by Meta AI

Llama Guard 4 12B.

multimodal open weights laptop+ 12B params 164K ctx
Cheapest input
$0.18/M
on DeepInfra
Cheapest output
$0.18/M
on DeepInfra
Smallest GPU
1× Nvidia GeForce RTX 3050
$0.022/hr

Llama Guard 4 12B is Meta's 12B safety classifier for text and multi-image prompts and responses, returning safe or unsafe plus the hazard categories broken.

Smallest GPU to run it See all quantisations →

1× Nvidia GeForce RTX 3050 · $0.022/hr.

Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
DeepInfra hosted inference $0.18 $0.18 Launch ↗
OpenRouter api aggregator $0.18 $0.18 Launch ↗
Sources

Official references.

FAQ

Frequently asked.

How do I run Llama Guard 4 12B?
Llama Guard 4 12B is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access Llama Guard 4 12B?
Llama Guard 4 12B is available via DeepInfra, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Llama Guard 4 12B?
API pricing starts at $0.18/M input tokens and $0.18/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Llama Guard 4 12B open-source or proprietary?
Llama Guard 4 12B is open-weight under the llama4 license. You can download and self-host it.