​
Supported Providers

  • OpenAI

Use the moderations endpoint to identify content that may violate usage policies, such as text or images involving violence, hate speech, harassment, self-harm, or sexual content.

You can use two models for this endpoint:

  • omni-moderation-latest: This model and all snapshots support more categorization options and multi-modal inputs.
  • text-moderation-latest (Legacy): Older model that supports only text inputs and fewer input categorizations. The newer omni-moderation models will be the best choice for new applications.

You can add these models in your OpenAI provider account.

Code Snippets

from openai import OpenAI

BASE_URL = "https://{controlPlaneUrl}/api/llm"
API_KEY = "your-truefoundry-api-key"

# Configure OpenAI client with TrueFoundry settings
client = OpenAI(
    api_key=API_KEY,
    base_url=BASE_URL,
)

response = client.moderations.create(
    model="openai-main/omni-moderation-latest",
    input=[
        {"type": "text", "text": "Text to check for moderation"},
        {
            "type": "image_url",
            "image_url": {
                "url": "https://example.com/image.png",
            }
        },
    ],
)

print(response)

Here’s a full example output, where the input is an image from a single frame of a war movie. The model correctly predicts indicators of violence in the image, with a violence category score of greater than 0.8.

{
  "id": "modr-970d409ef3bef3b70c73d8232df86e7d",
  "model": "omni-moderation-latest",
  "results": [
    {
      "flagged": true,
      "categories": {
        "sexual": false,
        "sexual/minors": false,
        "harassment": false,
        "harassment/threatening": false,
        "hate": false,
        "hate/threatening": false,
        "illicit": false,
        "illicit/violent": false,
        "self-harm": false,
        "self-harm/intent": false,
        "self-harm/instructions": false,
        "violence": true,
        "violence/graphic": false
      },
      "category_scores": {
        "sexual": 2.34135824776394e-7,
        "sexual/minors": 1.6346470245419304e-7,
        "harassment": 0.0011643905680426018,
        "harassment/threatening": 0.0022121340080906377,
        "hate": 3.1999824407395835e-7,
        "hate/threatening": 2.4923252458203563e-7,
        "illicit": 0.0005227032493135171,
        "illicit/violent": 3.682979260160596e-7,
        "self-harm": 0.0011175734280627694,
        "self-harm/intent": 0.0006264858507989037,
        "self-harm/instructions": 7.368592981140821e-8,
        "violence": 0.8599265510337075,
        "violence/graphic": 0.37701736389561064
      },
      "category_applied_input_types": {
        "sexual": [
          "image"
        ],
        "sexual/minors": [],
        "harassment": [],
        "harassment/threatening": [],
        "hate": [],
        "hate/threatening": [],
        "illicit": [],
        "illicit/violent": [],
        "self-harm": [
          "image"
        ],
        "self-harm/intent": [
          "image"
        ],
        "self-harm/instructions": [
          "image"
        ],
        "violence": [
          "image"
        ],
        "violence/graphic": [
          "image"
        ]
      }
    }
  ]
}

​
Key Fields

  • flagged: true if any content is considered harmful.
  • categories: Dictionary of category flags, true means the input falls under that harmful category.
  • category_scores: Probability scores (0 to 1) for each category.
  • category_applied_input_types : Indicates whether the category was triggered by the text or image.