Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Moderation API gives trust & safety teams frontier moderation models that are purpose-built, trained in-house and ready for production. Instead of prompting a general-purpose LLM, our models were trained from the ground up on a large proprietary dataset of real-world harmful content. That makes them faster, more cost-efficient and harder to fool.
One API covers text, images and other user content, detecting toxicity, harassment, hate, sexual content, spam, scams, phishing, malicious URLs and personal data. Specialist detectors for scams and malicious links go beyond the usual harm categories, and robust handling of obfuscation means evasive content doesn't slip through.
Your policies, enforced precisely: build custom models on your own data in Model studio, or use AI agents that apply your written guidelines with full conversation context. Each result is a clear allow, review or reject recommendation you can automate on immediately.
Human expertise stays in the loop. Flagged content lands in review queues inside a moderation dashboard, where moderators act on bad actors and every decision improves your models over time. Dry-run mode lets you measure accuracy on real traffic before enforcement goes live.
Developer-first from day one: SDKs, a REST API and no-code integrations get you live in hours, not months. GDPR and CCPA compliant, and free to start.
Description
VigiMod serves as an API designed for content moderation across various platforms including chats, forums, games, comment sections, and online communities. By examining each message in conjunction with up to 10 prior messages, it effectively interprets context for replies, jokes, and spoilers. The API assesses various factors such as toxicity, insults, hate speech, threats, sexual content, self-harm, advertising, and spam, while also allowing for the inclusion of custom rules expressed in straightforward language. Developers have the flexibility to establish thresholds and policies that control how content is managed, enabling actions like reviews, deletions, warnings, timeouts, or bans within their applications. Additionally, VigiMod provides tools such as moderator queues, ban lists, and webhooks to streamline moderation processes. It retains only queued messages for a period ranging from 1 to 90 days, discarding those deemed unnecessary. This robust moderation tool supports 26 different languages, with the most comprehensive training available in Italian, English, Spanish, French, German, and Portuguese. Furthermore, a user-friendly dashboard allows for the tracking of API keys and their usage statistics. Currently, beta access is offered free of charge, subject to rate and key limitations, allowing developers to test its features before committing to a paid plan.
API Access
Has API
No
API Access
Has API
Yes
Screenshots View All
No images available
Pricing Details
$0
Free Trial
Yes
Free Version
Yes
Pricing Details
$0
Beta access is free, with up to 120 messages per minute per API key and a maximum of 10 API keys. Paid tiers for higher limits are planned but are not currently offered.
Free Trial
Yes
Free Version
Yes
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
Yes
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Types of Training
Training Docs
No
Webinars
No
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
Moderation API
Founded
2023
Country
United States
Website
moderationapi.com
Vendor Details
Company Name
VigiMod Team
Founded
2026
Country
Italy
Website
www.vigimod.com
Product Features
Content Moderation
Artificial Intelligence
No
Audio Moderation
No
Brand Moderation
No
Comment Moderation
No
Customizable Filters
No
Image Moderation
No
Moderation by Humans
No
Reporting / Analytics
No
Social Media Moderation
No
User-Generated Content (UGC) Moderation
No
Video Moderation
No
Product Features
Content Moderation
Artificial Intelligence
No
Audio Moderation
No
Brand Moderation
No
Comment Moderation
No
Customizable Filters
No
Image Moderation
No
Moderation by Humans
No
Reporting / Analytics
No
Social Media Moderation
No
User-Generated Content (UGC) Moderation
No
Video Moderation
No