Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
Llama Guard 4 12B - Model - OpenSmartRoute
Modelv1.0.0
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...
Reference model card from the OpenRouter listing - model meta-llama/llama-guard-4-12b. Prices are per million tokens as listed; ratings and installs below are from this marketplace.
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...
Facts
Vendor
Meta
Context window
163,840 tokens
Max output
16,384 tokens
Input price
$0.18 / 1M tokens
Output price
$0.18 / 1M tokens
Input
image, text
Output
text
Tool calling
no
Structured outputs
no
Reasoning
no
Open weights
meta-llama/Llama-Guard-4-12B
Endpoint: https://openrouter.ai/api/v1 (OpenAI-compatible), model meta-llama/llama-guard-4-12b
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configure
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
# or pin it on the OpenAI-compatible endpoint: {"model": "model-meta-llama-llama-guard-4-12b", ...}
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
model-meta-llama-llama-guard-4-12b.ocm.jsonjson
{
"ocm": "1",
"id": "model-meta-llama-llama-guard-4-12b",
"kind": "llm",
"name": "Llama Guard 4 12B",
"description": "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...",
"publisher": "Meta",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"llm",
"meta-llama",
"openrouter",
"open-weights",
"image",
"models"
],
"languages": [
"en"
],
"modalities": [
"image",
"text"
],
"supports_tools": false,
"supports_streaming": true,
"context_window": 163840
},
"quality_prior": 0.6,
"examples": [
"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..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1745975193",
"url": "https://openrouter.ai/meta-llama/llama-guard-4-12b",
"key": "meta-llama/llama-guard-4-12b",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "meta-llama/llama-guard-4-12b",
"pricing": {
"input_usd_per_1m": 0.18,
"output_usd_per_1m": 0.18
},
"max_output_tokens": 16384,
"output_modalities": [
"text"
],
"hugging_face_id": "meta-llama/Llama-Guard-4-12B",
"created": 1745975193,
"benchmarks": {
"hub_downloads": 46743,
"hub_downloads_total": 1519157,
"hub_likes": 128,
"hub_trending": 4
}
},
"cost": {
"usd_per_1k_tokens": 0.00018
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
}
Fetch it by URL: GET /api/v1/registry/model-meta-llama-llama-guard-4-12b/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
