Mercury 2

Inception · inception/mercury-2

← Back to leaderboard

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...

texttext->text

Context

Max context: 128000
Max output: 50000

Pricing

Input / 1M: 0.25
Output / 1M: 0.75
Blend / 1M: 0.50

Quality

Quality index:

Provider

Provider: Inception
Moderated: no