Meta: Llama 4 Scout
meta-llama/llama-4-scout
For $1, you can send approximately:
~186messages
How do we get this number?
One message = ~7,000 input tokens + ~7,000 output tokens
Input cost per message7,000 x $0.18/M = $0.001260
Output cost per message7,000 x $0.59/M = $0.004130
Total cost per message$0.005390
Messages for $1185.53
Context window
1.3M
tokens
Max response
118k
tokens
Input price
$0.18
per million tokens
Output price
$0.59
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...