Skip to main content
Shipped
No vapor
The AI that actually shipped
Front
Decision models
New
Rising
Vapor log
Roundup
Submit
Sign in
Home
Wiki
Shieldstral
Copy Markdown
View as Markdown
Shieldstral
Shieldstral is listed here as a model.
2026-04-27
2026-10-19
1
Items per week for 26 weeks, 2026-04-27 to 2026-10-19; peak 1; latest week 0. Bars: items per week. Dashed line: four-week average.
Mentioned with
Licence
Apache-2.0
2
Task
content moderation
2
Model
GPT-OSS-Safeguard-20B
1
Model
LlavaGuard
1
Model
LlavaGuard-7B
1
Maker
Mistral AI
1
Maker
OpenAI
1
Concept
VRAM
1
Model
gpt-oss-safeguard
1
Task
multimodal safety classification
1
Task
policy-based classification
1
Licensed under
Licence
Apache-2.0
2
Made by
Maker
Mistral AI
1
Related coverage
Mistral AI releases Shieldstral 1.0, a 3B multimodal safety classifier under Apache 2.0
2026-07-16
OpenAI releases gpt-oss-safeguard, open-weight safety reasoning models that read your policy
2025-10-29