Skip to content
OneAtlas

Mercury 2

inception/mercury-2
InceptionTextClosed weightsReasoningTool callStructured output
Compare 6 providers

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

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...

Context

128K

128,000 tokens

Max output

50K

50,000 tokens

Input

$0.25

per 1M tokens

Output

$0.75

per 1M tokens

Providers

6

6 listings

Intelligence

10.8

Intelligence Index

Pricing

USD per 1M tokens · listed by Inception

Token typeStandard
Input$0.25
Output$0.75
Cache read$0.03

Lowest input price across providers: $0.25.

Capabilities

ReasoningYes

Effort: low, medium, high

Tool callYes
Structured outputYes
TemperatureYes
AttachmentsNo
Interleaved reasoningNo
Open weightsNo
ModeratedNo

Input

Text

Output

Text

Benchmarks

Published scores and Design Arena Elo

Design Arena categoryEloWin rateArena rank
Website1,03422.1%#127
Code1,01821.1%#125
Data viz1,01222.6%#116
SVG99524.6%#88
UI component99019.4%#119
ASCII art98624.2%#71
Game dev97918.3%#126
3D97521.1%#117

Rankings

Position on each OneAtlas leaderboard

Providers · 6

6 listings

ProviderModel IDContextInput limitOutputInput $Output $Reasoning $Cache readCache writeAudio inAudio outReasoningToolsStructuredTemp.Updated
AI/ML APIinception/mercury-2128K—50K$0.26$0.79—$0.03———YesYesYesYesFeb 24, 2026
Inceptionmercury-2128K—50K$0.25$0.75—$0.03———YesYesYesYesFeb 24, 2026
Kilo Gatewayinception/mercury-2128K—50K$0.25$0.75—$0.03———YesYesYesYesFeb 24, 2026
NanoGPTmercury-2128K128K50K$0.25$0.75—$0.03———YesYesYesYesFeb 24, 2026
Venice AImercury-2128K—50K$0.31$0.94—$0.03———YesYesYesYesFeb 24, 2026
Vercel AI Gatewayinception/mercury-2128K—50K$0.25$0.75—$0.03———YesYesYesYesFeb 24, 2026