Shieldstral 1.0

A compact multimodal moderation model for prompt moderation, response moderation, prompt-response pair classification, refusal detection, and safety filtering across text and image inputs. It uses na…

mistral/shieldstral-1-0

A compact multimodal moderation model for prompt moderation, response moderation, prompt-response pair classification, refusal detection, and safety filtering across text and image inputs. It uses natural-language policy questions and returns a yes or no classification.

Specifications & capabilities

Input
text, image
Output
text
Context window · tokens
32000
Published model ID
shieldstral-1-0
Capabilities
moderation, multimodal, visionInput

Provider specifications & access

1–1 / 1

Shieldstral 1.0 ↗

source model id
shieldstral-1-0
hosting
open-weights
platforms
  • Mistral
context length
32000
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • moderation

Safety assessments

1–1 / 1

Foundation Model Transparency Index 2025 ↗

18 / 100

source id
stanfordFMTI
canonical model id
mistral/shieldstral-1-0
taxonomy
transparency
hazard category
transparency
hazard name
Organization transparency
policy area
Mistral
assessment type
organization-level disclosure
metric
disclosure_score
result label
18 / 100
sample size
100
updated at
2026-11-09T18:08:05.227Z

Source specification observations

1–1 / 1

mistral ↗

field
context_length
value
32000
normalized value
32000
scope
source-model
source id
mistral
confidence
1

Original sources

1–5 / 5

Hugging Face · Weights ↗

Mistral AI · Model documentation ↗

www.apache.org · Weights ↗

GitHub · Catalog ↗

Mistral AI · Catalog ↗

Source links

1–2 / 2

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace