inception
Inception: Mercury 2.5
inception/mercury-2.5
For $1, you can send approximately:
~752messages
How do we get this number?
One message = ~7,000 input tokens + ~7,000 output tokens
Input cost per message7,000 x $0.04/M = $0.000280
Output cost per message7,000 x $0.15/M = $0.001050
Total cost per message$0.001330
Messages for $1751.88
Context window
260k
tokens
Max response
66k
tokens
Input price
$0.04
per million tokens
Output price
$0.15
per million tokens
Modalities
Input:textOutput:text
Description
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...