Llama Prompt Guard 2 86M
Developed by Meta AI, Llama Prompt Guard 2 86M is a moderation model exceling at detecting prompt injection and jailbreaking attacks in LLM-powered applications. Its notable technical trait is the use of adversarial-attack resistant tokenization, which helps mitigate attacks such as whitespace manipulations and fragmented tokens.
Input
Output
Context
1K
Max Output
1K
Parameters
278.8M
Technical Specifications
Model TypeChat
Context Window512 tokens
Max Output Tokens512 tokens
Parameters278.8M
Release DateApr 28, 2025
Training CutoffNot available
Licenseother
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Llama Prompt Guard 2 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.