Meta: Llama 3.1 8B Instruct
meta-llama/llama-3.1-8b-instruct
For $1, you can send approximately:
~2.9kmessages
How do we get this number?
One message = ~7,000 input tokens + ~7,000 output tokens
Input cost per message7,000 x $0.02/M = $0.000140
Output cost per message7,000 x $0.03/M = $0.000210
Total cost per message$0.000350
Messages for $12857.14
Context window
131k
tokens
Max response
16k
tokens
Input price
$0.02
per million tokens
Output price
$0.03
per million tokens
Modalities
Input:textOutput:text
Description
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...