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
Sup AI is a multi-LLM platform that merges outputs from several top large language models, such as GPT, Claude, Llama, and more, to generate richer, more accurate, and better-validated answers than any single model could provide. It applies real-time “logprob confidence scoring,” analyzing each token’s probability to detect uncertainty or hallucination; when a model’s confidence falls below a threshold, the response is halted, helping ensure that delivered answers remain high-quality and trustworthy. Sup’s “multi-model fusion” then compares, contrasts, and consolidates outputs from different models, cross-verifying and synthesizing the best parts into a final result. Sup also supports “multimodal RAG” (retrieval-augmented generation) to incorporate external data (text, PDFs, images) into context-aware responses, giving the AI access to factual sources and helping it “never forget” relevant information.
|
|||||
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
Researchers, knowledge workers, teams and professionals wanting a tool offering high-accuracy AI-assisted content generation, reasoning or research
|
|||||
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
$20 per 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 InformationSup AI
United States
sup.ai/
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
||||||
|
|
|
|||||
Categories |
Categories |
|||||
Integrations
Claude Haiku 4.5
Claude Opus 4.5
Claude Opus 4.7
Claude Opus 5
Claude Sonnet 4.5
Claude Sonnet 4.6
GLM-4.1V
GLM-4.5V
GLM-4.5V-Flash
GLM-4.6
|
Integrations
Claude Haiku 4.5
Claude Opus 4.5
Claude Opus 4.7
Claude Opus 5
Claude Sonnet 4.5
Claude Sonnet 4.6
GLM-4.1V
GLM-4.5V
GLM-4.5V-Flash
GLM-4.6
|
|||||
|
|
|