inception
Inception: Mercury
inception/mercury
For $1, you can send approximately:
~143messages
How do we get this number?
One message = ~7,000 input tokens + ~7,000 output tokens
Input cost per message7,000 x $0.25/M = $0.001750
Output cost per message7,000 x $0.75/M = $0.005250
Total cost per message$0.007000
Messages for $1142.86
Context window
128k
tokens
Max response
32k
tokens
Input price
$0.25
per million tokens
Output price
$0.75
per million tokens
Modalities
Input:textOutput:text
Description
Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like GPT-4.1 Nano and Claude...