# Mistral AI — Introducing Shieldstral.

- Company: Mistral AI (mistral.ai)
- Announced: 2026-08-04T00:00:00+00:00
- Category: product-launch
- Subject: Mistral / Le Chat
- Coverage: Covered by 3 outlets
- Source: https://mistral.ai/news/shieldstral
- Record: https://forck.live/items/3504-introducing-shieldstral

By Mistral Back to Blog 5 min read Share this post Copy url to clipboard Copied Thinking Summary Shieldstral introduces a 3B open-weights multimodal safety classifier that outperforms models up to 7x its size by framing content moderation as a policy-adaptive question-answering task. Unlike traditional guardrail models, it accepts plain-language policies at inference time, unifying text and image safety evaluation without retraining. Released under Apache 2.0, it delivers calibrated safety scores across diverse benchmarks while running efficiently on a single 16GB NVIDIA GPU. A 3B open-weights, policy-adaptive multimodal safety classifier that matches models up to 7x its size on text safety and sets a new state of the art on multimodal moderation. “Does this content promote violence against a protected group? Is this image safe to show to a minor? Did the assistant refuse the request?” Every product that ships a model needs to answer questions like these — but the right answer depends on the product, the audience, and the moment. …

## Evidence

Verbatim from https://mistral.ai/news/shieldstral:

> Introducing Shieldstral.

## Around this story

Outlets this record can name and link:

- TestingCatalog AI News: https://testingcatalog.com/mistral-releases-shieldstral-for-multimodal-moderation
- Unite.AI: https://unite.ai/mistrals-shieldstral-packs-policy-adaptive-safety-screening-into-3b-parameters
- The Deep View: https://thedeepview.com/articles/mistral-bets-on-ai-s-missing-safeguards
- arXiv.org: https://arxiv.org/abs/2607.25857

---

Record: https://forck.live/items/3504-introducing-shieldstral
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md