Skip to content
For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to the page URL.
Primary navigation

Suggested
Overview Models Agents Tools Voice & Audio Production API reference
API Dashboard
Try ChatGPT
API Reference

Moderations

Given text and/or image inputs, classifies if those inputs are potentially harmful.

Create moderation
moderations.create(**kwargs) -> ModerationCreateResponse { id, model, results }
POST/moderations
ModelsExpand Collapse
class Moderation { categories, category_applied_input_types, category_scores, flagged }
class ModerationCreateResponse { id, model, results }

Represents if a given text input is potentially harmful.

class ModerationImageURLInput { image_url, type }

An object describing an image to classify.

ModerationModel = :"omni-moderation-latest" | :"omni-moderation-2024-09-26" | :"text-moderation-latest" | :"text-moderation-stable"
ModerationMultiModalInput = ModerationImageURLInput { image_url, type } | ModerationTextInput { text, type }

An object describing an image to classify.

class ModerationTextInput { text, type }

An object describing text to classify.