Inception · inception/mercury-2
mercury-2
Budget Everyday 128k context Hermes LimitedMercury 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...
Input / M
$0.250
Output / M
$0.750
Value score
86.39
30d price Δ
0%
Reasoning (AA)
—
Coding (AA)
31.1
Tool / agentic
—
Knowledge cutoff
—
Price history
Not enough history yet — newer than the backfill window.
Capability snapshot
Last-known Artificial Analysis indexes via OpenRouter.
| Index | Score |
|---|---|
| coding | 31.1 |
| context | 35.6 |
| tool_use | 1.6 |