--- title: "Create moderation" method: POST path: "/v2/router/moderations" tags: ["Moderations"] --- # Create moderation `POST /v2/router/moderations` Analyze text for content policy violations using the moderation model and return classification results. ## Request body - object - `input` union, required — Input (or inputs) to classify. Can be a single string, an array of strings, or an array of multi-modal input objects similar to other models. - string - string[] - `model` string, required — The content moderation model you would like to use. Defaults to omni-moderation-latest ## Response `200` Returns moderation classification results - object - `id` string, required — The unique identifier for the moderation request - `model` string, required — The model used to generate the moderation results - `results` union[], required — A list of moderation objects - union - object - `flagged` boolean, required — Whether any of the categories are flagged - `categories` object, required — A list of the categories, and whether they are flagged or not - `hate` boolean, required — Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. - `hate/threatening` boolean, required — Hateful content that also includes violence or serious harm towards the targeted group. - `harassment` boolean, required — Content that expresses, incites, or promotes harassing language towards any target. - `harassment/threatening` boolean, required — Harassment content that also includes violence or serious harm towards any target. - `illicit` boolean, required — Content that includes instructions or advice that facilitate the planning or execution of wrongdoing. - `illicit/violent` boolean, required — Content that includes instructions or advice that facilitate the planning or execution of wrongdoing that also includes violence. - `self-harm` boolean, required — Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders. - `self-harm/intent` boolean, required — Content where the speaker expresses that they are engaging or intend to engage in acts of self-harm. - `self-harm/instructions` boolean, required — Content that encourages performing acts of self-harm, or that gives instructions or advice on how to commit such acts. - `sexual` boolean, required — Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services. - `sexual/minors` boolean, required — Sexual content that includes an individual who is under 18 years old. - `violence` boolean, required — Content that depicts death, violence, or physical injury. - `violence/graphic` boolean, required — Content that depicts death, violence, or physical injury in graphic detail. - `category_scores` object, required — A list of the categories along with their scores as predicted by model - `hate` number, required — The score for the category hate - `hate/threatening` number, required — The score for the category hate/threatening - `harassment` number, required — The score for the category harassment - `harassment/threatening` number, required — The score for the category harassment/threatening - `illicit` number, required — The score for the category illicit - `illicit/violent` number, required — The score for the category illicit/violent - `self-harm` number, required — The score for the category self-harm - `self-harm/intent` number, required — The score for the category self-harm/intent - `self-harm/instructions` number, required — The score for the category self-harm/instructions - `sexual` number, required — The score for the category sexual - `sexual/minors` number, required — The score for the category sexual/minors - `violence` number, required — The score for the category violence - `violence/graphic` number, required — The score for the category violence/graphic - `category_applied_input_types` object — A list of the categories along with the input type(s) that the score applies to - `hate` string[], required — The applied input type(s) for the category hate - `hate/threatening` string[], required — The applied input type(s) for the category hate/threatening - `harassment` string[], required — The applied input type(s) for the category harassment - `harassment/threatening` string[], required — The applied input type(s) for the category harassment/threatening - `illicit` string[], required — The applied input type(s) for the category illicit - `illicit/violent` string[], required — The applied input type(s) for the category illicit/violent - `self-harm` string[], required — The applied input type(s) for the category self-harm - `self-harm/intent` string[], required — The applied input type(s) for the category self-harm/intent - `self-harm/instructions` string[], required — The applied input type(s) for the category self-harm/instructions - `sexual` string[], required — The applied input type(s) for the category sexual - `sexual/minors` string[], required — The applied input type(s) for the category sexual/minors - `violence` string[], required — The applied input type(s) for the category violence - `violence/graphic` string[], required — The applied input type(s) for the category violence/graphic - object - `categories` object, required — A list of the categories, and whether they are flagged or not - `sexual` boolean, required — Sexual content detected - `hate_and_discrimination` boolean, required — Hate and discrimination content detected - `violence_and_threats` boolean, required — Violence and threats content detected - `dangerous_and_criminal_content` boolean, required — Dangerous and criminal content detected - `selfharm` boolean, required — Self-harm content detected - `health` boolean, required — Unqualified health advice detected - `financial` boolean, required — Unqualified financial advice detected - `law` boolean, required — Unqualified legal advice detected - `pii` boolean, required — Personally identifiable information detected - `category_scores` object, required — A list of the categories along with their scores as predicted by model - `sexual` number, required — The score for sexual content - `hate_and_discrimination` number, required — The score for hate and discrimination content - `violence_and_threats` number, required — The score for violence and threats content - `dangerous_and_criminal_content` number, required — The score for dangerous and criminal content - `selfharm` number, required — The score for self-harm content - `health` number, required — The score for unqualified health advice - `financial` number, required — The score for unqualified financial advice - `law` number, required — The score for unqualified legal advice - `pii` number, required — The score for personally identifiable information ## Other responses - `422` — Returns validation error --- [API](https://skmtc.net/orq-ai/apis/orq-ai-api.md) · [All operations](https://skmtc.net/orq-ai/apis/orq-ai-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/orq-ai/orq-ai-api/revisions/2cd7e7f7bcb4/schema)