Using Llama Prompt Guard 2 22M on GroqCloud

Implementation guide · Prompt Guard · AI at Meta

ServerlessOpen Weights

GroqCloud exposes Llama Prompt Guard 2 22M through model ID meta-llama/llama-prompt-guard-2-22m. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

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

Quick Start

  1. 1
    Create an account at GroqCloud and generate an API key.
  2. 2
    Use the GroqCloud SDK or REST API to call meta-llama/llama-prompt-guard-2-22m — see the documentation for request format.
  3. 3
    You'll be billed $0.03/1M input, $0.03/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See GroqCloud documentation for integration details.

Pricing on GroqCloud

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.

Full model details →

Model Specs

Released2025-04-29
Parameters22M
Context512
ArchitectureDecoder Only

More Models on GroqCloud

Llama Prompt Guard 2 86M
All models on GroqCloud →

Provider

GroqCloud

Groq

Mountain View, California, United States