Introducing Shieldstral. | Mistral
https://mistral.ai/news/shieldstral/
Shieldstral — Mistral safety publication; watched for whether further documentation is added alongside it
2
Lines added
2
Lines removed
Was read
2026-09-08
66f03817c75fc0f8…
Changed by
2026-09-30
d088d4618b17bb62…
2 lines added, 2 lines removed
Left column is the version read 2026-09-08, right is 2026-09-30. Unchanged stretches are elided. Both bodies are kept in full and are addressed by the hashes above.
⋯ 66 unchanged lines
6767 BTW, we're hiring! If you want to help make AI better, see our careers page .
6868
6969 Shieldstral
7070
71−Open
71+Apache 2.0
7272
73−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.
73+Text and image safety classification against a supplied policy.
7474 Text-to-text
7575 Image-to-Text
7676
7777 Read documentation