86M-parameter (mDeBERTa-base) multilingual classifier that detects prompt injection and jailbreak attempts
Context
512
512 tokens
Max output
2
2 tokens
Input
$0.01
per 1M tokens
Output
$0.01
per 1M tokens
Providers
3
3 listings
Intelligence
—
Not yet scored
Pricing
USD per 1M tokens · listed by Helicone
| Token type | Standard |
|---|---|
| Input | $0.01 |
| Output | $0.01 |
Lowest input price across providers: $0.01.
Capabilities
ReasoningNo
Tool callNo
Structured outputNo
TemperatureYes
AttachmentsNo
Interleaved reasoningNo
Open weightsYes
ModeratedUnknown
Input
Text
Output
Text
Benchmarks
Published scores and Design Arena Elo
No published benchmark scores for this model yet.
Rankings
Position on each OneAtlas leaderboard
Providers · 3
3 listings
| Provider | Model ID | Context | Input limit | Output | Input $ | Output $ | Reasoning $ | Cache read | Cache write | Audio in | Audio out | Reasoning | Tools | Structured | Temp. | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
 Eden AI | groq/meta-llama/llama-prompt-guard-2-86m | 512 | — | 512 | $0.04 | $0.04 | — | $0.02 | — | — | — | No | No | No | No | Apr 29, 2025 |
 Groq | meta-llama/llama-prompt-guard-2-86m | 512 | — | 512 | $0.04 | $0.04 | — | — | — | — | — | No | No | Unknown | No | Apr 29, 2025 |
 Helicone | llama-prompt-guard-2-86m | 512 | — | 2 | $0.01 | $0.01 | — | — | — | — | — | No | No | Unknown | Yes | Apr 29, 2025 |