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
This tool is the perfect tool to automatically moderate content. Filter unwanted content from photos, videos, and live streams. The API instantly returns moderation results and scales automatically to meet your needs. You can easily increase your Moderation Pipeline to millions of images per month. The API was designed by developers for developers. To get the API up and running, you only need to write a few lines. Use our SDKs to get detailed documentation. Built on state-of the-art models and proprietary technology. Moderation decisions are consistent and easily auditable. Feedback loops and continuous improvement are also included. Your images are kept private and are not shared with third parties. The 'offensive endpoint detects and recognizes different types of items that are inappropriate for the general public.
API Access
Has API
No
API Access
Has API
Yes
Integrations
Mistral AI
No
Pricing Details
No price information available.
Free Trial
No
Free Version
No
Pricing Details
$29 per month
Free Trial
No
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
Yes
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
Sightengine
Country
France
Website
sightengine.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
Yes
Audio Moderation
Yes
Brand Moderation
Yes
Comment Moderation
Yes
Customizable Filters
Yes
Image Moderation
Yes
Moderation by Humans
No
Reporting / Analytics
Yes
Social Media Moderation
Yes
User-Generated Content (UGC) Moderation
Yes
Video Moderation
Yes