AI Observatory / Model Radar Meta / meta-llama/llama-guard-3-8b

Llama Guard 3 8B

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)...

131,072 Context
N/A Max output
$0.48 / 1M Prompt price
2025-02-12 Created
01 / Snapshot

Pricing, context, modalities, and parameters.

Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.

Provider Meta Input modalities text
Output modalities text Prompt price $0.48 / 1M
Completion price $0.03 / 1M Request price N/A
Context length 131,072 Max completion tokens N/A
Supported parameters frequency_penalty, max_tokens, presence_penalty, repetition_penalty, seed, temperature, top_k, top_p
Best for meta-llama/llama-guard-3-8b

Llama Guard 3 8B

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)...

High-volume usage low-cost
03 / Colophon

Routes and exits.

Each model page stays simple: overview, compare, related models, then back to the public hub.