llama-guard-4-12b - API in Egypt, billed in EGP

Live
Meta

Llama Guard 4 is a natively multimodal safety classifier with 12 billion parameters trained jointly on text and multiple images. Llama Guard 4 is a dense architecture pruned from the Llama 4 Scout pre-trained model and 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 itself 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.

Modality

Chat

Context window

164K tokens

Max output

16K tokens

Region

US

Weights

Open weights

Published

Jul 14, 2026

Pricing

Input

10.30

EGP per 1M tokens

Output

10.30

EGP per 1M tokens

Monthly cost example

669.24 EGP

Illustrative estimate: 50M input + 15M output tokens per month at this model's catalog rates.

Use it via the API

llama-guard-4-12b works with any OpenAI-compatible SDK — point the base URL at https://backend.sovereigneg.com/v1 and use your SovereignEG API key.

Run inference

OpenAI-compatible — POST /v1/chat/completions — drop-in for any OpenAI SDK.

from openai import OpenAI

client = OpenAI(
    base_url="https://backend.sovereigneg.com/v1",
    api_key="YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="llama-guard-4-12b",
    messages=[
        {"role": "user", "content": "What are some fun things to do in Cairo?"}
    ],
)

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

Frequently asked questions

How much does llama-guard-4-12b cost?

10.30 EGP per 1M input tokens; 10.30 EGP per 1M output tokens. Billing is metered per token in Egyptian pounds (EGP), with no minimum commitment.

What is the context window of llama-guard-4-12b?

llama-guard-4-12b supports a context window of 163,840 tokens (164K), with up to 16,384 output tokens per response.

Where is llama-guard-4-12b hosted?

llama-guard-4-12b is served from US (US-hosted inference).

Is llama-guard-4-12b an open-weights model?

Yes — llama-guard-4-12b is an open-weights model. You call it through the SovereignEG API like any other catalog model, with per-token EGP billing.

How do I use llama-guard-4-12b via the API?

llama-guard-4-12b is available through the OpenAI-compatible SovereignEG API: point your SDK's base URL at https://backend.sovereigneg.com/v1 and call /v1/chat/completions with model "llama-guard-4-12b" and your API key.