Shieldstral

Mistral AI

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.

Specs

Model

Family
Shieldstral
Variant
1.0 3B
Parameters
3B
Weights
Open
License
Apache-2.0

Limits

Context
262,144 tokens

Modalities

Input
Text Image
Output
Text

Capabilities

Reasoning
No
Tool calling
No
Attachments
Yes

Dates

Announced
4 Aug 2026
Released
4 Aug 2026

Introducing Shieldstral.

Shieldstral introduces a 3B open-weights multimodal safety classifier that outperforms models up to 7x its size.

Mistral AI
mistral.ai

More from Mistral AI

All models

Mistral Large 4

Mistral AI · beta

Mistral Large 4 is a natively multimodal model with 1 trillion total parameters and 49 billion active parameters, built for coding, agentic workflows and multimodal understanding. Available in public API preview; weights are planned for release by the end of October 2026.

$0.68 / $2.09 per 1M · $0.07 cached 6w ago

Keep up with the tools

An occasional email when notable AI dev tools and models land in the directory. No spam, unsubscribe anytime.