Skip to content
LLMs
Meta Llama logo

Meta: Llama Guard 4 12B

by Meta Llama

Meta: Llama Guard 4 12B is a large language model from Meta Llama. It costs $0.180 per million input tokens and $0.180 per million output tokens. Its context window is 164K tokens.

Structured outputOpen weightsimage input
Input / 1M tokens
$0.180
Output / 1M tokens
$0.180
Cached input / 1M
-

Not supported

Context window
164K

tokens

Who serves it cheapest

1 hosts serve Llama Guard 4 12B. Same weights, same API - the price difference is pure margin and routing.

Providers serving Meta: Llama Guard 4 12B, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
DeepInfraCheapestbf16$0.180$0.180164K-100.0%

About 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...

Specifications

Meta: Llama Guard 4 12B specifications
Model IDmeta-llama/llama-guard-4-12b
ProviderMeta Llama
Context window164K tokens
Max output16K tokens
Input modalitiesimage, text
Output modalitiestext
Knowledge cutoff2024-08-31
Open weightsYes - meta-llama/Llama-Guard-4-12B
ReleasedApril 30, 2025

Cheaper alternatives

Models that cost less than Llama Guard 4 12B while keeping at least half its context window and every input modality it supports.

Frequently asked

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

$0.180 per million input tokens and $0.180 per million output tokens.

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

164K tokens, with up to 16K tokens of output per request.