Llama Prompt Guard 2 22M on GroqCloud

Prompt Guard · AI at Meta

ServerlessOpen Weights

Last refreshed 2026-07-09. Next refresh: weekly.

Why use Llama Prompt Guard 2 22M on GroqCloud?

GroqCloud offers Llama Prompt Guard 2 22M with pay-as-you-go pricing at $0.03/1M input tokens. Groq is a company specializing in AI inference technology, particularly with their flagship product, the Language Processing Unit (LPU™).

Input / 1M
$0.030
Output / 1M
$0.030
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: meta-llama/llama-prompt-guard-2-22m
Model ID
meta-llama/llama-prompt-guard-2-22m

Request example

Curated snippets for this provider are not sourced yet. Use GroqCloud documentation with model ID meta-llama/llama-prompt-guard-2-22m.

Gotchas

  • Use provider model ID "meta-llama/llama-prompt-guard-2-22m", not the LLMReference slug "llama-prompt-guard-2-22m".

Pricing

TypePrice (per 1M)
Input tokens$0.03
Output tokens$0.03

Capabilities

Structured Outputs

About Llama Prompt Guard 2 22M

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

Get Started

Model CardDocsPortalPlaygroundPricing

Model Specs

Released2025-04-29
Parameters22M
Context512
ArchitectureDecoder Only

Related Models on GroqCloud

Llama Prompt Guard 2 86M

Provider

GroqCloud

Groq

All models on GroqCloud →Provider setup guide →