Meta logo

Prompt Guard


Prompt Guard is Meta's language model. A DeBERTa-v2-based classifier designed to detect prompt injection and jailbreak attempts in LLM inputs for safety and security applications.
Specifications
Canonical IDmeta-prompt-guard
TypeLanguage
StatusActive
CreatorMetaMeta
Input ModalitiesText
Output ModalitiesText

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·

Model IDs