Llama Guard 4 12B
by Meta · meta-llama/llama-guard-4-12b · #58 cheapest of 325 paid models
Prices updated Jul 22, 2026, 2:26 AM UTC · refreshed hourly
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...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.18
per 1M tokens
Output
$0.18
per 1M tokens
Blended (3:1)
$0.18
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Llama Guard 4 12B (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.18 | $0.0185 | — |
| 50% | $0.18 | $0.0185 | −0% |
| 90% | $0.18 | $0.0185 | −0% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.000144 | $0.144 |
| Document summary | 8,000 | 1,000 | $0.00162 | $1.62 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.00576 | $5.76 |
| Long-context analysis | 150,000 | 5,000 | $0.0279 | $27.90 |
Specs
Context window
1.05M
tokens
Max output
16K
tokens
Input modalities
image, text
Tokenizer
Other