Irisnet

Overview

Irisnet provides an API-first solution for automated image and video moderation, designed to assist online platforms in enforcing content policies and maintaining brand safety. The service uses machine learning algorithms to identify and categorize various types of content, including explicit, violent, illegal, and otherwise undesirable material. This automation aims to reduce the operational overhead associated with manual content review, allowing for faster processing of user-generated content (UGC) and adherence to platform guidelines.

The system is engineered to detect a range of content policy violations, from graphic violence and sexually explicit imagery to hate speech and drug-related content. By integrating the Irisnet API, developers can submit images or video frames for analysis, receiving a programmatic response that details the detected content and its severity. This output can then be used to automate actions such as content removal, flagging for human review, or user warnings, depending on the platform's specific moderation rules. The API is applicable across various industries, including social media, e-commerce, dating apps, and online gaming, where user-generated content is prevalent and requires stringent moderation to ensure a safe and compliant environment.

Irisnet's emphasis on data privacy and compliance is reflected in its adherence to General Data Protection Regulation (GDPR) standards. This commitment is important for businesses operating within the European Union or handling data from EU citizens, as it helps ensure that content moderation processes align with regulatory requirements for data processing and user rights. The platform also offers flexibility in its consumption model, providing both monthly subscription plans and pay-as-you-go options to accommodate different usage volumes and budgetary needs. Its developer experience is described as straightforward, with documentation that includes API references and code examples to facilitate integration into existing applications.

For organizations seeking to scale their content moderation efforts without a proportional increase in human resources, Irisnet offers a programmatic approach to identify and manage problematic content. Its core product, the Irisnet API, is built to process high volumes of visual data efficiently, providing a critical tool for platforms committed to fostering safe online communities and protecting their users from harmful content. Businesses can leverage its capabilities to augment human moderation teams or to establish an initial layer of automated filtering before human review, thereby streamlining content workflows and improving response times to policy violations.

Key features

• Image Moderation: Automatically scans and analyzes still images for compliance with predefined content policies, detecting categories such as nudity, violence, and hate symbols.
• Video Moderation: Processes video content by analyzing individual frames, identifying prohibited material, and providing time-coded detections for review.
• Content Categorization: Classifies detected content into specific risk categories (e.g., explicit, suggestive, graphic violence, drug use) to enable granular policy enforcement.
• Customizable Policies: Allows users to define and configure their own content moderation rules and thresholds to align with specific platform guidelines and regional regulations.
• Real-time Analysis: Provides near real-time content analysis, enabling prompt action on newly uploaded user-generated content.
• API-First Design: Offers a RESTful API for seamless integration into existing applications and moderation workflows.
• GDPR Compliance: Processes data in accordance with General Data Protection Regulation standards to ensure privacy and regulatory adherence.

Pricing

Irisnet's pricing model is credit-based, offering both monthly subscription plans and a pay-as-you-go option. Each credit typically corresponds to one image or video frame analysis. As of May 2026, the following plans are available:

For the most current and detailed pricing information, refer to the official Irisnet pricing page.

Common integrations

The Irisnet API is designed for integration into various platforms and applications requiring automated content moderation. Typical integration points include:

• User-Generated Content (UGC) Platforms: Websites and apps where users upload images or videos, such as social media, forums, and dating services, integrate the API to moderate new submissions.
• E-commerce Marketplaces: Platforms that allow third-party sellers to list products can use Irisnet to ensure product images comply with marketplace guidelines.
• Online Gaming Platforms: To moderate in-game content, user profiles, or community posts for inappropriate imagery.
• Content Management Systems (CMS): Integration with CMS platforms to automatically scan and moderate media assets before publication.
• Cloud Storage Solutions: For automated scanning of uploaded media files in cloud environments to identify and flag problematic content.

Alternatives

• Sightengine: Offers AI-powered content moderation APIs for images, videos, and text, with a focus on comprehensive detection categories.
• Amazon Rekognition: A cloud-based computer vision service providing image and video analysis, including content moderation, object and scene detection, and facial analysis.
• Google Cloud Vision AI: Google's cloud-based computer vision service for image analysis, capable of detecting explicit content, performing object recognition, and extracting text.

Getting started

To begin using the Irisnet API, you typically obtain an API key and then send requests to their moderation endpoints. Here's a basic Python example demonstrating how to send an image URL for moderation:

import requests

API_KEY = "YOUR_IRISNET_API_KEY" # Replace with your actual API key
IMAGE_URL = "https://example.com/your-image.jpg" # Replace with the URL of the image to moderate

headers = {
    "x-api-key": API_KEY,
    "Content-Type": "application/json"
}

payload = {
    "media": {
        "url": IMAGE_URL
    }
}

try:
    response = requests.post("https://api.irisnet.de/v1/moderation", headers=headers, json=payload)
    response.raise_for_status() # Raise HTTPError for bad responses (4xx or 5xx)

    result = response.json()
    print("Moderation Result:")
    print(result)

    # Example of parsing results
    if result.get("moderation"):
        for category, details in result["moderation"].items():
            print(f"  Category: {category}")
            print(f"    Score: {details.get('score', 'N/A')}")
            print(f"    Label: {details.get('label', 'N/A')}")
            if details.get('is_detected'):
                print(f"    Detected: True")
                print(f"    Severity: {details.get('severity', 'N/A')}")
    else:
        print("No moderation data found.")

except requests.exceptions.HTTPError as http_err:
    print(f"HTTP error occurred: {http_err} - {response.text}")
except requests.exceptions.ConnectionError as conn_err:
    print(f"Connection error occurred: {conn_err}")
except requests.exceptions.Timeout as timeout_err:
    print(f"Timeout error occurred: {timeout_err}")
except requests.exceptions.RequestException as req_err:
    print(f"An unexpected error occurred: {req_err}")

This Python script sends a POST request to the Irisnet moderation endpoint with an image URL. It expects an API key for authentication and processes the JSON response to print the moderation results, indicating detected categories and their scores. For comprehensive details on request parameters, video moderation, and other functionalities, consult the official Irisnet developer documentation. Implementing robust error handling and response parsing tailored to specific moderation policies is recommended for production environments. For example, a platform might consider content with a high 'score' in the 'nudity' category to be automatically removed, while content with a lower score might be flagged for human review, as described in content moderation best practices by organizations like the Mozilla Developer Network's Content Security Policy guidance.