Shieldstral

Shieldstral

Mistral AI
+
+

Related Products

  • Canditech
    111 Ratings
    Visit Website
  • ContractSafe
    326 Ratings
    Visit Website
  • Dynamo Software
    71 Ratings
    Visit Website
  • D&B Credit Insights
    58 Ratings
    Visit Website
  • FrameworkLTC
    48 Ratings
    Visit Website
  • Jobma
    278 Ratings
    Visit Website
  • LeaseAccounting.app
    Visit Website
  • DropTrack
    191 Ratings
    Visit Website
  • ChatD&B
    Visit Website
  • HubSpot AEO
    151 Ratings
    Visit Website

About

The Decisions API turns text and images into typed decisions an application can use, evaluating inputs about 10x faster than the Responses API. Developers provide a model, shared input evidence, and one or more questions describing what should be evaluated, and the API returns structured answers that can be used to classify content, route requests, prioritize work, or make threshold-based decisions. It supports three question types: predicate checks whether a condition is true and returns a probability from 0 to 1; choice selects one value from a fixed set and returns option probabilities and confidence; and score evaluates an input against ordered rubric levels and returns a probability-weighted score. Inputs can be plain text or user messages containing both text and images, allowing applications to evaluate cases such as visible product damage, request intent, document type, issue severity, or answer relevance.

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

Developers and AI application teams needing to classify, score, route, and prioritize text or image inputs through fast, structured model decisions

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

No information available.
Free Version Not Supported
Free Trial Not Supported

Pricing

No information available.
Free Version Not Supported
Free Trial Not Supported

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

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 Information

OpenAI
Founded: 2015
United States
developers.openai.com/api/docs/guides/decisions

Company Information

Mistral AI
Founded: 2023
France
mistral.ai/news/shieldstral/

Alternatives

Clef-flash

Clef-flash

Cloudflare

Alternatives

Clef

Clef

Cloudflare
Jev

Jev

TypeSafe AI
Solar Decide

Solar Decide

Upstage

Categories

AI Decision Models Supported

Categories

AI Models Supported
Content Moderation Supported

Integrations

GPT-6 Luna Supported
Mistral AI Not Supported
OpenAI Supported

Integrations

GPT-6 Luna Not Supported
Mistral AI Supported
OpenAI Not Supported
Claim OpenAI Decisions API and update features and information
Claim OpenAI Decisions API and update features and information
Claim Shieldstral and update features and information
Claim Shieldstral and update features and information