Mercury 2
by Inception
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 token
Models
Mercury 2
Added 10 July 2026
Overview
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...
How to use / API access
Call via OpenRouter with model id `inception/mercury-2`.
- openrouter ·
inception/mercury-2Docs
OpenRouter id: inception/mercury-2
Benchmarks
- Coding Index (artificial-analysis) : 31.1 index
- Agentic Index (artificial-analysis) : 1.6 index
- Design Arena 3d (other) : 993 elo · #106
- Design Arena asciiart (other) : 1001 elo · #68
- Design Arena codecategories (other) : 1023 elo · #111
- Design Arena dataviz (other) : 1015 elo · #107
Notes
Mercury 2 is listed in the EDNA Models directory from the OpenRouter catalogue.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.