All models
Meta
Llama Guard 4 12B fastruns locally
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...
Input / 1M
$0.18
USD per million tokens
Output / 1M
$0.18
USD per million tokens
Est. cost / token
$0.00000018
$0.18 per 1M, 3:1 mix
Context window
164K
max output 16K
Major features
VisionOpen weights
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning2
- math2
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision3
- long context3
- agentic1
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 7.1 GB |
| Q3_K_M | fair | 8 GB |
| Q4_K_Mrecommended | good | 9.6 GB |
| Q5_K_M | very good | 10.8 GB |
| Q6_K | excellent | 12.2 GB |
| Q8_0 | near-lossless | 15.3 GB |
| F16 | lossless | 27.1 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.18 | $0.18 | — | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.18
- Output
- $0.18
- Blended (3:1)
- $0.18
Details
- Company
- Meta
- Version
- 4
- Family
- Llama
- Released
- 2025-04-30
- Parameters
- 12B
- Max output
- 16K
- Open weights
- Yes
- Inputs
- image, text
- Last synced
- 32 min ago