ShieldstralMistral AI
|
||||||
Related Products
|
||||||
About
Moderation API is the content moderation platform built on our own frontier models. Instead of wrapping a general-purpose LLM, we train purpose-built trust & safety models on a large proprietary dataset of real-world harmful content. They detect toxicity, harassment, hate, sexual content, spam, scams, phishing, malicious URLs and personal data across text and images, and catch the obfuscation bad actors use to evade filters. Train custom models on your own policy in Model studio, or deploy AI agents that enforce your guidelines with full conversation context. Every decision returns a clear allow, review or reject recommendation. Built-in review queues and a moderation dashboard let your team handle edge cases, act on bad actors and improve accuracy with every decision. Dry-run mode lets you test on live traffic before blocking anything. Go live in an afternoon with SDKs, a REST API or no-code integrations. GDPR and CCPA compliant. Start free, no credit card.
|
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.
|
|||||
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
Organizations and companies of all sizes
|
Audience
AI platform teams that need customizable, multimodal content moderation without retraining a separate safety model for every policy
|
|||||
Support
Phone Support
Supported
24/7 Live Support
Not Supported
Online
Supported
|
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
|||||
API
Offers API
Not Supported
|
API
Offers API
Not Supported
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
$0
Free Version
Supported
Free Trial
Supported
|
Pricing
No information available.
Free Version
Not Supported
Free Trial
Not Supported
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
Training
Documentation
Supported
Webinars
Supported
Live Online
Supported
In Person
Not Supported
|
|||||
Company InformationModeration API
Founded: 2023
United States
moderationapi.com
|
Company InformationMistral AI
Founded: 2023
France
mistral.ai/news/shieldstral/
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
|
|||||
Categories |
Categories |
|||||
|
|
|