Create moderation
create_moderationCheck single or multiple texts for potentially harmful content with an OpenAI moderation model and return flagged status plus per-category flags and scores.
Instructions
Check text for potentially harmful content using an OpenAI moderation model. Returns, for each input, whether it was flagged plus per-category flags and scores
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"input": "<input>",
"model": "<model>"
},
"name": "create_moderation"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | Text (or array of texts) to classify | |
| model | Yes | OpenAI model to use for moderation |