Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Shieldstral is an innovative multimodal safety classifier with a 3B parameter open-weight structure, adept at assessing text, images, and combined text-plus-image content based on dynamically defined policies during inference. Rather than adhering to a static set of harm categories, it approaches moderation as a binary question-and-answer format: users submit a contextual instruction outlining the evaluation criteria and strictness, pose a yes-or-no safety inquiry, and present the content for assessment. The model processes the “yes” and “no” logits to generate a continuous, calibrated safety score, enabling applications to prioritize or rank outcomes based on confidence levels instead of relying on a single categorical label. This design effectively integrates prompt classification, response moderation, refusal detection, toxicity assessment, and multimodal safety evaluation into a singular interface, empowering teams to modify policies without the need for model retraining. Shieldstral's versatility allows it to analyze prompts, responses, pairs of prompts and responses, images, and images paired with text, making it a comprehensive tool for safety evaluation. As such, it represents a significant advancement in the field of content moderation.
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
No price information available.
Free Trial
No
Free Version
No
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
No
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
Yes
Live Training (Online)
Yes
In Person
No
Types of Training
Training Docs
No
Webinars
No
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
Mistral AI
Founded
2023
Country
France
Website
mistral.ai/news/shieldstral/
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