ModelRegistry
Explore text, image, video and speech models
Find the right AI by model, modality and provider.
Browse modelsChoose with facts
Turn the model directory into an actionable evaluation workflow.
Clear capabilities
Review modalities, protocols, limits and status.
Transparent coverage
See which providers expose each model.
Easy comparison
Compare candidates using consistent dimensions.
Start exploring the directory
Begin with a model, provider or organization.
Model spotlight
Shieldstral 1.0 3B
A 3B policy-adaptive multimodal safety classifier for text, images, and combined text-image content. It evaluates content against natural-language policies and returns a safety score from a single forward pass.
Compare modelsCore capabilities
A compact view of the model contract before integration.
Input and output
See supported modalities and generation directions.
Limits and context
Check context, output limits and release details.
Provider coverage
Compare the providers and protocols that expose this version.
Shieldstral 1.0 3B FAQ
Start building with Shieldstral 1.0 3B
Move from model evaluation to a production-ready workflow.
Shieldstral 1.0 3B
mistral/shieldstral-1.0-3b
A 3B open multimodal safety classifier with policies supplied at inference time.
Model family
Shieldstral
-
Focus areas
Core specifications
Modalities
Identity
- Version
- 1.0
- License
- Apache-2.0
- Aliases
- Shieldstral-1.0-3B, mistralai/Shieldstral-1.0-3B
Capabilities
Capabilities and fit
Model summary
A 3B open multimodal safety classifier with policies supplied at inference time.
- Output
- Text
- Capabilities
- 1
- Catalog updated
- 2026-08-06T01:20:46.818Z
- Status