Shieldstral

Shieldstral

Mistral AI
Tev1

Tev1

Together AI
+
+

Related Products

  • Omnilert
    26 Ratings
    Visit Website
  • Adobe Firefly
    25,051 Ratings
    Visit Website
  • SDS Manager
    4 Ratings
    Visit Website
  • SciSure
    311 Ratings
    Visit Website
  • Breathe
    655 Ratings
    Visit Website
  • HSI Donesafe
    176 Ratings
    Visit Website
  • Google AI Studio
    41 Ratings
    Visit Website
  • SmartDraw
    573 Ratings
    Visit Website
  • LM-Kit.NET
    29 Ratings
    Visit Website
  • Canditech
    111 Ratings
    Visit Website

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

Tev1 is a fast decision and classification model built by Together AI and fine-tuned from Qwen3.5 4B. It is designed around a simple interface: provide a piece of state, a question, and 2 to 24 labeled options, and the model returns exactly one letter that software can map back to a semantic key. This structure supports production tasks such as routing support tickets, evaluating automated returns, applying policy rules, rating sentiment, categorizing documents, and inserting deterministic decision points into larger agent pipelines. The model has 4.7B parameters, a 32.8K-token context window, and runs with non-thinking generation for fast, predictable classification. It was trained on 37,840 examples spanning intent detection, boolean comprehension, sentiment, policy application, routing, news categories, and research-paper taxonomy. Recommended settings use temperature 0 and a very small output budget so responses remain stable and easy to parse.

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

AI platform teams that need customizable, multimodal content moderation without retraining a separate safety model for every policy

Audience

Developers and AI engineering teams seeking to route, classify, score, and apply policy decisions through fast, deterministic structured outputs

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 Not Supported

API

Offers API Supported

Screenshots and Videos

Screenshots and Videos

Pricing

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

Pricing

$0.04 per 1M tokens
Free Version 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 Supported
Live Online Supported
In Person Not Supported

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported

Company Information

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

Company Information

Together AI
Founded: 2022
United States
www.together.ai/models/tev1-4b-experimental

Alternatives

Alternatives

Clef-flash

Clef-flash

Cloudflare
Clef

Clef

Cloudflare
Jev

Jev

TypeSafe AI

Categories

AI Models Supported
Content Moderation Supported

Categories

AI Decision Models Supported

Integrations

Mistral AI Supported
Python Not Supported
Qwen3.5 Not Supported
TypeScript Not Supported

Integrations

Mistral AI Not Supported
Python Supported
Qwen3.5 Supported
TypeScript Supported
Claim Shieldstral and update features and information
Claim Shieldstral and update features and information
Claim Tev1 and update features and information
Claim Tev1 and update features and information