Mistral has introduced Shieldstral, a 3B open-weights multimodal safety classifier that can evaluate the safety of text and image content. The model is designed to be policy-adaptive, allowing it to be fine-tuned for specific use cases without requiring retraining. Shieldstral has been released under the Apache 2.0 license and is available for download. The model has been shown to match or outperform larger models in certain benchmarks.