Pass IndexThe State of AISign in

Llama Prompt Guard 2 22M

Llama Prompt Guard 2 22M is the smaller of Meta's two BERT-based prompt-attack classifiers, trained on a large corpus of attacks to detect both prompt injections in untrusted inputs and explicitly malicious jailbreak prompts.

text → text · made by Meta

$0.03$0.03per Mtok in / out
Groq

Free

Offered at no charge, which is not the same as cheap: a free lane carries a rate limit and can be withdrawn. The prices above are what you pay when it is not available to you.

Sold by 2 ways

SellerLaneRate
Groq apistandard$0.03per Mtok in$0.03per Mtok outconsole.groq.com · read 2026-08-25
Groq aggregatorfree$0per Mtok in$0per Mtok outconsole.groq.com · read 2026-09-16

About

Llama Prompt Guard 2 22M — a text model from Meta, sold by one company from $0.03 in and $0.03 out per million tokens.

It takes text and returns text, with a context window of 512 tokens. It was published in October 2024, trained on material up to October 2024. The catalogue files it under chat. Only Groq sells it, at $0.03 in and $0.03 out per million tokens. Beside the standard rate there is a separately routed lane.

Every current figure

Maker
Meta
Register
model
Takes
text
Returns
text
Context
512 tokens
Published
October 2024
Knowledge to
October 2024
Licence
not read
Sellers
1
Maker's own price
not read
Price
$0.03 in and $0.03 out per million tokens — Groq

Known as 1 name

meta-llama/llama-prompt-guard-2-22m