NAME
OpenAPI::Client::OpenAI::Path::moderations - Documentation for the /moderations path.
DESCRIPTION
This document describes the API endpoint at /moderations
.
See the examples/
directory in the distribution for examples of how to use this.
POST /moderations
Classifies if text and/or image inputs are potentially harmful. Learn more in the [moderation guide](/docs/guides/moderation).
Operation ID
createModeration
$client->createModeration( ... );
Request Body
Content Type: application/json
Example:
{
"model" : "omni-moderation-2024-09-26"
}
Responses
Status Code: 200
OK
Content Types:
application/json
Example:
{ "results" : [ { "category_scores" : null, "category_applied_input_types" : { "harassment" : [ null ], "self-harm/instructions" : [ null ], "hate/threatening" : [ null ], "illicit/violent" : [ null ], "violence" : [ null ], "sexual/minors" : [ null ], "illicit" : [ null ], "hate" : [ null ], "self-harm" : [ null ], "harassment/threatening" : [ null ], "self-harm/intent" : [ null ], "sexual" : [ null ], "violence/graphic" : [ null ] }, "categories" : null } ] }
SEE ALSO
COPYRIGHT AND LICENSE
Copyright (C) 2023-2025 by Nelson Ferraz
This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself, either Perl version 5.14.0 or, at your option, any later version of Perl 5 you may have available.