ShieldstralMistral AI
|
||||||
Related Products
|
||||||
About
Trusted across the internet to protect communities against offensive content. With an API that couldn't be easier to integrate into your website, app or platform. Analyze an anime (animated) image and rate it for the appropriateness of it's content for a type of audience - adult, teen, everyone. Tags images with detected labels. Detects names any visible anime characters. Detects copyrights (if any) of image content. Analyze text and return any bad words founds for 27 languages, also returns cleaned version of the text. Analyze an image and return the text found in the QRcode. Analyze an image and rate it for the appropriateness of its content for a type of audience - adult, teen, everyone.
|
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
Content Moderation solution for anyone
|
Audience
AI platform teams that need customizable, multimodal content moderation without retraining a separate safety model for every policy
|
|||||
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
Supported
|
|||||
API
Offers API
Supported
|
API
Offers API
Not Supported
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
$0.15 per 1,000 images
Free Version
Supported
Free Trial
Not 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 InformationModerateContent
Canada
moderatecontent.com
|
Company InformationMistral AI
Founded: 2023
France
mistral.ai/news/shieldstral/
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
||||||
|
|
|
|||||
Categories |
Categories |
|||||
Integrations
Discord
Supported
Mistral AI
Not Supported
Slack
Supported
WordPress
Supported
|
Integrations
Discord
Not Supported
Mistral AI
Supported
Slack
Not Supported
WordPress
Not Supported
|
|||||
|
|
|