Skip to main content
INInception/ Mercury

Mercury 2

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...

Model information

Released
2026-03-04
Context window
128K
Max output
50K
Weights
Closed

Modalities

Input
Text
Output
Text

Identity

Version
mercury-2

Capabilities

ReasoningStructuredTemperatureTool call

Official price

input $0.25/M · output $0.75/M
cache read $0.025/M

Providers

ProviderProvider model IDProtocolContextMax outputInputOutputCapabilitiesNotesPricingStreaming
OpenRouterinception/mercury-2openai_chat128K50K
ReasoningTool callStructuredTemperature
Reasoning levels: high, medium, low, none, Default reasoning: medium
input $0.25/M · output $0.75/M
cache read $0.025/M
Yes
Inceptionmercury-2openai_chat128K50K
ReasoningTool callStructuredTemperature
-
input $0.25/M · output $0.75/M
cache read $0.025/M
Yes
Kilo Gatewayinception/mercury-2openai_chat128K50K
ReasoningTool callStructuredTemperature
-
input $0.25/M · output $0.75/M
cache read $0.025/M
Yes
Vercel AI Gatewayinception/mercury-2openai_chat128K50K
ReasoningTool callTemperature
-
input $0.25/M · output $0.75/M
cache read $0.025/M
Yes

FAQ