AgentHub

Inception: Mercury 2

Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating token…

Live
Open / InstallLast updated July 27, 2026

Description

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...

Author

inception

Platform

api

Pricing model

paid

Categories

Research

Tags

openrouter
llm
inception
text

Capabilities

  • 128,000 token context