LlamaGuard 2 8B

About LlamaGuard 2 8B

This safeguard model has 8B parameters and is based on the Llama 3 family. Just like is predecessor, [LlamaGuard 1](https://huggingface.co/meta-llama/LlamaGuard-7b), 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. To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Meta Model Lineup

Compare all models from Meta to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Molmo2 8B (free)

Allen AI

Input: $0.20

Output: $0.20

Context: 37k

Mistral Small Creative

Mistral

Input: $0.10

Output: $0.30

Context: 33k

Mistral 7B Instruct v0.3

Mistral

Input: $0.20

Output: $0.20

Context: 33k

Mistral 7B Instruct v0.2

Mistral

Input: $0.20

Output: $0.20

Context: 33k

💡 Cheaper Alternatives

Same Brand (Meta)

Cross Brand

🚀 Quick Start

Get started with LlamaGuard 2 8B API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="meta-llama/llama-guard-2-8b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision