Inception: Mercury 2

proprietary

Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM).

Context
128K
Max output
50K
Input price
$0.25/1M tokens
Output price
$0.75/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming

Details

Model IDinception/mercury-2
Provider OpenRouter
Creator Inception Labs
Family—
Licenseproprietary
Status—
Type—
Input modalitiestext
Output modalitiestext
Open weightNo
Parameters—
Architecture—
Context window128K tokens
Max input—
Max output50K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.25
Output
$0.75
Cache write
—
Cache read
$0.03
Batch in
—
Batch out
—

API

GET/v1/models/openrouter/inception/mercury-2

Inception: Mercury 2

inception/mercury-2

Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM).

Changes · 3 entries
inception/mercury-2update1cd659eMar 24, 2026, 04:19 AM
capabilitiesjson modeyes
inception/mercury-2update2b100acMar 23, 2026, 05:30 AM
release_date2026-03-04
taglineMercury 2 is an extremely fast reasoning LLM, and the fir...
tools["function_calling"]
inception/mercury-2create7f5c66fMar 21, 2026, 05:16 AM