Inception: Mercury 2

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...

Modalities
Text
In / out price
₩439 / ₩1,316
1M
Context
128K
Released
Mar 4, 2026

Pricing

Prices are quoted in Korean won. Changes to the exchange rate or margin show up immediately.

Input (prompt)₩439 / 1M
Output (completion)₩1,316 / 1M
Cache read₩44 / 1M
Cache write

1,000 input tokens plus 1,000 output tokens costs about ₩1.76.