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...
Rank
#111
Up 3% week over week
Tokens
42.5B
2026-10-15
Requests
6.1M
6,116,125
Tool calls
-
Input / M
$0.04
Output / M
$0.15
Cache / M
$0.004
Context
260K
260,000 tokens