Meta: Llama Prompt Guard 2 86M
86M-parameter (mDeBERTa-base) multilingual classifier that detects prompt injection and jailbreak attempts
Cheapest input
$0.01
$/MTok · models.dev
Cheapest output
$0.01
$/MTok
Context
512
tokens
Sources
2
5 listings
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestllama-prompt-guard-2-86m | Helicone | $0.01 | $0.01 | $0 | 512 |
| models.devgroq/meta-llama/llama-prompt-guard-2-86m | Eden AI | $0.04 | $0.04 | $0.02 | 512 |
| models.devmeta-llama/llama-prompt-guard-2-86m | Groq | $0.04 | $0.04 | $0.004 | 512 |
| LiteLLMmeta-llama/llama-prompt-guard-2-86m | N/A | $0.04 | $0.04 | $0.004 | N/A |
| LiteLLMllama-prompt-guard-2-86m | N/A | $0.04 | $0.04 | $0.004 | N/A |
Capabilities
- Open weights
- In: text
- Out: text
Knowledge cutoff: 2024-10Released: 2025-04-29Family: llama
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.