Detector24
Back to Model Catalogue
Violence Detection
ImageStandard Moderation

Violence Detection

Detect violence levels in images using AI vision analysis

Accuracy
92%
Avg. Speed
15.0s
Per Request
$0.0150
API Name
vlm-violence-detection

API Reference

Version
2601
Jan 3, 2026
Avg. Processing
15.0s
Per Request
$0.015
Required Plan
trial

Input Parameters

Vision Language Model for image/video understanding with reasoning

media_typestring

Type of media being sent: 'image' or 'video'. Auto-detected if not specified.

Example:
image
image_urlstring

URL of image to analyze

Example:
https://example.com/image.jpg
base64_imagestring

Base64-encoded image data

video_urlstring

URL of video to analyze

Example:
https://example.com/video.mp4
base64_videostring

Base64-encoded video data

Response Fields

Structured Violence Detection response

responseobject

Structured response from the model

Object Properties:
violencestring
Possible values:
severe_violencelight_violenceno_violence
thinkingstring

Chain-of-thought reasoning from the model (may be empty)

Complete Example

Request

{
  "model": "vlm-violence-detection",
  "image_url": "https://example.com/image.jpg"
}

Response

{
  "inference_id": "inf_abc123def456",
  "model_id": "vlm_violence_detection",
  "model_name": "Violence Detection",
  "moderation_type": "image",
  "status": "completed",
  "result": {
    "response": {
      "violence": "severe_violence"
    },
    "thinking": ""
  }
}

Additional Information

Rate Limiting
If we throttle your request, you will receive a 429 HTTP error code along with an error message. You should then retry with an exponential back-off strategy, meaning that you should retry after 4 seconds, then 8 seconds, then 16 seconds, etc.
Supported Formats
gif, jpeg, jpg, png, webp
Maximum File Size
20MB
Tags:violencesafetyvlmai-analysis

Ready to get started?

Integrate Violence Detection into your application today with our easy-to-use API.

Learn more about image moderationBrowse all models