How do you use Llama Guard 4 12B?

Llama Guard 4 12B can be called through OpenRouter's OpenAI-compatible API using the model ID meta-llama/llama-guard-4-12b. This page includes a ready-to-run curl example and the supported parameter list.

Is Llama Guard 4 12B free?

Llama Guard 4 12B is a paid model in the OpenRouter catalog, with separate input and output token pricing shown on this page.

Llama Guard 4 12B

All models

MetaLlama

Llama Guard 4 12B

Q: What is Llama Guard 4 12B?

Llama Guard 4 12B is an AI model from Meta in the Llama series. Agent Mag tracks its context window, pricing, modalities, and supported API parameters on this page.

164K context

$0.180/M input

$0.180/M output

Llama Guard 4 12B is an AI model from Meta built for agent workflows, with support for image, text input and text output. 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...

What is Llama Guard 4 12B?

Llama Guard 4 12B is an AI model from Meta that Agent Mag tracks for pricing, context window, modalities, benchmarks, and API compatibility. Builders can use this page to compare Llama Guard 4 12B against other models for agent workflows and production deployments.

Model ID

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...

Modalities

Input

imagetext

Output

text

Supported Parameters

frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstoptemperaturetop_ktop_p

More from Meta

Llama 4 Maverick

1.0M ctx$0.150/M

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

Llama 4 Scout

328K ctx$0.080/M

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...

Llama Guard 3 8B

131K ctx$0.480/M

Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification)...

Llama 3.3 70B Instruct

131K ctx$0.100/M

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

Stay in the know

Llama Guard 4 12B

What is Llama Guard 4 12B?

More from Meta

Related content