParamsInputModerationMultiModalArray []ModerationMultiModalInput`~~27 - `type ModerationNewParamsInputModerationMultiModalArray []ModerationMultiModalInputUnion`

27 28

28 An array of multi-modal inputs to the moderation model.29 An array of multi-modal inputs to the moderation model.

29 30

31 - `type ModerationImageURLInput struct{…}`

33 An object describing an image to classify.

35 - `ImageURL ModerationImageURLInputImageURL`

37 Contains either an image URL or a data URL for a base64 encoded image.

39 - `URL string`

41 Either a URL of the image or the base64 encoded image data.

43 - `Type ImageURL`

45 Always `image_url`.

47 - `const ImageURLImageURL ImageURL = "image_url"`

49 - `type ModerationTextInput struct{…}`

51 An object describing text to classify.

53 - `Text string`

55 A string of text to classify.

57 - `Type Text`

59 Always `text`.

61 - `const TextText Text = "text"`

30 - `Model param.Field[ModerationModel]`63 - `Model param.Field[ModerationModel]`

31 64

32 The content moderation model you would like to use. Learn more in65 The content moderation model you would like to use. Learn more in

605 638

606### Moderation Image URL Input639### Moderation Image URL Input

607 640

608- `type ModerationImageURLInput interface{…}`641- `type ModerationImageURLInput struct{…}`

642

643 An object describing an image to classify.

644

645 - `ImageURL ModerationImageURLInputImageURL`

646

647 Contains either an image URL or a data URL for a base64 encoded image.

648

649 - `URL string`

650

651 Either a URL of the image or the base64 encoded image data.

652

653 - `Type ImageURL`

654

655 Always `image_url`.

656

657 - `const ImageURLImageURL ImageURL = "image_url"`

609 658

610### Moderation Model659### Moderation Model

611 660

621 670

622### Moderation Multi Modal Input671### Moderation Multi Modal Input

623 672

624- `type ModerationMultiModalInput interface{…}`673- `type ModerationMultiModalInputUnion interface{…}`

674

675 An object describing an image to classify.

676

677 - `type ModerationImageURLInput struct{…}`

678

679 An object describing an image to classify.

680

681 - `ImageURL ModerationImageURLInputImageURL`

682

683 Contains either an image URL or a data URL for a base64 encoded image.

684

685 - `URL string`

686

687 Either a URL of the image or the base64 encoded image data.

688

689 - `Type ImageURL`

690

691 Always `image_url`.

692

693 - `const ImageURLImageURL ImageURL = "image_url"`

694

695 - `type ModerationTextInput struct{…}`

696

697 An object describing text to classify.

698

699 - `Text string`

700

701 A string of text to classify.

702

703 - `Type Text`

704

705 Always `text`.

706

707 - `const TextText Text = "text"`

625 708

626### Moderation Text Input709### Moderation Text Input

627 710

628- `type ModerationTextInput interface{…}`711- `type ModerationTextInput struct{…}`

712

713 An object describing text to classify.

714

715 - `Text string`

716

717 A string of text to classify.

718

719 - `Type Text`

720

721 Always `text`.

722

723 - `const TextText Text = "text"`