Skip to main content
Method: client.generateModeration().

​
Example

const moderation = await client.generateModeration({
  model: "openai/omni-moderation-latest",
  input: "Text to classify",
});

​
Key parameters

  • model (required): Moderation model id (e.g., openai/omni-moderation-latest).
  • input (required): String or array of content items (text or image_url).
  • Optional: categories/severity filters (when supported), user tag.

​
Returns

ModerationResponse 
{
  "results": [
    {
      "flagged": false,
      "categories": {
        "hate": false,
        "hate/threatening": false,
        "harassment": false,
        "harassment/threatening": false,
        "self-harm": false,
        "self-harm/intent": false,
        "self-harm/instructions": false,
        "sexual": false,
        "sexual/minors": false,
        "violence": false,
        "violence/graphic": false
      },
      "category_scores": {
        "hate": 0.01,
        "hate/threatening": 0.0,
        "harassment": 0.02,
        "harassment/threatening": 0.0,
        "self-harm": 0.0,
        "self-harm/intent": 0.0,
        "self-harm/instructions": 0.0,
        "sexual": 0.05,
        "sexual/minors": 0.0,
        "violence": 0.01,
        "violence/graphic": 0.0
      }
    }
  ]
}