Llama Guard 3 8B
Llama Guard 3 8B (meta-llama, 2025) is an chat model. 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)...
by meta-llama · 131K token context window
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Llama Guard 3 8B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your meta-llama API key. osFoundry discovers Llama Guard 3 8B automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
Run Llama Guard 3 8B yourself
Llama Guard 3 8B is also available as open weights — self-host it for full data control and no per-token cost. See that page for GPU requirements and a cost comparison against API pricing.
Llama Guard 3 8B vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| Llama Guard 3 8B | meta-llama | — | 131K | $ 0.480 /1M | API only |
| Saba | Mistral | — | 33K | $ 0.200 /1M | API only |
| o3 Mini High | OpenAI | — | 200K | $ 1.10 /1M | API only |
| Sonar Deep Research | Perplexity | — | 128K | $ 2.00 /1M | API only |
Licence
Hosted — usage subject to provider terms — Hosted-only model — usage governed by the provider's API terms. Bring your own provider key.
No weights distributed; usage subject to provider terms.
Frequently asked about Llama Guard 3 8B
How much does Llama Guard 3 8B cost?
Llama Guard 3 8B is metered at $ 0.480 /1M for input, and $ 0.030 /1M for output. Bring your own meta-llama API key — osFoundry passes through provider pricing without markup.
Can I use Llama Guard 3 8B commercially?
Commercial use is allowed with conditions. Hosted-only model — usage governed by the provider's API terms. Bring your own provider key. No weights distributed; usage subject to provider terms.
What is the context window of Llama Guard 3 8B?
Llama Guard 3 8B supports a 131K token context window.
Can I run Llama Guard 3 8B locally?
No — Llama Guard 3 8B is hosted only and accessed via the meta-llama API. An open-weights equivalent is available to self-host — see the cross-link above.
What is Llama Guard 3 8B best at?
Llama Guard 3 8B is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Llama Guard 3 8B in osFoundry?
Paste your meta-llama API key in the key dialog (or deploy the open weights for self-hostable models), assign Llama Guard 3 8B to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by meta-llama on February 12, 2025. Source: https://openrouter.ai/meta-llama/llama-guard-3-8b