Shieldstral 1 is Mistral AI's language model with a 32K context window. A Mistral safety-focused LLM designed for content moderation and policy-compliance filtering, representing Mistral's dedicated guardrail model sub-brand.
| Specifications | |
|---|---|
mistral-shieldstral-1 | |
| Language | |
| Active | |
| 32K tokens | |
| Text | |
| Text | |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·