Average Ratings 0 Ratings

Total
ease
features
design
support

No User Reviews. Be the first to provide a review:

Write a Review

Average Ratings 0 Ratings

Total
ease
features
design
support

No User Reviews. Be the first to provide a review:

Write a Review

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

OpenShield is an API service focused on content moderation and fraud prevention, operated by Sway SRL based in Belgium. Users can transmit images or text from their servers to obtain decisions regarding acceptance, review, or rejection, as well as insights into the categories, scores, and thresholds that influenced those decisions. This service encompasses checks for various concerns, including nudity, violence, weapons, hate symbols, hate speech, personal information, spam, scams, and even custom-defined image categories. Moreover, the same API is capable of analyzing content generated by users and interpreting material created by AI agents. To assess events such as sign-ups, logins, or payments, users can send these events and receive responses indicating whether to allow, step up, hold, or block the action, along with the specific rules that prompted such decisions. The pack rules initially operate in shadow mode and can transition to automatic actions following a 30-day replay period. Notably, content is evaluated in real-time and is not retained after processing. OpenShield utilizes openmod and openfraud, which are open-source engines written in Rust and released under the Apache-2.0 license. Its pricing model is based on a prepaid balance for each check, offering up to 2,000 free checks every month without requiring a credit card for access, making it an accessible option for various users. This combination of features provides a comprehensive solution for organizations seeking to maintain safe and compliant digital environments.

API Access

Has API No 

API Access

Has API Yes 

Screenshots View All

Screenshots View All

No images available

Integrations

Mistral AI Yes 

Integrations

Mistral AI No 

Pricing Details

No price information available.
Free Trial No 
Free Version No 

Pricing Details

Pay per check from a prepaid balance; up to 2,000 checks per month are free, with no card required.
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 No 

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

Sway SRL

Country

Belgium

Website

openshield.dev/

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 

Alternatives

Alternatives

Detectivision Reviews

Detectivision

Detectivision AI