S CostSaver
Sign in

Mercury 2

LLM

by inception · inception-mercury-2-20260304

Context window

128K

Max output

50K

Providers

1

Best input

$0.25

About this model

Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...

Providers & prices

Provider Input $/MTok Output $/MTok Context
I Inception $0.25 $0.75 128K