Verified record · from the answer index

Inception: Mercury 2

modeltested · static-verifiedscore 20/100signed passport ✓published 231d ago · verified 2026-10-20

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...

Declared tools (3)

text->texttool-callingstructured-outputs

model:openrouter:inception/mercury-2