Model dossier

Inception: Mercury 2

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...

ProviderInception Start comparison

Context128,000

Max output50,000

Pricing viewTVP price

Identity

Inception: Mercury 2

Model ID: inception/mercury-2
Canonical slug: inception/mercury-2-20260304
Knowledge cutoff: n/a
Created: 3/4/2026

Capabilities

texttoolsstructured

Modalities

text->texttext

Capacity

Context128,000

Max output50,000

TokenizerOther