meta-llama Open weights Vision

Llama Guard 4 12B pricing & benchmarks

Released Apr 30, 2025 · served by 2 providers

Input / 1M tokens$0.180
Output / 1M tokens$0.180
Context window1.0M
Cached input
1M in + 300K out$0.23

What Llama Guard 4 12B is

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 and prices for Llama Guard 4 12B

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
DeepInfracheapest $0.180 $0.180 164K bf16 99.4%
Together $0.200 $0.200 1.0M 99.0%

FAQ

How much does the Llama Guard 4 12B API cost?

$0.180 per 1M input tokens and $0.180 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.23.

Is Llama Guard 4 12B free?

No. It is a paid model starting at $0.180 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Llama Guard 4 12B?

DeepInfra at $0.180 input / $0.180 output per 1M tokens (bf16 quantization).

Can I self-host Llama Guard 4 12B?

Yes — weights are published as meta-llama/Llama-Guard-4-12B on Hugging Face, so you can run it on your own hardware.