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... First reasoning diffusion LLM parallel token generation Extremely fast inference via parallel refinement Novel architecture for reasoning tasks Competitive pricing Experimental architecture with unknown edge cases Limited track record Narrower general knowledge vs traditional LLMs Latency-critical reasoning High-throughput classification Experimental LLM workflows
Specifications
| Lab | Inception |
|---|---|
| Context window | 128,000 |
| Input price | $0.25/1M |
| Output price | $0.75/1M |
| Release | 2026-03-01 00:00:00 |
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 2026-03-01 00:00:00. It currently appears in the Overall category on LMRank. It supports Text input and produces Text output, with a context window of 128K tokens. Input pricing is $0.25 per 1M tokens and output is $0.75 per 1M tokens on OpenRouter.