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
Reduce manual moderation overhead with human-like AI classification. Highly accurate AI that understands tone, context, and setting. By considering signals together, just like a human would, Unitary enables you to make more accurate classifications. This means better user experience, less time reviewing inaccurate judgments, and more time for your moderators to focus on what matters. Models custom-fit to your detailed trust and safety guidelines. Off-the-shelf models that take into account tone, context, and setting to deliver significant increases in accuracy. Power real-time customer journeys and workflows. Process tens of millions of pieces of content per day. Reduce manual moderation costs and protect users. Unitary was founded to help brands and platforms understand every piece of content in detail. We do this by building context-aware AI and multimodal machine learning methods to interpret content in context.
|
|||||
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
Companies in need of a solution to understand and accurately interpret content in detail
|
|||||
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
Free
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 InformationUnitary
United Kingdom
www.unitary.ai/
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
||||||
|
|
|
|||||
|
|
||||||
Categories |
Categories |
|||||
|
|
|