← all models

Mercury 2

inception

openrouter
Parameters — not published
Context 125K 128000 tokens
Input $0.25 OpenRouter
Output $0.75 OpenRouter
Cache read $0.03 OpenRouter

Accepts

text

Capabilities

include_reasoning max_tokens reasoning reasoning_effort response_format stop structured_outputs temperature tool_choice tools

Description

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...

The OpenRouter API truncates descriptions — read the full text at the source

Also known as

Every id and name this model has been seen under — for matching it against another catalogue.

openrouter inception/mercury-2 version slug inception/mercury-2-20260304 name Inception: Mercury 2 display name Mercury 2

Identifiers

Vendor
inception
OpenRouter
inception/mercury-2
Version slug
inception/mercury-2-20260304
Released
2026-03-04T14:57:55.000Z
First seen
59 d ago
Last crawled
10 d ago