Moderations

Create moderation

moderations.create(**kwargs) -> ModerationCreateResponse

post /moderations

Create moderation

Parameters

input: String | Array[String] | Array[ModerationMultiModalInput]

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 = String
  
  A string of text to classify for moderation.
- UnionMember1 = Array[String]
  
  An array of strings to classify for moderation.
- ModerationMultiModalArray = Array[ModerationMultiModalInput]
  
  An array of multi-modal inputs to the moderation model.
model: String | ModerationModel

The content moderation model you would like to use. Learn more in the moderation guide, and learn about available models here.
- String = String
- ModerationModel = :"omni-moderation-latest" | :"omni-moderation-2024-09-26" | :"text-moderation-latest" | :"text-moderation-stable"
  - :"omni-moderation-latest"
  - :"omni-moderation-2024-09-26"
  - :"text-moderation-latest"
  - :"text-moderation-stable"

Returns

class ModerationCreateResponse

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: Array[Moderation]
  
  A list of moderation objects.
  - categories: Categories{ harassment, harassment_threatening, hate, 10 more}
    
    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.
    - harassment_threatening: 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.
    - hate_threatening: 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.
    - illicit_violent: 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.
    - self_harm: bool
      
      Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.
    - self_harm_instructions: 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.
    - self_harm_intent: 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).
    - sexual_minors: bool
      
      Sexual content that includes an individual who is under 18 years old.
    - violence: bool
      
      Content that depicts death, violence, or physical injury.
    - violence_graphic: bool
      
      Content that depicts death, violence, or physical injury in graphic detail.
  - category_applied_input_types: CategoryAppliedInputTypes{ harassment, harassment_threatening, hate, 10 more}
    
    A list of the categories along with the input type(s) that the score applies to.
    - harassment: Array[:text]
      
      The applied input type(s) for the category 'harassment'.
      - :text
    - harassment_threatening: Array[:text]
      
      The applied input type(s) for the category 'harassment/threatening'.
      - :text
    - hate: Array[:text]
      
      The applied input type(s) for the category 'hate'.
      - :text
    - hate_threatening: Array[:text]
      
      The applied input type(s) for the category 'hate/threatening'.
      - :text
    - illicit: Array[:text]
      
      The applied input type(s) for the category 'illicit'.
      - :text
    - illicit_violent: Array[:text]
      
      The applied input type(s) for the category 'illicit/violent'.
      - :text
    - self_harm: Array[:text | :image]
      
      The applied input type(s) for the category 'self-harm'.
      - :text
      - :image
    - self_harm_instructions: Array[:text | :image]
      
      The applied input type(s) for the category 'self-harm/instructions'.
      - :text
      - :image
    - self_harm_intent: Array[:text | :image]
      
      The applied input type(s) for the category 'self-harm/intent'.
      - :text
      - :image
    - sexual: Array[:text | :image]
      
      The applied input type(s) for the category 'sexual'.
      - :text
      - :image
    - sexual_minors: Array[:text]
      
      The applied input type(s) for the category 'sexual/minors'.
      - :text
    - violence: Array[:text | :image]
      
      The applied input type(s) for the category 'violence'.
      - :text
      - :image
    - violence_graphic: Array[:text | :image]
      
      The applied input type(s) for the category 'violence/graphic'.
      - :text
      - :image
  - category_scores: CategoryScores{ harassment, harassment_threatening, hate, 10 more}
    
    A list of the categories along with their scores as predicted by model.
    - harassment: Float
      
      The score for the category 'harassment'.
    - harassment_threatening: Float
      
      The score for the category 'harassment/threatening'.
    - hate: Float
      
      The score for the category 'hate'.
    - hate_threatening: Float
      
      The score for the category 'hate/threatening'.
    - illicit: Float
      
      The score for the category 'illicit'.
    - illicit_violent: Float
      
      The score for the category 'illicit/violent'.
    - self_harm: Float
      
      The score for the category 'self-harm'.
    - self_harm_instructions: Float
      
      The score for the category 'self-harm/instructions'.
    - self_harm_intent: Float
      
      The score for the category 'self-harm/intent'.
    - sexual: Float
      
      The score for the category 'sexual'.
    - sexual_minors: Float
      
      The score for the category 'sexual/minors'.
    - violence: Float
      
      The score for the category 'violence'.
    - violence_graphic: Float
      
      The score for the category 'violence/graphic'.
  - flagged: bool
    
    Whether any of the below categories are flagged.

Example

require "openai"

openai = OpenAI::Client.new(api_key: "My API Key")

moderation = openai.moderations.create(input: "I want to kill them.")

puts(moderation)

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

class Moderation
- categories: Categories{ harassment, harassment_threatening, hate, 10 more}
  
  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.
  - harassment_threatening: 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.
  - hate_threatening: 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.
  - illicit_violent: 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.
  - self_harm: bool
    
    Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.
  - self_harm_instructions: 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.
  - self_harm_intent: 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).
  - sexual_minors: bool
    
    Sexual content that includes an individual who is under 18 years old.
  - violence: bool
    
    Content that depicts death, violence, or physical injury.
  - violence_graphic: bool
    
    Content that depicts death, violence, or physical injury in graphic detail.
- category_applied_input_types: CategoryAppliedInputTypes{ harassment, harassment_threatening, hate, 10 more}
  
  A list of the categories along with the input type(s) that the score applies to.
  - harassment: Array[:text]
    
    The applied input type(s) for the category 'harassment'.
    - :text
  - harassment_threatening: Array[:text]
    
    The applied input type(s) for the category 'harassment/threatening'.
    - :text
  - hate: Array[:text]
    
    The applied input type(s) for the category 'hate'.
    - :text
  - hate_threatening: Array[:text]
    
    The applied input type(s) for the category 'hate/threatening'.
    - :text
  - illicit: Array[:text]
    
    The applied input type(s) for the category 'illicit'.
    - :text
  - illicit_violent: Array[:text]
    
    The applied input type(s) for the category 'illicit/violent'.
    - :text
  - self_harm: Array[:text | :image]
    
    The applied input type(s) for the category 'self-harm'.
    - :text
    - :image
  - self_harm_instructions: Array[:text | :image]
    
    The applied input type(s) for the category 'self-harm/instructions'.
    - :text
    - :image
  - self_harm_intent: Array[:text | :image]
    
    The applied input type(s) for the category 'self-harm/intent'.
    - :text
    - :image
  - sexual: Array[:text | :image]
    
    The applied input type(s) for the category 'sexual'.
    - :text
    - :image
  - sexual_minors: Array[:text]
    
    The applied input type(s) for the category 'sexual/minors'.
    - :text
  - violence: Array[:text | :image]
    
    The applied input type(s) for the category 'violence'.
    - :text
    - :image
  - violence_graphic: Array[:text | :image]
    
    The applied input type(s) for the category 'violence/graphic'.
    - :text
    - :image
- category_scores: CategoryScores{ harassment, harassment_threatening, hate, 10 more}
  
  A list of the categories along with their scores as predicted by model.
  - harassment: Float
    
    The score for the category 'harassment'.
  - harassment_threatening: Float
    
    The score for the category 'harassment/threatening'.
  - hate: Float
    
    The score for the category 'hate'.
  - hate_threatening: Float
    
    The score for the category 'hate/threatening'.
  - illicit: Float
    
    The score for the category 'illicit'.
  - illicit_violent: Float
    
    The score for the category 'illicit/violent'.
  - self_harm: Float
    
    The score for the category 'self-harm'.
  - self_harm_instructions: Float
    
    The score for the category 'self-harm/instructions'.
  - self_harm_intent: Float
    
    The score for the category 'self-harm/intent'.
  - sexual: Float
    
    The score for the category 'sexual'.
  - sexual_minors: Float
    
    The score for the category 'sexual/minors'.
  - violence: Float
    
    The score for the category 'violence'.
  - violence_graphic: Float
    
    The score for the category 'violence/graphic'.
- flagged: bool
  
  Whether any of the below categories are flagged.

Moderation Image URL Input

ModerationImageURLInput = untyped

Moderation Model

ModerationModel = :"omni-moderation-latest" | :"omni-moderation-2024-09-26" | :"text-moderation-latest" | :"text-moderation-stable"
- :"omni-moderation-latest"
- :"omni-moderation-2024-09-26"
- :"text-moderation-latest"
- :"text-moderation-stable"

ModerationMultiModalInput = untyped

Moderation Text Input

ModerationTextInput = untyped

Moderation Create Response

class ModerationCreateResponse

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: Array[Moderation]
  
  A list of moderation objects.
  - categories: Categories{ harassment, harassment_threatening, hate, 10 more}
    
    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.
    - harassment_threatening: 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.
    - hate_threatening: 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.
    - illicit_violent: 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.
    - self_harm: bool
      
      Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.
    - self_harm_instructions: 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.
    - self_harm_intent: 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).
    - sexual_minors: bool
      
      Sexual content that includes an individual who is under 18 years old.
    - violence: bool
      
      Content that depicts death, violence, or physical injury.
    - violence_graphic: bool
      
      Content that depicts death, violence, or physical injury in graphic detail.
  - category_applied_input_types: CategoryAppliedInputTypes{ harassment, harassment_threatening, hate, 10 more}
    
    A list of the categories along with the input type(s) that the score applies to.
    - harassment: Array[:text]
      
      The applied input type(s) for the category 'harassment'.
      - :text
    - harassment_threatening: Array[:text]
      
      The applied input type(s) for the category 'harassment/threatening'.
      - :text
    - hate: Array[:text]
      
      The applied input type(s) for the category 'hate'.
      - :text
    - hate_threatening: Array[:text]
      
      The applied input type(s) for the category 'hate/threatening'.
      - :text
    - illicit: Array[:text]
      
      The applied input type(s) for the category 'illicit'.
      - :text
    - illicit_violent: Array[:text]
      
      The applied input type(s) for the category 'illicit/violent'.
      - :text
    - self_harm: Array[:text | :image]
      
      The applied input type(s) for the category 'self-harm'.
      - :text
      - :image
    - self_harm_instructions: Array[:text | :image]
      
      The applied input type(s) for the category 'self-harm/instructions'.
      - :text
      - :image
    - self_harm_intent: Array[:text | :image]
      
      The applied input type(s) for the category 'self-harm/intent'.
      - :text
      - :image
    - sexual: Array[:text | :image]
      
      The applied input type(s) for the category 'sexual'.
      - :text
      - :image
    - sexual_minors: Array[:text]
      
      The applied input type(s) for the category 'sexual/minors'.
      - :text
    - violence: Array[:text | :image]
      
      The applied input type(s) for the category 'violence'.
      - :text
      - :image
    - violence_graphic: Array[:text | :image]
      
      The applied input type(s) for the category 'violence/graphic'.
      - :text
      - :image
  - category_scores: CategoryScores{ harassment, harassment_threatening, hate, 10 more}
    
    A list of the categories along with their scores as predicted by model.
    - harassment: Float
      
      The score for the category 'harassment'.
    - harassment_threatening: Float
      
      The score for the category 'harassment/threatening'.
    - hate: Float
      
      The score for the category 'hate'.
    - hate_threatening: Float
      
      The score for the category 'hate/threatening'.
    - illicit: Float
      
      The score for the category 'illicit'.
    - illicit_violent: Float
      
      The score for the category 'illicit/violent'.
    - self_harm: Float
      
      The score for the category 'self-harm'.
    - self_harm_instructions: Float
      
      The score for the category 'self-harm/instructions'.
    - self_harm_intent: Float
      
      The score for the category 'self-harm/intent'.
    - sexual: Float
      
      The score for the category 'sexual'.
    - sexual_minors: Float
      
      The score for the category 'sexual/minors'.
    - violence: Float
      
      The score for the category 'violence'.
    - violence_graphic: Float
      
      The score for the category 'violence/graphic'.
  - flagged: bool
    
    Whether any of the below categories are flagged.

ruby/resources/moderations/index.md +839 −0 created

1# Moderations

3## Create moderation

5`moderations.create(**kwargs) -> ModerationCreateResponse`

7**post** `/moderations`

9Create moderation

11### Parameters

13- `input: String | Array[String] | Array[ModerationMultiModalInput]`

15 Input (or inputs) to classify. Can be a single string, an array of strings, or

16 an array of multi-modal input objects similar to other models.

18 - `String = String`

20 A string of text to classify for moderation.

22 - `UnionMember1 = Array[String]`

24 An array of strings to classify for moderation.

26 - `ModerationMultiModalArray = Array[ModerationMultiModalInput]`

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

30- `model: String | ModerationModel`

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

33 [the moderation guide](https://platform.openai.com/docs/guides/moderation), and learn about

34 available models [here](https://platform.openai.com/docs/models#moderation).

36 - `String = String`

38 - `ModerationModel = :"omni-moderation-latest" | :"omni-moderation-2024-09-26" | :"text-moderation-latest" | :"text-moderation-stable"`

40 - `:"omni-moderation-latest"`

42 - `:"omni-moderation-2024-09-26"`

44 - `:"text-moderation-latest"`

46 - `:"text-moderation-stable"`

48### Returns

50- `class ModerationCreateResponse`

52 Represents if a given text input is potentially harmful.

54 - `id: String`

56 The unique identifier for the moderation request.

58 - `model: String`

60 The model used to generate the moderation results.

62 - `results: Array[Moderation]`

64 A list of moderation objects.

66 - `categories: Categories{ harassment, harassment_threatening, hate, 10 more}`

68 A list of the categories, and whether they are flagged or not.

70 - `harassment: bool`

72 Content that expresses, incites, or promotes harassing language towards any target.

74 - `harassment_threatening: bool`

76 Harassment content that also includes violence or serious harm towards any target.

78 - `hate: bool`

80 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.

82 - `hate_threatening: bool`

84 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.

86 - `illicit: bool`

88 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.

90 - `illicit_violent: bool`

92 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.

94 - `self_harm: bool`

96 Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.

98 - `self_harm_instructions: bool`

100 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.

101

102 - `self_harm_intent: bool`

103

104 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.

105

106 - `sexual: bool`

107

108 Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness).

109

110 - `sexual_minors: bool`

111

112 Sexual content that includes an individual who is under 18 years old.

113

114 - `violence: bool`

115

116 Content that depicts death, violence, or physical injury.

117

118 - `violence_graphic: bool`

119

120 Content that depicts death, violence, or physical injury in graphic detail.

121

122 - `category_applied_input_types: CategoryAppliedInputTypes{ harassment, harassment_threatening, hate, 10 more}`

123

124 A list of the categories along with the input type(s) that the score applies to.

125

126 - `harassment: Array[:text]`

127

128 The applied input type(s) for the category 'harassment'.

129

130 - `:text`

131

132 - `harassment_threatening: Array[:text]`

133

134 The applied input type(s) for the category 'harassment/threatening'.

135

136 - `:text`

137

138 - `hate: Array[:text]`

139

140 The applied input type(s) for the category 'hate'.

141

142 - `:text`

143

144 - `hate_threatening: Array[:text]`

145

146 The applied input type(s) for the category 'hate/threatening'.

147

148 - `:text`

149

150 - `illicit: Array[:text]`

151

152 The applied input type(s) for the category 'illicit'.

153

154 - `:text`

155

156 - `illicit_violent: Array[:text]`

157

158 The applied input type(s) for the category 'illicit/violent'.

159

160 - `:text`

161

162 - `self_harm: Array[:text | :image]`

163

164 The applied input type(s) for the category 'self-harm'.

165

166 - `:text`

167

168 - `:image`

169

170 - `self_harm_instructions: Array[:text | :image]`

171

172 The applied input type(s) for the category 'self-harm/instructions'.

173

174 - `:text`

175

176 - `:image`

177

178 - `self_harm_intent: Array[:text | :image]`

179

180 The applied input type(s) for the category 'self-harm/intent'.

181

182 - `:text`

183

184 - `:image`

185

186 - `sexual: Array[:text | :image]`

187

188 The applied input type(s) for the category 'sexual'.

189

190 - `:text`

191

192 - `:image`

193

194 - `sexual_minors: Array[:text]`

195

196 The applied input type(s) for the category 'sexual/minors'.

197

198 - `:text`

199

200 - `violence: Array[:text | :image]`

201

202 The applied input type(s) for the category 'violence'.

203

204 - `:text`

205

206 - `:image`

207

208 - `violence_graphic: Array[:text | :image]`

209

210 The applied input type(s) for the category 'violence/graphic'.

211

212 - `:text`

213

214 - `:image`

215

216 - `category_scores: CategoryScores{ harassment, harassment_threatening, hate, 10 more}`

217

218 A list of the categories along with their scores as predicted by model.

219

220 - `harassment: Float`

221

222 The score for the category 'harassment'.

223

224 - `harassment_threatening: Float`

225

226 The score for the category 'harassment/threatening'.

227

228 - `hate: Float`

229

230 The score for the category 'hate'.

231

232 - `hate_threatening: Float`

233

234 The score for the category 'hate/threatening'.

235

236 - `illicit: Float`

237

238 The score for the category 'illicit'.

239

240 - `illicit_violent: Float`

241

242 The score for the category 'illicit/violent'.

243

244 - `self_harm: Float`

245

246 The score for the category 'self-harm'.

247

248 - `self_harm_instructions: Float`

249

250 The score for the category 'self-harm/instructions'.

251

252 - `self_harm_intent: Float`

253

254 The score for the category 'self-harm/intent'.

255

256 - `sexual: Float`

257

258 The score for the category 'sexual'.

259

260 - `sexual_minors: Float`

261

262 The score for the category 'sexual/minors'.

263

264 - `violence: Float`

265

266 The score for the category 'violence'.

267

268 - `violence_graphic: Float`

269

270 The score for the category 'violence/graphic'.

271

272 - `flagged: bool`

273

274 Whether any of the below categories are flagged.

275

276### Example

277

278```ruby

279require "openai"

280

281openai = OpenAI::Client.new(api_key: "My API Key")

282

283moderation = openai.moderations.create(input: "I want to kill them.")

284

285puts(moderation)

286```

287

288#### Response

289

290```json

291{

292 "id": "id",

293 "model": "model",

294 "results": [

295 {

296 "categories": {

297 "harassment": true,

298 "harassment/threatening": true,

299 "hate": true,

300 "hate/threatening": true,

301 "illicit": true,

302 "illicit/violent": true,

303 "self-harm": true,

304 "self-harm/instructions": true,

305 "self-harm/intent": true,

306 "sexual": true,

307 "sexual/minors": true,

308 "violence": true,

309 "violence/graphic": true

310 },

311 "category_applied_input_types": {

312 "harassment": [

313 "text"

314 ],

315 "harassment/threatening": [

316 "text"

317 ],

318 "hate": [

319 "text"

320 ],

321 "hate/threatening": [

322 "text"

323 ],

324 "illicit": [

325 "text"

326 ],

327 "illicit/violent": [

328 "text"

329 ],

330 "self-harm": [

331 "text"

332 ],

333 "self-harm/instructions": [

334 "text"

335 ],

336 "self-harm/intent": [

337 "text"

338 ],

339 "sexual": [

340 "text"

341 ],

342 "sexual/minors": [

343 "text"

344 ],

345 "violence": [

346 "text"

347 ],

348 "violence/graphic": [

349 "text"

350 ]

351 },

352 "category_scores": {

353 "harassment": 0,

354 "harassment/threatening": 0,

355 "hate": 0,

356 "hate/threatening": 0,

357 "illicit": 0,

358 "illicit/violent": 0,

359 "self-harm": 0,

360 "self-harm/instructions": 0,

361 "self-harm/intent": 0,

362 "sexual": 0,

363 "sexual/minors": 0,

364 "violence": 0,

365 "violence/graphic": 0

366 },

367 "flagged": true

368 }

369 ]

370}

371```

372

373## Domain Types

374

375### Moderation

376

377- `class Moderation`

378

379 - `categories: Categories{ harassment, harassment_threatening, hate, 10 more}`

380

381 A list of the categories, and whether they are flagged or not.

382

383 - `harassment: bool`

384

385 Content that expresses, incites, or promotes harassing language towards any target.

386

387 - `harassment_threatening: bool`

388

389 Harassment content that also includes violence or serious harm towards any target.

390

391 - `hate: bool`

392

393 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.

394

395 - `hate_threatening: bool`

396

397 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.

398

399 - `illicit: bool`

400

401 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.

402

403 - `illicit_violent: bool`

404

405 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.

406

407 - `self_harm: bool`

408

409 Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.

410

411 - `self_harm_instructions: bool`

412

413 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.

414

415 - `self_harm_intent: bool`

416

417 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.

418

419 - `sexual: bool`

420

421 Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness).

422

423 - `sexual_minors: bool`

424

425 Sexual content that includes an individual who is under 18 years old.

426

427 - `violence: bool`

428

429 Content that depicts death, violence, or physical injury.

430

431 - `violence_graphic: bool`

432

433 Content that depicts death, violence, or physical injury in graphic detail.

434

435 - `category_applied_input_types: CategoryAppliedInputTypes{ harassment, harassment_threatening, hate, 10 more}`

436

437 A list of the categories along with the input type(s) that the score applies to.

438

439 - `harassment: Array[:text]`

440

441 The applied input type(s) for the category 'harassment'.

442

443 - `:text`

444

445 - `harassment_threatening: Array[:text]`

446

447 The applied input type(s) for the category 'harassment/threatening'.

448

449 - `:text`

450

451 - `hate: Array[:text]`

452

453 The applied input type(s) for the category 'hate'.

454

455 - `:text`

456

457 - `hate_threatening: Array[:text]`

458

459 The applied input type(s) for the category 'hate/threatening'.

460

461 - `:text`

462

463 - `illicit: Array[:text]`

464

465 The applied input type(s) for the category 'illicit'.

466

467 - `:text`

468

469 - `illicit_violent: Array[:text]`

470

471 The applied input type(s) for the category 'illicit/violent'.

472

473 - `:text`

474

475 - `self_harm: Array[:text | :image]`

476

477 The applied input type(s) for the category 'self-harm'.

478

479 - `:text`

480

481 - `:image`

482

483 - `self_harm_instructions: Array[:text | :image]`

484

485 The applied input type(s) for the category 'self-harm/instructions'.

486

487 - `:text`

488

489 - `:image`

490

491 - `self_harm_intent: Array[:text | :image]`

492

493 The applied input type(s) for the category 'self-harm/intent'.

494

495 - `:text`

496

497 - `:image`

498

499 - `sexual: Array[:text | :image]`

500

501 The applied input type(s) for the category 'sexual'.

502

503 - `:text`

504

505 - `:image`

506

507 - `sexual_minors: Array[:text]`

508

509 The applied input type(s) for the category 'sexual/minors'.

510

511 - `:text`

512

513 - `violence: Array[:text | :image]`

514

515 The applied input type(s) for the category 'violence'.

516

517 - `:text`

518

519 - `:image`

520

521 - `violence_graphic: Array[:text | :image]`

522

523 The applied input type(s) for the category 'violence/graphic'.

524

525 - `:text`

526

527 - `:image`

528

529 - `category_scores: CategoryScores{ harassment, harassment_threatening, hate, 10 more}`

530

531 A list of the categories along with their scores as predicted by model.

532

533 - `harassment: Float`

534

535 The score for the category 'harassment'.

536

537 - `harassment_threatening: Float`

538

539 The score for the category 'harassment/threatening'.

540

541 - `hate: Float`

542

543 The score for the category 'hate'.

544

545 - `hate_threatening: Float`

546

547 The score for the category 'hate/threatening'.

548

549 - `illicit: Float`

550

551 The score for the category 'illicit'.

552

553 - `illicit_violent: Float`

554

555 The score for the category 'illicit/violent'.

556

557 - `self_harm: Float`

558

559 The score for the category 'self-harm'.

560

561 - `self_harm_instructions: Float`

562

563 The score for the category 'self-harm/instructions'.

564

565 - `self_harm_intent: Float`

566

567 The score for the category 'self-harm/intent'.

568

569 - `sexual: Float`

570

571 The score for the category 'sexual'.

572

573 - `sexual_minors: Float`

574

575 The score for the category 'sexual/minors'.

576

577 - `violence: Float`

578

579 The score for the category 'violence'.

580

581 - `violence_graphic: Float`

582

583 The score for the category 'violence/graphic'.

584

585 - `flagged: bool`

586

587 Whether any of the below categories are flagged.

588

589### Moderation Image URL Input

590

591- `ModerationImageURLInput = untyped`

592

593### Moderation Model

594

595- `ModerationModel = :"omni-moderation-latest" | :"omni-moderation-2024-09-26" | :"text-moderation-latest" | :"text-moderation-stable"`

596

597 - `:"omni-moderation-latest"`

598

599 - `:"omni-moderation-2024-09-26"`

600

601 - `:"text-moderation-latest"`

602

603 - `:"text-moderation-stable"`

604

605### Moderation Multi Modal Input

606

607- `ModerationMultiModalInput = untyped`

608

609### Moderation Text Input

610

611- `ModerationTextInput = untyped`

612

613### Moderation Create Response

614

615- `class ModerationCreateResponse`

616

617 Represents if a given text input is potentially harmful.

618

619 - `id: String`

620

621 The unique identifier for the moderation request.

622

623 - `model: String`

624

625 The model used to generate the moderation results.

626

627 - `results: Array[Moderation]`

628

629 A list of moderation objects.

630

631 - `categories: Categories{ harassment, harassment_threatening, hate, 10 more}`

632

633 A list of the categories, and whether they are flagged or not.

634

635 - `harassment: bool`

636

637 Content that expresses, incites, or promotes harassing language towards any target.

638

639 - `harassment_threatening: bool`

640

641 Harassment content that also includes violence or serious harm towards any target.

642

643 - `hate: bool`

644

645 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.

646

647 - `hate_threatening: bool`

648

649 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.

650

651 - `illicit: bool`

652

653 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.

654

655 - `illicit_violent: bool`

656

657 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.

658

659 - `self_harm: bool`

660

661 Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.

662

663 - `self_harm_instructions: bool`

664

665 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.

666

667 - `self_harm_intent: bool`

668

669 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.

670

671 - `sexual: bool`

672

673 Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness).

674

675 - `sexual_minors: bool`

676

677 Sexual content that includes an individual who is under 18 years old.

678

679 - `violence: bool`

680

681 Content that depicts death, violence, or physical injury.

682

683 - `violence_graphic: bool`

684

685 Content that depicts death, violence, or physical injury in graphic detail.

686

687 - `category_applied_input_types: CategoryAppliedInputTypes{ harassment, harassment_threatening, hate, 10 more}`

688

689 A list of the categories along with the input type(s) that the score applies to.

690

691 - `harassment: Array[:text]`

692

693 The applied input type(s) for the category 'harassment'.

694

695 - `:text`

696

697 - `harassment_threatening: Array[:text]`

698

699 The applied input type(s) for the category 'harassment/threatening'.

700

701 - `:text`

702

703 - `hate: Array[:text]`

704

705 The applied input type(s) for the category 'hate'.

706

707 - `:text`

708

709 - `hate_threatening: Array[:text]`

710

711 The applied input type(s) for the category 'hate/threatening'.

712

713 - `:text`

714

715 - `illicit: Array[:text]`

716

717 The applied input type(s) for the category 'illicit'.

718

719 - `:text`

720

721 - `illicit_violent: Array[:text]`

722

723 The applied input type(s) for the category 'illicit/violent'.

724

725 - `:text`

726

727 - `self_harm: Array[:text | :image]`

728

729 The applied input type(s) for the category 'self-harm'.

730

731 - `:text`

732

733 - `:image`

734

735 - `self_harm_instructions: Array[:text | :image]`

736

737 The applied input type(s) for the category 'self-harm/instructions'.

738

739 - `:text`

740

741 - `:image`

742

743 - `self_harm_intent: Array[:text | :image]`

744

745 The applied input type(s) for the category 'self-harm/intent'.

746

747 - `:text`

748

749 - `:image`

750

751 - `sexual: Array[:text | :image]`

752

753 The applied input type(s) for the category 'sexual'.

754

755 - `:text`

756

757 - `:image`

758

759 - `sexual_minors: Array[:text]`

760

761 The applied input type(s) for the category 'sexual/minors'.

762

763 - `:text`

764

765 - `violence: Array[:text | :image]`

766

767 The applied input type(s) for the category 'violence'.

768

769 - `:text`

770

771 - `:image`

772

773 - `violence_graphic: Array[:text | :image]`

774

775 The applied input type(s) for the category 'violence/graphic'.

776

777 - `:text`

778

779 - `:image`

780

781 - `category_scores: CategoryScores{ harassment, harassment_threatening, hate, 10 more}`

782

783 A list of the categories along with their scores as predicted by model.

784

785 - `harassment: Float`

786

787 The score for the category 'harassment'.

788

789 - `harassment_threatening: Float`

790

791 The score for the category 'harassment/threatening'.

792

793 - `hate: Float`

794

795 The score for the category 'hate'.

796

797 - `hate_threatening: Float`

798

799 The score for the category 'hate/threatening'.

800

801 - `illicit: Float`

802

803 The score for the category 'illicit'.

804

805 - `illicit_violent: Float`

806

807 The score for the category 'illicit/violent'.

808

809 - `self_harm: Float`

810

811 The score for the category 'self-harm'.

812

813 - `self_harm_instructions: Float`

814

815 The score for the category 'self-harm/instructions'.

816

817 - `self_harm_intent: Float`

818

819 The score for the category 'self-harm/intent'.

820

821 - `sexual: Float`

822

823 The score for the category 'sexual'.

824

825 - `sexual_minors: Float`

826

827 The score for the category 'sexual/minors'.

828

829 - `violence: Float`

830

831 The score for the category 'violence'.

832

833 - `violence_graphic: Float`

834

835 The score for the category 'violence/graphic'.

836

837 - `flagged: bool`

838

839 Whether any of the below categories are flagged.

ruby/resources/moderations/index.md 2026-07-07 08:02 UTC to 2026-07-09 20:58 UTC

Moderations

Create moderation

Parameters

Returns

Example

Response

Domain Types

Moderation

Moderation Image URL Input

Moderation Model

Moderation Multi Modal Input

Moderation Text Input

Moderation Create Response