DetectivisionDetectivision AI
|
ShieldstralMistral AI
|
|||||
Related Products
|
||||||
About
Detectivision is an AI content moderation API for businesses that review user-generated content across websites, mobile apps, marketplaces, social networks, forums, dating services, gaming platforms, and other interactive products. It screens text, images, video, and live streams for potentially harmful or policy-violating material, returning flags and, when requested, the location of each finding or a censored copy. Teams can connect the API to their existing publishing and review workflows, then use the results in their own tools or the Detectivision dashboard. Product, engineering, and trust and safety teams can use it to support human review and reduce the need to inspect every submission manually. Text moderation supports Turkish and English.
|
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
Businesses and organizations that host user-generated content, including e-commerce platforms, online marketplaces, social media networks, online communities, forums, dating apps, gaming platforms, and customer review websites. Ideal users include product managers, software developers, trust and safety teams, content moderators, and business owners seeking to automate content screening, reduce manual moderation workloads, and maintain safer online environments.
|
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
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 VideosNo images available
|
Screenshots and Videos |
|||||
Pricing
$49/month
The Basic plan costs $49 per month and includes 10,000 text credits, 10,000 image credits, and 300 video credits. The plan is free for the first two months.
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 InformationDetectivision AI
Founded: 2025
Turkey
detectivision.ai/
|
Company InformationMistral AI
Founded: 2023
France
mistral.ai/news/shieldstral/
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
||||||
|
|
||||||
Categories |
Categories |
|||||
Integrations
Mistral AI
Not Supported
|
||||||
|
|
|