LLM ReferenceLLM Reference

Llama Prompt Guard 2 22M

llama-prompt-guard-2-22m

Researched 29d ago

Last refreshed 2026-04-19. Next refresh: weekly.

Open SourceClassificationJSON / Tool use

Llama Prompt Guard 2 22M is worth evaluating for classification and json / tool use when its provider route and context window match the workload.

Decision context: Classification task fit, 1 tracked provider route, and research from 2026-04-19.

Use it for

  • Teams evaluating classification and json / tool use
  • Workloads that can use a 512 context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Vision or document-understanding workloads

Cheapest output

$0.030

GroqCloud per 1M tokens

Provider routes

1

Tracked API hosts

Quality / dollar

Unknown

No task benchmark coverage yet

Freshness

2026-04-19

Researched 29d ago

fresh

Top use-case fit

Classification

Included by capability and metadata signals in the decision map.

JSON / Tool use

Included by capability and metadata signals in the decision map.

Provider price ladder

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

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.

About

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

Llama Prompt Guard 2 22M has a 512-token context window.

Llama Prompt Guard 2 22M input tokens at $0.03/1M, output at $0.03/1M.

Capabilities

Structured Outputs

Rankings

Specifications

Released2025-04-29
Parameters22M
Context512
ArchitectureDecoder Only
Specializationsafety
LicenseLlama 3.1 Community
Trainingfinetuned

Created by

Large-scale open-source AI for social technologies.

Menlo Park, California, United States
Founded 2013
Website

Providers(1)