Llama Prompt Guard 2 22M

Released
2025-04-29
Last refreshed
2026-07-09
Status
Researched 164d ago
Open weightsCommercial use: conditionalClassificationJSON / Tool use
AI at Meta releases · 7 in the last 12 monthsChangelog →
Specifications
Released
2025-04-29
Context
512
Parameters
22M
Architecture
Decoder Only
Specialization
safety
Openness
Open weights
License
Llama 3 CommunityCommercial use: conditional
Weights
Available
Code
Unknown
Training
Fine-tuned
Created by

Large-scale open-source AI for social technologies.

Menlo Park, California, United States
Founded 2013
Website
Pricing
Output / 1M
$0.030
Input / 1M
$0.030

Cheapest of 1 route · GroqCloud

About

Lightweight prompt injection and jailbreak detection classifier from Meta. 22M parameter variant optimized for low-latency content moderation with 512 token context.

Provider price ladder

Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
GroqCloud$0.030$0.030
Serverless

Capabilities

Structured Outputs

Benchmark peer barsfor Classification

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

Compare Llama Prompt Guard 2 22M with other models