What does Llama Guard 4 12B do?

It classifies content safety, and because it is multimodal it can inspect both text and image in the input and decide whether they are safe or unsafe.

How do I reach Llama Guard 4 12B from inside Iran?

Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.

Is Llama Guard 4 12B compatible with OpenAI-style code?

Yes. Hormouz exposes an OpenAI-compatible API. Point your base URL at Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.

Meta: Llama Guard 4 12B: AI model

Llama Guard 4 12B is Meta's multimodal content-safety model, derived from Llama 4 Scout, that classifies text and image as safe or unsafe. Reachable from inside Iran through Hormouz.

Context window:: 163,840 tokens
Input:: $0.18/1M tokens
Output:: $0.18/1M tokens
Type:: text, image

Vision
Streaming
Long context

Llama Guard 4 12B is a model fine-tuned from Llama 4 Scout for content-safety classification. Unlike earlier versions this one is multimodal and can inspect both text and image in the input.

It behaves like a language model: it generates text output indicating whether a prompt or response is safe or unsafe, and when unsafe it lists the violated content categories. Llama Guard 4 is aligned to the standardized MLCommons hazards taxonomy.

Pricing is usage-based: $0.20 per million input tokens and $0.20 per million output tokens. Llama Guard 4 12B is served through Hormouz behind an OpenAI-compatible API, and Hormouz provides stable access to it from inside Iran.

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-guard-4-12b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

Vendor	Meta
Type	Text, Image
Context window	163,840 tokens
Pricing	$0.18/M in · $0.18/M out
API	Chat Completions
Capabilities	Streaming · Vision

Code example

cURL

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-guard-4-12b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Python

from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="meta-llama/llama-guard-4-12b",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

JavaScript

import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "meta-llama/llama-guard-4-12b",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Meta: Llama Guard 4 12B API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches Meta: Llama Guard 4 12B and 600+ other models, and you pay only for what you use.
No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.

Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

What does Llama Guard 4 12B do?: It classifies content safety, and because it is multimodal it can inspect both text and image in the input and decide whether they are safe or unsafe.
How much does Llama Guard 4 12B cost?: Billing is usage-based: $0.20 per million input tokens and $0.20 per million output tokens.
How do I reach Llama Guard 4 12B from inside Iran?: Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Is Llama Guard 4 12B compatible with OpenAI-style code?: Yes. Hormouz exposes an OpenAI-compatible API. Point your base URL at Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.

Updated 2026-10-13