Atlas / Models / Meta / Meta: Llama Guard 4 12B

Meta: Llama Guard 4 12B✓ Catalog verified

meta-llama/llama-guard-4-12b

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 inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM—generating 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. Llama Guard 4 was aligned to safeguard against the standardized MLCommons hazards taxonomy and designed to support multimodal Llama 4 capabilities. Specifically, it combines features from previous Llama Guard models, providing content moderation for English and multiple supported languages, along with enhanced capabilities to handle mixed text-and-image prompts, including multiple images. Additionally, Llama Guard 4 is integrated into the Llama Moderations API, extending robust safety classification to text and images.

Input price
$0.18 /1M
Output price
$0.18 /1M
Context
164K
Modalities
imagetext
Released
Apr 30, 2025
Tool calling
Atlas signal
80/100
01

Overview

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 inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM—generating 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. Llama Guard 4 was aligned to safeguard against the standardized MLCommons hazards taxonomy and designed to support multimodal Llama 4 capabilities. Specifically, it combines features from previous Llama Guard models, providing content moderation for English and multiple supported languages, along with enhanced capabilities to handle mixed text-and-image prompts, including multiple images. Additionally, Llama Guard 4 is integrated into the Llama Moderations API, extending robust safety classification to text and images.

Access: available through the official Meta API. Context window: 164K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Aug 5, 2026
02

Specifications

API identifiermeta-llama/llama-guard-4-12b
ProviderMeta
Model typeMultimodal LLM
Context window164K catalog
Input modalitiesimage · text
Output modalitiestext
ReleasedApr 30, 2025
ModeratedNo
Architecture modalitytext+image->text
Supported parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstoptemperaturetop_ktop_p
Source: provider documentation + catalog feedMethodology →
03

Pricing

Live pricing components for meta-llama/llama-guard-4-12b as published in the catalog.

$0.18
Input /1M
$0.18
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$1.8e-7$0.18 / 1MPer input token
Completion tokens$1.8e-7$0.18 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$0.13Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual Understanding✓ SupportedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool CallingNot advertisedSupports tools / function calling
Self-Hosting✓ SupportedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

Meta: Llama Guard 4 12B
MMLU Signal (Reasoning)
79signal
Coding Signal (HumanEval proxy)
82signal
Math Signal (GSM8K proxy)
79signal
Science Signal (GPQA proxy)
79signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call Meta: Llama Guard 4 12B through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="meta-llama/llama-guard-4-12b",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does Meta: Llama Guard 4 12B cost?

$0.18 per 1M input tokens and $0.18 per 1M output tokens on the official Meta API.

What is the context window of Meta: Llama Guard 4 12B?

Meta: Llama Guard 4 12B supports up to 164K tokens of context.

Does Meta: Llama Guard 4 12B support tool / function calling?

Meta: Llama Guard 4 12B does not advertise first-class tool/function calling. Check vendor docs for the latest capabilities.

How do I access Meta: Llama Guard 4 12B?

Use the official Meta API with the model id `meta-llama/llama-guard-4-12b`. See the Quick start section above for code examples.