Back to comparator
meta-llama

Meta: Llama 4 Scout

meta-llama/llama-4-scout

For $1, you can send approximately:
~376messages

How do we get this number?

One message = ~7,000 input tokens + ~7,000 output tokens
Input cost per message7,000 x $0.08/M = $0.000560
Output cost per message7,000 x $0.30/M = $0.002100
Total cost per message$0.002660
Messages for $1375.94
Context window
328k
tokens
Max response
16k
tokens
Input price
$0.08
per million tokens
Output price
$0.30
per million tokens

Modalities

Input:textInput:imageOutput:text

Description

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...