mercury-2

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...

Modalities

Input

text

Output

text

Pricing

Cost per 1 million tokens

Input

$0.3

Output

$0.9

Model Specs

Context Window

128,000

Max Output

50,000

Release Date

2026-03-04

Knowledge Cutoff

Capabilities

Reasoning

Tool Calling

Vision

Last Updated: 2026-03-04

Provider: