# Mistral's Shieldstral brings safety checks to images

> A compact 3B open-weights classifier flags unsafe text and visual content, and ships under Apache 2.0.

Published by The Open Weights on Jul 16, 2026. Canonical: https://theopenweights.com/news/shieldstral-1-0-3b-5n2j

## Key facts

- Company: Mistral AI
- Model: Shieldstral 1.0 3B
- Version: 1.0
- Category: Vision-Language
- Modalities: Text / LLM, Vision-Language
- License: Apache 2.0 (Open weights, commercial use allowed)
- Parameters: 3B
- Context window: 262K tokens
- Architecture: Mistral3ForConditionalGeneration
- Precision: BF16
- Weights size: 7.7 GB
- Significance: notable
- Published: 2026-07-16
- Last verified: 2026-08-14
- Hugging Face: https://huggingface.co/mistralai/Shieldstral-1.0-3B
- Canonical URL: https://theopenweights.com/news/shieldstral-1-0-3b-5n2j

Mistral AI has released **Shieldstral 1.0 3B**, a compact multimodal classifier built to moderate both text and images. At 3 billion parameters, it is small enough to run cheaply as a guardrail alongside larger generative systems, and it arrives under a permissive Apache 2.0 license on [Hugging Face](https://huggingface.co/mistralai/Shieldstral-1.0-3B).

Unlike a chat model, Shieldstral is purpose-built to judge content rather than produce it. Its multimodal design means it can evaluate visual inputs as well as text, a capability that matters as image generation and vision-language systems become more common in production. Mistral positions the model as a content-moderation and safety tool, according to its [announcement](https://mistral.ai/news/shieldstral/).

## Why it matters

Safety classifiers are increasingly treated as infrastructure: teams deploy them at the input and output layers of an application to catch policy-violating prompts and responses. A few points stand out here:

- **Open weights**, so developers can inspect, fine-tune, and self-host the classifier.
- **Multimodal coverage**, extending moderation beyond text to images.
- **Small footprint** at 3B parameters, keeping latency and cost low for a component that runs on every request.

The permissive license is notable in a category where safety tooling is often gated or API-only. By putting a vision-capable moderation model in the open, Mistral gives builders an alternative they can adapt to their own policies rather than relying on a hosted service. Details on supported categories and evaluation are available on the model's Hugging Face page.

## Get the model

- [Hugging Face](https://huggingface.co/mistralai/Shieldstral-1.0-3B)
- [Hacker News](https://mistral.ai/news/shieldstral/)

## Sources

- [mistralai/Shieldstral-1.0-3B](https://huggingface.co/mistralai/Shieldstral-1.0-3B) — Hugging Face, Jul 16, 2026
- [Mistral's Shieldstral: 3B open-weights model for multimodal moderation](https://mistral.ai/news/shieldstral/) — Hacker News, Aug 4, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Mistral's Shieldstral brings safety checks to images", The Open Weights, Jul 16, 2026, https://theopenweights.com/news/shieldstral-1-0-3b-5n2j