llama-guard-4-12b
Llama Guard 4 12B is a Meta content-safety classifier derived from Llama 4 Scout. It labels prompts and responses (text and images) as safe or unsafe and lists the violated categories — it is a moderation model, not a general assistant.
料金： 入力：100 万トークンあたり 43.2 クレジット（約 $0.22）、出力：100 万トークンあたり 43.2 クレジット（約 $0.22）。
今日はどんなお手伝いができますか？
このデモページにはクライアントの完全な記憶機能はありません。すべての機能をご利用いただくには、クライアントまたは CLI から接続してください。
Meta のほかの AI モデル
Llama Guard 4 12B API on ModelFold
Llama Guard 4 12B is a Meta content-safety classifier derived from Llama 4 Scout. It labels prompts and responses (text and images) as safe or unsafe and lists the violated categories — it is a moderation model, not a general assistant. Try Llama Guard 4 12B in the ModelFold Playground, then call it from your own code through an OpenAI-compatible chat completions API.
What Is the Llama Guard 4 12B API
Llama Guard 4 12B at a glance
Llama Guard 4 12B is a chat model from Meta. It accepts text and images as input and returns text, with a context window of up to 164K tokens.
Use it without hosting anything
On ModelFold you call Llama Guard 4 12B with a single API key — no model weights to download and no inference servers to run. The same key also works for the other chat, image, video and audio models on ModelFold.
Core Capabilities of Llama Guard 4 12B
Up to 164K tokens of context
Keep long conversations, large documents and sizeable code in a single request, so the model can reason over the full material instead of fragments.
Understands images
Besides text, Llama Guard 4 12B accepts images as input, so a single request can combine instructions with visual or other media.
How to Use Llama Guard 4 12B on ModelFold
- 1
Step 1: Try it in the Playground
Open the Playground at the top of this page, type a prompt and see how Llama Guard 4 12B responds before writing any code.
- 2
Step 2: Create an API key
Sign in to ModelFold and create an API key in the console. Keep it secret and send it as a Bearer token.
- 3
Step 3: Send a request
Call POST https://modelfold.ai/v1/chat/completions with "model": "llama-guard-4-12b" and your messages. Existing OpenAI-compatible SDKs work by changing the base URL and key.
- ✓
Step 4: Ship and monitor
Integrate the response into your product and check token usage and spend for every call in the console logs.
What You Can Build with Llama Guard 4 12B
Security analysis
Assist with code auditing, vulnerability triage and reviewing configurations as part of security workflows.
Screenshot and image understanding
Read screenshots, charts, diagrams and photos alongside text — for UI review, visual QA or turning images into structured data.
Enterprise workflows
Automate internal processes such as reporting, knowledge-base Q&A, ticket handling and document review.
Frequently Asked Questions
What is Llama Guard 4 12B?⌄
Llama Guard 4 12B is a Meta content-safety classifier derived from Llama 4 Scout. It labels prompts and responses (text and images) as safe or unsafe and lists the violated categories — it is a moderation model, not a general assistant.
Which inputs does Llama Guard 4 12B support?⌄
Llama Guard 4 12B accepts text and images and returns text. Through ModelFold you can send text and images (OpenAI-style image_url content); in the Playground you can also attach documents, which are converted to text.
How long is the context window of Llama Guard 4 12B?⌄
Up to 164K tokens, shared between your input and the model’s output.
Does Llama Guard 4 12B support function calling?⌄
Function calling is not listed for Llama Guard 4 12B; requests that include tools will be rejected. Use plain prompts or JSON output instead.
How is Llama Guard 4 12B billed on ModelFold?⌄
Pay as you go by tokens: input and output tokens are charged at the per-million-token prices shown on this page. There is no monthly fee, and failed requests are not charged.
How do I call Llama Guard 4 12B through the API?⌄
Send a POST request to https://modelfold.ai/v1/chat/completions with "model": "llama-guard-4-12b", using your ModelFold API key as the Bearer token.
| 入力 | 43.2 クレジット 1M tokens≈ $0.22 |
| 出力 | 43.2 クレジット 1M tokens≈ $0.22 |
トークン単位で課金し、入力と出力は別料金です。思考トークンは出力に含まれます。Playground でも同じ計算を使います。
API ドキュメントを見る →AI Agents · Claude Code / Cursor / Trae →curl https://modelfold.ai/v1/chat/completions \
-H "Authorization: Bearer $MODELFOLD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"llama-guard-4-12b","messages":[{"role":"user","content":"Hello"}]}'