Mercury 2.5 Preview: Fastest Reasoning LLM Now Live on OpenRouter with Image Benchmarks

OpenRouter · 2026-09-01

Key Info

Mercury 2.5 Preview from Inception AI, described as the fastest reasoning LLM, is now live exclusively on OpenRouter, with image benchmarks available at the provided link.

Highlights

Reaches 1,107 tokens/sec through parallel token generation.
Supports tunable reasoning and is available exclusively on OpenRouter.
Image benchmark results can be browsed via the official link.