mercury-2

1346 Score third-party Elo · arena.ai / LMArena ?

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...

LLM & Generative AI 1 model 1 listings snapshot Oct 14, 2026, 12:43 AM

Platforms

click a card to open the detail table

Cheapest OpenRouter no official benchmark Input$0.250 Output$0.750 per 1M tokens Fastest OpenRouter lowest p50 latency on this board 128.1 ms p50 Most free quota — largest published free allowance — free tier

Model variants

W3r9 dedup — same model + identical tags merge; prices are listed per billing form

Model	Provider	Tags	Input /1M	Output /1M
inception/mercury-2	OpenRouter	125k contextreasoning	$0.250	$0.750

Capabilities

official design_arena & architecture metadata

Design Arena Elo official design_arena benchmark (OpenRouter)

website 1036 · 22.0% wr
codecategories 1023 · 21.4% wr
dataviz 1013 · 22.6% wr
uicomponent 998 · 19.6% wr
asciiart 997 · 25.2% wr
svg 996 · 24.6% wr
gamedev 992 · 19.3% wr
3d 983 · 21.9% wr

Input / Output modalities modality: text->text

text in+out

Platform details

per provider

provider	model	Input /1M	Output /1M	Latency ?	Official $/1M	Availability	Data time
OpenRouter	inception/mercury-2	$0.250	$0.750	128.1 ms	—	100% available	2026-10-14 00:43:21

1 rows · snapshot 2026-10-14 00:43:21 · from data/public/prices.json + measurements.json