Meta: Llama 4 Scout
6.8 / 10
1.3M context
Proprietary
About this model
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...
Benchmark Scores
MBPP
67.8
Technical Specs
- Architecture: text+image->text
- Context Window: 1,310,720 tokens
- Input Modalities: text
Hardware Requirements
- API-only (no local hardware needed)
Pricing
| Input | Output | Currency |
|---|---|---|
| 0.11 / 1M tokens | 0.33999999999999997 / 1M tokens | USD |