Meta: Llama 4 Scout
meta-llama/llama-4-scout
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
Modalities
TextImage
In / out price
₩176 / ₩527
1M
Context
1.31M
Released
Apr 6, 2025
Pricing
Prices are quoted in Korean won. Changes to the exchange rate or margin show up immediately.
| Input (prompt) | ₩176 / 1M |
| Output (completion) | ₩527 / 1M |
| Cache read | ₩18 / 1M |
| Cache write | — |
1,000 input tokens plus 1,000 output tokens costs about ₩0.702.