/ Models

Language models

Meta: 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...

Maker
Meta-llama
Context window
1M
Max output
16K
Input / 1M
$0.18
Output / 1M
$0.18
1M in + 1M out
$0.36

Everything else

Max output16K
Input / 1M$0.18
Output / 1M$0.18
Cache read / 1M
Cache write / 1M
1M in + 1M out$0.36
Takesimage, text
Returnstext
Toolsno
Reasoningno
Open weightsyes
Released2025-04-30
Knowledge cutoff2024-08-31
Retires
Catalog idmeta-llama/llama-guard-4-12b

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models