ShieldstralMistral AI
|
openshieldSway SRL
|
|||||
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
openshield is a hosted API for content moderation and fraud prevention, run by Sway SRL in Belgium. Send images or text from your server to receive an accept, review, or reject decision, along with the categories, scores, and thresholds behind it. Checks cover nudity, gore, weapons, hate symbols, hate speech, personal data, spam, scams, and custom image categories. The same API can check content that users post and that AI agents read or write. Send a sign-up, login, or payment event to receive an allow, step-up, hold, or block decision and the rules that triggered it. Pack rules begin in shadow mode and can act automatically after a 30-day replay. Content is checked in memory and is not stored. openshield is built on openmod and openfraud, open-source Rust engines licensed under Apache-2.0. Pricing is per check from a prepaid balance, with up to 2,000 free checks per month and no card required.
|
|||||
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
|||||
Audience
AI platform teams that need customizable, multimodal content moderation without retraining a separate safety model for every policy
|
Audience
Developers and platforms that need to moderate user content and stop fraud at sign-up, login and payment.
|
|||||
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Not Supported
|
|||||
API
Offers API
Not Supported
|
API
Offers API
Supported
|
|||||
Screenshots and Videos |
Screenshots and VideosNo images available
|
|||||
Pricing
No information available.
Free Version
Not Supported
Free Trial
Not Supported
|
PricingPay per check from a prepaid balance; up to 2,000 checks per month are free, with no card required.
Free Version
Supported
Free Trial
Not Supported
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Supported
Webinars
Supported
Live Online
Supported
In Person
Not Supported
|
Training
Documentation
Not Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
|||||
Company InformationMistral AI
Founded: 2023
France
mistral.ai/news/shieldstral/
|
Company InformationSway SRL
Belgium
openshield.dev/
|
|||||
Alternatives |
Alternatives |
|||||
|
|
|
|||||
Categories |
Categories |
|||||
Integrations
Mistral AI
Not Supported
|
||||||
|
|
|