Meta: LlamaGuard 2 8B
Review
LlamaGuard 2 8B is a specialised safety-classification model from Meta with no general benchmark data; it serves a narrow moderation use case and is not suitable for general business content or coding tasks.
Assessment date: April 16, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
Performance Profile
This safeguard model has 8B parameters and is based on the Llama 3 family. Just like is predecessor, LlamaGuard 1, it can do both prompt and response classification. LlamaGuard 2 acts as a normal LLM would, generating text that indicates whether the given input/output is safe/unsafe. If deemed unsafe, it will also share the content categories violated. For best results, please use raw prompt input or the /completions endpoint, instead of the chat API. It has demonstrated strong performance compared to leading closed-source models in human evaluations. Usage of this model is subject to Meta's Acceptable Use Policy.
Architecture
| Modality | Text → Text |
| Tokenizer | Llama3 |
| Instruct Type | none |
| Parameters | 8B |
How does Meta: LlamaGuard 2 8B stack up?
Compare side-by-side with other legacy models.
Model Information
| OpenRouter ID |
meta-llama/llama-guard-2-8b
|
| Provider | meta-llama |
| Release Date | May 13, 2024 |
| Context Length | 8,192 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.20 | $0.000200 |
| Output | $0.20 | $0.000200 |
