Mistral AI · Safety & moderation
Shieldstral 1.0
Compact self-hosted safety classifier: you write policy questions in natural language and it returns yes/no for prompt moderation, response moderation, prompt-response pair classification and refusal detection, over text and images. Weights-only — it is listed in the model catalogue but carries no API model id and appears on neither pricing page, so run it yourself.
Open weights · Permissive (Apache, MIT, OpenMDW) · Data checked September 6, 2026 · Not a hands-on evaluation
Model ID
- Parameters
- 3.8B dense
- Architecture
- Dense
- Context window
- 32,000 tokensMaximum input
- Max output
- Not recordedPer response
- Input price
- Not published
- Output price
- Not published
- Cached input
- Not published
- Blended price
- Not available3:1 input to output
- Knowledge cutoff
- Not recorded
- Released
- 2026-08-04
- Status
- preview
- Size band
- Up to 4B
License and openness
Shieldstral 1.0 is released under the Apache-2.0. This is a permissive license. It generally allows use, modification and redistribution, including commercial use, subject to attribution and notice requirements. License terms can change between versions; confirm the text published with the weights you download.
Capabilities
The reference records no capability tags for this model.
| Input modalities | text, image |
|---|---|
| Output modalities | text |
What it is for
Weights-only — it is listed in the model catalogue but carries no API model id and appears on neither pricing page, so run it yourself.
Cost at list price
| Input | Not published |
|---|---|
| Output | Not published |
| Cached input | Not published |
| Blended, 3:1 | Not available |
The provider publishes no per-token price for this model. Any price you see elsewhere belongs to a third-party host, and running the weights yourself has hardware costs instead.
Estimate a workload across all models ↗Sources
- Source: docs.mistral.ai ↗
- Mistral AI pricing ↗
- API docs ↗
- Full reference record for Shieldstral 1.0 ↗
- Mistral AI in the reference ↗
Sources checked September 6, 2026. Specifications and prices change without notice; confirm against the provider before you commit.
Other open-weight models from Mistral AI
- Mistral Medium 3.5 · 128B dense
- Mistral Large 3 · 675B total · 41B active
- Mistral Small 4 · 119B total · 6.5B active
- Ministral 3 14B · 14B dense
- Ministral 3 8B · 8B dense
- Ministral 3 3B · 3B dense
- Z.ai GLM 5.2 · Not recorded
- Leanstral 1.5 · 119B total · 6.5B active
- Voxtral Small · 24B dense
- Voxtral Mini Transcribe Realtime · 4B dense
- Voxtral TTS · 4B dense