openai
OpenAI: GPT-3.5 Turbo (older v0613)
openai/gpt-3.5-turbo-0613
For $1, you can send approximately:
~47.6messages
How do we get this number?
One message = ~7,000 input tokens + ~7,000 output tokens
Input cost per message7,000 x $1.00/M = $0.007000
Output cost per message7,000 x $2.00/M = $0.014000
Total cost per message$0.021000
Messages for $147.62
Context window
4k
tokens
Max response
4k
tokens
Input price
$1.00
per million tokens
Output price
$2.00
per million tokens
Modalities
Input:textOutput:text
Description
GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.