Back to Models

Meta: Llama 4 Scout

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

Input

textimage

Output

text
Pricing
Cost per 1 million tokens
Input
$0.096
Output
$0.36
Model Specs
Context Window
327,680
Max Output
16,384
Release Date
2025-04-05
Knowledge Cutoff
Capabilities
Reasoning
Tool Calling
Vision

Last Updated: 2025-04-05

Provider: