TokenCenter
← Back to Models
MetaOfficial

Meta: 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...

Pricing

Input
$0.08/1M tokens
Output
$0.30/1M tokens

Capabilities

Context Window328K tokens
Max Output16K tokens
SpeedMedium
Release2025-04
Vision
Tool Use
API Access
Local / Open

API Access

Official Links

Compare Meta: Llama 4 Scout

See how it stacks up side by side.

Compare Models →