Inception: Mercury 2

INCEPTION Developer Architecture Profile

OpenRouter ↗HuggingFace ↗

Intelligence (ELO)1415Chatbot Arena Verified

Max Context Limit128,000Max Out: 50,000 tokens

Prompt Caching90% OFF$0.02 / 1M cached

Standard API / 1M$1.00🧠 Deep Reasoner

Model Capabilities & Contract SLAs

Reasoning
Coding & Logic
Fictional
🧠 Extended Test-Time Reasoning

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...

Granular Pricing Matrix

Input Tokens (Standard Prompt)$0.25 / 1M

⚡ Cached Input (Prompt Cache Read)90% OFF$0.02 / 1M

Output Tokens (Completion)$0.75 / 1M

Pricing data via OpenRouter. Sync: 10/2/2026

Evaluate Competitors

VS Engine MatchupInception: Mercury 2 vs MiniMax: MiniMax M3 VS Engine MatchupInception: Mercury 2 vs SpaceXAI: Grok Build 0.1 VS Engine MatchupInception: Mercury 2 vs Perceptron: Perceptron Mk1 VS Engine MatchupInception: Mercury 2 vs Qwen: Qwen-Plus VS Engine MatchupInception: Mercury 2 vs Perceptron: Perceptron Mk1.5 VS Engine MatchupInception: Mercury 2 vs Sakana: Sakana Namazu