models/Meta/Llama-Guard-3-8b

Llama-Guard-3-8b

moderation

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.

slug · meta/llama-guard-3-8bprovider · Metafamily · Llama Guardreleased · 2025-01-22

Quickstart

POST /v1/chat/completions  model: "meta/llama-guard-3-8b"

Capabilities

Streaming
CONTEXT
131,072 tok
MAX OUTPUT
4,096 tok

Strengths

  • Policy-aware
  • Fast
  • Open-weight

Use cases

Input/output moderationAbuse detection

Pricing

Input$0.480 / 1M tokens
Output$0.030 / 1M tokens
You pay pass-through · 5% applied at credit top-up, not per-call.
Try in playground →CompareAPI referenceSee usage ranking →

Collections

More text models →More from MetaFrontier models →Free-tier models →
API schema

Call Llama-Guard-3-8b from any OpenAI SDK

POST https://api.aigateway.sh/v1/chat/completions·Content-Type: application/json·Auth: Bearer sk-aig-...

Request body

json
{
  "model": "meta/llama-guard-3-8b",
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user",   "content": "Hello!" }
  ],
  "temperature": 0.7,
  "top_p": 0.95,
  "max_tokens": 1024,
  "stream": false

}

Response

json
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1776947082,
  "model": "meta/llama-guard-3-8b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 12,
    "total_tokens": 36
  }
}

Streaming (SSE) — set "stream": true

// 1. Role announcement (first chunk):
data: {"choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}

// 2. Content chunks (final answer):
data: {"choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}
data: {"choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}

// Finish chunk:
data: {"choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

// Terminator:
data: [DONE]

Quickstart

# pip install aigateway-py openai
# aigateway-py adds sub-accounts, evals, replays, jobs, webhook verify.
# openai SDK covers chat — drop-in per our SDK's own guidance.
from openai import OpenAI

client = OpenAI(
    base_url="https://api.aigateway.sh/v1",
    api_key="sk-aig-...",
)

stream = client.chat.completions.create(
    model="meta/llama-guard-3-8b",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

Errors

401authentication_errorInvalid or missing API key
402insufficient_creditsWallet empty (PAYG only)
404not_foundUnknown model or endpoint
429rate_limit_errorOver per-minute limit — see Retry-After header
500server_errorUpstream provider failed (retryable)
503service_unavailableUpstream saturated (retryable)
Full docs →API reference →OpenAPI spec →llms.txt →