Skip to main content

​
API Information

  • Endpoint: https://api.aihubmix.com/v1/moderations
  • Request Method: POST
  • Authentication: Authorization: Bearer <AIHUBMIX_API_KEY>
  • Content-Type: application/json
  • This endpoint supports two models: 1. omni-moderation-latest: This model and all snapshots support more classification options and multimodal input. 2. text-moderation-latest: Supports only text input, with fewer classification options.

​
Quick Start

​
Usage Example

import openai

client = openai.OpenAI(
  api_key="AIHUBMIX_API_KEY",  
  base_url="https://aihubmix.com/v1"
)

response = client.moderations.create(
    model="text-moderation-latest",
    input="The Yangtze River rolls eastward, its waves washing away heroes. Right and wrong, success and failure, all seem empty; the green hills remain, though the sun sets many times. The white-haired fisherman and woodcutter on the riverbank, accustomed to watching the autumn moon and spring breeze. A pot of turbid wine brings joy in meeting, how many events through time are all laughed off.",
)

print(response)

​
Output Example

Here is a complete output example, where the model correctly predicts self-harm and violence elements in the image. 
{
  "id": "modr-5175",
  "model": "omni-moderation-latest",
  "results": [
    {
      "flagged": true,

      "categories": {
        "harassment": false,
        "harassment_threatening": false,
        "hate": false,
        "hate_threatening": false,
        "illicit": false,
        "illicit_violent": false,

        "self_harm": true,
        "self_harm_instructions": false,
        "self_harm_intent": false,

        "sexual": false,
        "sexual_minors": false,

        "violence": true,
        "violence_graphic": true
      },

      "category_applied_input_types": {
        "harassment": ["text"],
        "harassment_threatening": ["text"],
        "hate": ["text"],
        "hate_threatening": ["text"],
        "illicit": ["text"],
        "illicit_violent": ["text"],

        "self_harm": ["text", "image"],
        "self_harm_instructions": ["text", "image"],
        "self_harm_intent": ["text", "image"],

        "sexual": ["text", "image"],
        "sexual_minors": ["text"],

        "violence": ["text", "image"],
        "violence_graphic": ["text", "image"]
      },

      "category_scores": {
        "harassment": 0.00507676338091392,
        "harassment_threatening": 0.0008967480822931635,
        "hate": 8.830458477845481e-05,
        "hate_threatening": 1.0720880092159908e-05,
        "illicit": 3.740956047302422e-05,
        "illicit_violent": 2.868540823874629e-05,

        "self_harm": 0.6967791744783793,
        "self_harm_instructions": 0.00027978227581033677,
        "self_harm_intent": 0.0003781080988395418,

        "sexual": 0.0007007652612809208,
        "sexual_minors": 2.5071593847983196e-06,

        "violence": 0.5236158587905301,
        "violence_graphic": 0.4213528687243541
      }
    }
  ]
}
The output result includes several categories in the JSON response, which inform you about the types of content present in the input (if any) and the extent to which the model believes they are present.
Output CategoryDescription
flaggedSet to true if the model classifies the content as potentially harmful,false otherwise.
categoriesContains a dictionary of per-category violation flags. For each category, the value is true if the model flags the corresponding category as violated, false otherwise.
category_scoresContains a dictionary of per-category scores output by the model, denoting the model’s confidence that the input violates the OpenAI’s policy for the category. The value is between 0 and 1, where higher values denote higher confidence.
category_applied_input_typesThis property contains information on which input types were flagged in the response, for each category. For example, if the both the image and text inputs to the model are flagged for “violence/graphic”, the violence/graphic property will be set to ["image", "text"]. This is only available on omni models.

​
Content Categories

The table below describes the types of content that the moderation API can detect, along with the models and input types supported for each category.
Categories labeled “text-only” do not support image input. If you send only images to the model (without text) using omni-moderation-latest, the model will return a score of 0 for these unsupported categories.
CategoryDescriptionModelInput
harassmentContent that expresses, incites, or promotes harassing language towards any target.AllText only
harassment/threateningHarassment content that also includes violence or serious harm towards any target.AllText only
hateContent that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. Hateful content aimed at non-protected groups (e.g., chess players) is harassment.AllText only
hate/threateningHateful content that also includes violence or serious harm towards the targeted group based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste.AllText only
illicitThe same types of content flagged by the illicit category, but also includes references to violence or procuring a weapon.Omni onlyText only
illicit/violentSimilar to the content type marked illicit, but also includes mentions of violence or acquiring weapons.Omni onlyText only
self-harmContent that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.AllText and Images
self-harm/intentContent where the speaker expresses that they are engaging or intend to engage in acts of self-harm, such as suicide, cutting, and eating disorders.AllText and Images
self-harm/instructionsContent that encourages performing acts of self-harm, such as suicide, cutting, and eating disorders, or that gives instructions or advice on how to commit such acts.AllText and Images
sexualContent meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness).AllText and Images
sexual/minorsSexual content that includes an individual who is under 18 years old.AllText only
violenceContent that depicts death, violence, or physical injury.AllText and Images
violence/graphicContent that depicts death, violence, or physical injury in graphic detail.AllText and Images