Meta: Llama Guard 4 12B
meta-llama/llama-guard-4-12b
JSONVision
Intelligence
—
Design Elo
—
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.180
92nd cheapest
Context
1.0M
16K max out
How it compares
Cheaper than72%
of all ranked models
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...
Providers & pricing (2)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfrabf16 | $0.180 | $0.180 | 164K | 98.3% |
| Together | $0.200 | $0.200 | 1.0M | 99.9% |
Specifications
Context window1.0M
Max output16K
Knowledge cutoffAug 2024
Input modalitiesimage, text
Output modalitiestext
Prompt caching—
Cache read price—
ModeratedNo
Open weightsmeta-llama/Llama-Guard-4-12B ↗
Llama Guard 4 12B FAQ
How much does Llama Guard 4 12B cost?
Llama Guard 4 12B costs $0.180 per million input tokens and $0.180 per million output tokens via OpenRouter, making it 92nd cheapest of 332 paid models.
What is Llama Guard 4 12B's context window?
Llama Guard 4 12B supports a 1.0M-token context window and can output up to 16K tokens. It accepts image, text input.
More from meta-llama
All Llama Guard 4 12B alternatives →Compare head-to-head
Meta: Llama Guard 4 12B vs Meta: Llama 4 MaverickMeta: Llama Guard 4 12B vs Meta: Llama 4 ScoutMeta: Llama Guard 4 12B vs Meta: Llama 3.3 70B InstructMeta: Llama Guard 4 12B vs Meta: Llama 3.2 1B InstructMeta: Llama Guard 4 12B vs Meta: Llama 3.2 3B InstructMeta: Llama Guard 4 12B vs Meta: Llama 3.1 70B Instruct