Prompt Guard 86M
Meta AI's Prompt Guard 86M is a moderation model exceling at detecting malicious prompts, including prompt injections and jailbreaks, to help guard against unintended behavior in LLM-powered applications. It is particularly effective at identifying explicitly malicious prompts and data with injected inputs, making it a valuable starting point for developers to identify and mitigate risky inputs.
Input
Output
Context
1K
Max Output
1K
Parameters
278.8M
Technical Specifications
Model TypeChat
Context Window512 tokens
Max Output Tokens512 tokens
Parameters278.8M
Release DateJul 21, 2024
Training CutoffNot available
Licensellama3.1
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Prompt Guard 86M
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.