Meta Llama Prompt Guard 2 22M
by Helicone · family llama · listed Apr 2025W
22M-parameter (DeBERTa-xsmall) English classifier that detects prompt injection and jailbreak attempts
Current rates USD per 1M tokens
Input$0.01
Output$0.01
Cache read—
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
llama-prompt-guard-2-22m- Context window
- 512 tokens
- Max output
- 2 tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- yes
- Knowledge cutoff
- Oct 2024
- Released
- 2025-04-29
- Last updated
- 2025-04-29
← All Helicone listings