Skip to content

Meta · Moderation

Llama Guard 4 12B

Meta 🇺🇸ModerationLlama familyOpen weights. One of its sources says the weights are publicly available.
From Fastrouter's listing:
Llama Guard 4 is a natively multimodal 12B safety classifier for classifying prompts and responses as safe or unsafe.
Max context
164K
Listings
17
Providers
13

Evidence and sources

🤗 meta-llama/Llama-Guard-4-12BFair value (50.2). Costs per task about what its benchmark results predict. From 1 benchmark with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 23 Apr 2025 Training-data cutoff, as its sources state it Maker HQ: US (according to Meta's own website)
All rankings: #289 on OpenRouter this week #291 on OpenRouter today #310 on OpenRouter this monthSources: DeepInfra data, flex.ai API data, Models.dev data, OpenRouter data docs, FastRouter data, Hugging FacePrimary data from DeepInfra from flex.ai API: hugging face id from Models.dev: weights availability from OpenRouter: knowledge cutoff from FastRouter: description from Hugging Face: release date

Input & output

as stated by the model's providers
Text
Images
Text

Capabilities

Supported operations and provider-stated features

VisionStructured output

Listings

 Kilometa-llama/llama-guard-4-12bSources: Kilo AI Gateway data, Models.dev data164K$0.144$0.144
 OpenRouterInference by DeepInframeta-llama/llama-guard-4-12b · bf16/flex · bf16Source: OpenRouter data docs164K$0.144$0.144
 Eden AIInference by DeepInfradeepinfra/meta-llama/Llama-Guard-4-12BSource: Models.dev data164K$0.18$0.18
 Fastroutermeta-llama/llama-guard-4-12bSource: FastRouter data164K$0.18$0.18
 Hugging FaceInference by DeepInframeta-llama/Llama-Guard-4-12BSource: Hugging Face Inference Providers data164K$0.18$0.18
 Wavespeedmeta-llama/llama-guard-4-12bSource: WaveSpeed AI data164K$0.18$0.18
 DeepInframeta-llama/Llama-Guard-4-12BSources: DeepInfra data, LiteLLM data, Models.dev data164K$0.18$0.18
 FlexaiRegions: 🇪🇺 euLlama-Guard-4-12BSources: flex.ai API data, flex.ai Pricing16K$0.18cache read $0.027$0.18
 Replicatereplicate/meta/llama-guard-4-12bSource: LiteLLM dataNot published by the provider$0.20$0.20
 Groqmeta-llama/llama-guard-4-12bSource: GenAI Prices data131K$0.20$0.20
Show all 14 listings

Showing 10 of 14: the cheapest per 1M input tokens from each provider.

3 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Reasoning

Data credits: SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence)

Also known as: deepinfra/meta-llama/llama-guard-4-12b, llama-guard-4, meta-llama/llama-guard-4-12b, meta/llama-guard-4-12b, nvidia_nim/meta/llama-guard-4-12b, replicate/meta/llama-guard-4-12b

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works