MMeta · Released Apr 30, 2025
Llama Guard 4 12B
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...
- Released
- Apr 30 2025
- Context window
- 164K 16K out
- Input / 1M tokens
- $0.18 from Free
- Output / 1M tokens
- $0.18 from Free
Where to run it
5 providers compared
Free to try on Nvidia — free endpoints are often limited-time and rate-limited. Cheapest: DeepInfra, Kilo Gateway at $0.14 / $0.14 per 1M input / output tokens — 47% less than the priciest option.
| Provider | Input | Output | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|
| Nvidiafree · may be limited-time · no tool calling | Free | Free | 164K | 16K | — | Free |
| DeepInfraBF16 · no tool calling | $0.14 | $0.14 | 164K | 147K | — | Cheapest |
| Kilo Gatewayno tool calling | $0.14 | $0.14 | 164K | 16K | — | Cheapest |
| DeepInfraBF16 · no tool calling | $0.18 | $0.18 | 164K | 16K | 99.3%24h | +25% |
| Hugging Faceno tool calling | $0.18 | $0.18 | 164K | 164K | — | +25% |
| Eden AIno tool calling | $0.18 | $0.18 | 164K | 164K | — | +25% |
| DeepInfrapriority · BF16 · no tool calling | $0.27 | $0.27 | 164K | 147K | 98.6%24h | +88% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Llama Guard 4 12B. Scores appear here automatically once it does.
Specs
Details
- Model ID
meta-llama/llama-guard-4-12b- Developer
- Meta
- Release date
- Apr 30, 2025 ·
- Context window
- 163,840 tokens
- Max output
- 16,384 tokens
- API price
- $0.18 / $0.18 per 1M input / output tokens
- Providers
- 5
- Input types
- image, text
- Reasoning
- No
- Tool calling
- No
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.