Llama Guard 4 12B Pricing
FastMeta · 164K tokens context
Llama Guard 4 12B from Meta costs $0.180 per 1 million input tokens and $0.180 per 1 million output tokens as of June 2026 (live OpenRouter data). The model supports a 163,840-token context window (approximately 122,880 words) with a 16K-token maximum output. A typical 1,000-token request costs $0.0002 in input charges; a 10,000-token request costs $0.0018.
| Input price | $0.180 / 1M tokens |
|---|---|
| Output price | $0.180 / 1M tokens |
| Output / input ratio | 1.0× |
| Context window | 163,840 tokens (~122,880 words) |
| Maximum output | 16,384 tokens |
| Cost per 1K tokens (input) | $0.0002 |
| Tier | Fast |
| Last verified |
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 Price
$0.180
per 1 million tokens
Output Price
$0.180
per 1 million tokens
Context Window
164K tokens
max 16K output
Cost Examples
| Request Type | Tokens | Input Cost | Output Cost |
|---|---|---|---|
| 1,000 word article | 1,333 | $0.00024 | $0.000072 |
| 10-page document (2,500 words) | 3,333 | $0.0006 | $0.00018 |
| 1,000 lines of code | 5,000 | $0.0009 | $0.00027 |
| 100K token document | 100,000 | $0.018 | $0.0054 |
Output cost estimated at 30% of input token count. Use the calculator for exact figures.
Strengths
- ✓Extremely cheap at $0.180/1M input tokens
- ✓Low latency for high-throughput workloads
- ✓Multimodal: understands images as well as text
Limitations
- –Less capable than flagship models on complex reasoning
- –Quality and availability can vary by hosting provider
Best Use Cases
Calculate Llama Guard 4 12B Costs
Use the TokenRate calculator to convert any budget, token count, or text into exact Llama Guard 4 12B costs — and compare across all models.
Open Calculator →Llama Guard 4 12B — FAQ
Related Models
Related Guides