meta-llama: Meta Llama Prompt Guard 2 86M

llama-prompt-guard-2-86m
Context: 512
Max Output: 2
Input: $0.010/1M
Output: $0.010/1M
86M parameter multilingual prompt safety classifier based on mDeBERTa-base, detecting prompt injections and jailbreaks across 8+ languages with adversarial-resistant tokenization.
Input: Text
Output: Text

Providers

groq
Credits
Context512
Max Output2
Input$0.010/1M
Output$0.010/1M
Cache Read—
Cache Write—

Quick Start

Use Meta Llama Prompt Guard 2 86M through Helicone's AI Gateway with automatic logging and monitoring.