Documentation 2026-04-30 06:13 UTC to 2026-05-02 05:57 UTC

1# Moderation1# Moderation

2 2 

3Use the [moderations](https://developers.openai.com/api/docs/api-reference/moderations) endpoint to check whether text or images are potentially harmful. If harmful content is identified, you can take corrective action, like filtering content or intervening with user accounts creating offending content. The moderation endpoint is free to use.3Use the [moderations](https://developers.openai.com/api/docs/api-reference/moderations) endpoint to check whether text or images are potentially harmful. If harmful content is identified, you can take corrective action, like filtering content or intervening with user accounts creating offending content. The moderation endpoint is free to use. Image files are limited to 20 MB.

4 4 

5You can use two models for this endpoint:5You can use two models for this endpoint:

6 6 

134 134 

135Categories marked as "Text only" do not support image inputs. If you send only135Categories marked as "Text only" do not support image inputs. If you send only

136 images (without accompanying text) to the `omni-moderation-latest` model, it136 images (without accompanying text) to the `omni-moderation-latest` model, it

137 will return a score of 0 for these unsupported categories.137 will return a score of 0 for these unsupported categories. Image files are

138 limited to 20 MB.

138 139 

139<table>140<table>

140 <tr>141 <tr>