Inception: Mercury 2.5
INCEPTION Developer Architecture Profile
Intelligence (ELO)1057Chatbot Arena Verified
Max Context Limit260,000Max Out: 65,536 tokens
Prompt Caching90% OFF$0.0040 / 1M cached
Standard API / 1M$0.19🧠 Deep Reasoner
Model Capabilities & Contract SLAs
- Reasoning
- 🧠 Extended Test-Time Reasoning
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...
Granular Pricing Matrix
Input Tokens (Standard Prompt)$0.04 / 1M
⚡ Cached Input (Prompt Cache Read)90% OFF$0.0040 / 1M
Output Tokens (Completion)$0.15 / 1M
Pricing data via OpenRouter. Sync: 10/2/2026
Evaluate Competitors
VS Engine MatchupInception: Mercury 2.5 vs Pareto Code RouterVS Engine MatchupInception: Mercury 2.5 vs Poolside: Laguna S 2.1 (free)VS Engine MatchupInception: Mercury 2.5 vs Auto Router (Beta)VS Engine MatchupInception: Mercury 2.5 vs Poolside: Laguna XS 2.1 (free)VS Engine MatchupInception: Mercury 2.5 vs Meta: Muse Spark 1.2 ContributorVS Engine MatchupInception: Mercury 2.5 vs NVIDIA: Nemotron 3.5 Content Safety (free)