Safety model for policy screening, moderation, and risk-aware routing workflows
Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...
Context
164K
163,840 tokens
Max output
16K
16,384 tokens
Input
$0.14
per 1M tokens
Output
$0.14
per 1M tokens
Providers
5
5 listings
Intelligence
—
Not yet scored
Pricing
USD per 1M tokens · listed by Kilo Gateway
| Token type | Standard |
|---|---|
| Input | $0.14 |
| Output | $0.14 |
Lowest input price across providers: Free.
Capabilities
ReasoningNo
Tool callNo
Structured outputNo
TemperatureYes
AttachmentsYes
Interleaved reasoningNo
Open weightsYes
ModeratedNo
Input
TextImage
Output
Text
Benchmarks
Published scores and Design Arena Elo
No published benchmark scores for this model yet.
Rankings
Position on each OneAtlas leaderboard
Providers · 5
5 listings
| Provider | Model ID | Context | Input limit | Output | Input $ | Output $ | Reasoning $ | Cache read | Cache write | Audio in | Audio out | Reasoning | Tools | Structured | Temp. | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
 Deep Infra | meta-llama/Llama-Guard-4-12B | 164K | — | 164K | $0.18 | $0.18 | — | — | — | — | — | No | No | Unknown | Yes | Apr 29, 2025 |
 Eden AI | deepinfra/meta-llama/Llama-Guard-4-12B | 164K | — | 164K | $0.18 | $0.18 | — | — | — | — | — | No | No | No | Yes | Apr 29, 2025 |
 Hugging Face | meta-llama/Llama-Guard-4-12B | 164K | — | 164K | $0.18 | $0.18 | — | — | — | — | — | No | No | Unknown | Yes | Apr 29, 2025 |
 Kilo Gateway | meta-llama/llama-guard-4-12b | 164K | — | 16K | $0.14 | $0.14 | — | — | — | — | — | No | No | No | Yes | Apr 29, 2025 |
 Nvidia | meta/llama-guard-4-12b | 164K | — | 16K | Free | Free | — | — | — | — | — | No | No | Unknown | Yes | Apr 29, 2025 |