ShieldstralMistral AI
|
||||||
Related Products
|
||||||
About
Bodyguard protects your online communities and platforms against toxic content, cyberharassment and hate speech. Leverage the power of positive interactions, shield your communities from the negative ones. Different toxic content categories and severity levels. Contextual analysis. Internet language “decoding”. From a few blog comments, to thousands of social media comments, all the way up to live streaming. Powerful data bank to inform content decisions and uncover new ways to engage with your followers. Choose what toxic content categories you want to moderate. Safe platforms are 3x more likely to retain users and to attract new users towards the community. A lack of toxic content means visitors will spend around 60% more time on your platforms. Protect your brand image, users and employees. Don’t attach your business or brand to toxic content. Smooth, quick integration via API. Works with any platform. Pricing based on your needs.
|
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
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
|||||
Audience
Content moderation solution for anyone wanting to prevent toxic online content, cyberbullying and hate speech
|
Audience
AI platform teams that need customizable, multimodal content moderation without retraining a separate safety model for every policy
|
|||||
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
No information available.
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationBodyguard
Founded: 2017
France
www.bodyguard.ai/businesses
|
Company InformationMistral AI
Founded: 2023
France
mistral.ai/news/shieldstral/
|
|||||
Alternatives |
Alternatives |
|||||
|
|
|
|||||
|
|
||||||
|
|
||||||
Categories |
Categories |
|||||
Integrations
Mistral AI
|
||||||
|
|
|