ShieldstralMistral AI
|
WardstoneJRL Software LTD
|
|||||
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
Wardstone is an LLM security API that sits between applications and language model providers, scanning inputs and outputs for threats across four categories in a single call: prompt attacks, content violations, data leakage, and unknown links.
It detects jailbreaks, prompt injections, harmful content (hate, violence, self-harm), PII (SSNs, credit cards, emails, phone numbers), and suspicious URLs. Each response returns risk bands per category with sub-30ms latency.
Works with any LLM provider. REST API with SDKs for TypeScript, Python, Go, Ruby, PHP, Java, and C#. Free tier at 10,000 calls/month, no credit card required. Includes a browser-based playground for testing.
|
|||||
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
AI developers, engineering teams building LLM-powered applications, cybersecurity professionals, content moderation teams, and compliance officers across SaaS, fintech, healthcare, legal, and education industries.
|
|||||
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 VideosNo images available
|
|||||
Pricing
No information available.
Free Version
Free Trial
|
Pricing
$0/month
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 InformationJRL Software LTD
Founded: 2024
wardstone.ai
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
||||||
|
|
|
|||||
Categories |
Categories |
|||||
Integrations
Mistral AI
|
||||||
|
|
|