Inception: Mercury 2

by Inception Fast Reasoning

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...

Choose a model to compare against Mercury 2

Specifications

Specifications for Mercury 2
AttributeValue
Lab Inception
Tags Fast Reasoning
Release Date 2026-03
Context Window 128,000 tokens
Input Price / 1M $0.25
Output Price / 1M $0.75
Input Modalities Text
Output Modalities Text

Strengths

  • First reasoning diffusion LLM parallel token generation
  • Extremely fast inference via parallel refinement
  • Novel architecture for reasoning tasks
  • Competitive pricing

Weaknesses

  • Experimental architecture with unknown edge cases
  • Limited track record
  • Narrower general knowledge vs traditional LLMs

Best For

  • Latency-critical reasoning
  • High-throughput classification
  • Experimental LLM workflows

In Depth: Mercury 2

Summary

Mercury 2 is an AI model from Inception.

Released 2026-03. It currently appears in the Overall category on LMRank. It supports Text input and produces Text output, with a context window of 128,000 tokens. Input pricing is $0.25 per 1M tokens and output is $0.75 per 1M tokens on OpenRouter.

Sources & Further Reading

Related Models