Llama Guard 3 8B (Cloudflare Workers AI)

Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM – it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.

Provider: All Meta models | Cloudflare Workers AI

API Endpoint

https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1/chat/completions

Quick Start (Python)

Install: pip install openai

import os

from openai import OpenAI

account_id = os.environ["CLOUDFLARE_ACCOUNT_ID"]

client = OpenAI(
    api_key=os.environ["CLOUDFLARE_API_TOKEN"],
    base_url=f"https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1",
)

response = client.chat.completions.create(
    model="@cf/meta/llama-guard-3-8b",
    messages=[
        {"role": "user", "content": "Hello, how are you?"},
    ],
    max_tokens=1024,
)

print(response.choices[0].message.content)

Additional examples: Basic invoke, REST API (any task)

Supported Parameters

Parameter	Type	Description
max_tokens	integer	Maximum tokens to generate. (≥1)
temperature	float	Controls randomness. Supported range varies by model. (≥0)
stream	boolean	Stream response chunks as they are generated. Default: false.

Feature Guides

OpenAI Compatibility

Call text generation and embedding models with OpenAI-compatible client libraries using the account-scoped Workers AI base URL.

Documentation

REST API

Run any Workers AI model, including image, speech, and embedding models, through the account-scoped /ai/run endpoint.

Documentation

Model Catalog

List available models, tasks, and per-model properties with the Workers AI models search API.

Documentation