ShieldstralMistral AI
|
||||||
Related Products
|
||||||
About
Shieldstral is a 3B open-weights, policy-adaptive multimodal safety classifier designed to evaluate text, images, and text-plus-image content using policies defined at inference time. Instead of relying on a fixed taxonomy of harm categories, it frames moderation as a binary question-answering task: users provide an instruction describing the evaluation context and strictness, a yes-or-no safety question, and the content to judge. The model reads the “yes” and “no” logits and converts them into a continuous, calibrated safety score, allowing applications to threshold or rank results by confidence rather than depend on a single discrete label. This formulation unifies prompt classification, response moderation, refusal detection, toxicity detection, and multimodal safety in one interface, while letting teams adapt policies without retraining the model. Shieldstral can evaluate prompts, responses, prompt-response pairs, images, and images with accompanying text.
|
About
TrustLab provides out-of-the box future-proof regulatory compliance powered by AI & leading industry experts.
Ensure your platform is compliant with:
EU Digital Services Act (DSA)
UK Online Safety Act
Australian Online Safety Act
Plug-and-play user complaints covering current and future regulatory requirements such as the Digital Services Act.
Compliance with regulatory requirements including transparency reports, messaging, statement of reasons, appeals, and more.
Liability protection for fines from user content moderation.
Monitor & measure platform moderation performance with certainty.
Leverage TrustGraph's AI capabilities and industry benchmark to quantify risk in real time.
Detect and enforce on networks of bad actors promoting harmful content.
|
|||||
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
|||||
Audience
AI platform teams that need customizable, multimodal content moderation without retraining a separate safety model for every policy
|
Audience
Online platforms and websites that need a tool to comply with online safety regulations like the Digital Services Act (DSA)
|
|||||
Support
Phone Support
24/7 Live Support
Online
|
Support
Phone Support
24/7 Live Support
Online
|
|||||
API
Offers API
|
API
Offers API
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
No information available.
Free Version
Free Trial
|
Pricing
No information available.
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationMistral AI
Founded: 2023
France
mistral.ai/news/shieldstral/
|
Company InformationTrustLab
Founded: 2019
United States
www.trustlab.com
|
|||||
Alternatives |
Alternatives |
|||||
|
|
|
|||||
|
|
|
|||||
Categories |
Categories |
|||||
Integrations
Mistral AI
|
||||||
|
|
|