Mercury 2.5 Diffusion LLM Lands on OpenRouter

OpenRouter Sep 9, 2026

Key Info

Mercury 2.5 from Inception AI is now generally available on OpenRouter, and it tops the platform's Fastest Models leaderboard among models that don't require specialized hardware.

Highlights

It's a diffusion-based LLM that decodes tokens in parallel rather than one at a time, with the largest speed gains on code-heavy prompts.
Now live on OpenRouter, with no specialized hardware required, making it accessible through standard setups.

Original post

Mercury 2.5 from @_inception_ai is now generally available on OpenRouter. It's the fastest model on our Fastest Models leaderboard that doesn't require specialized hardware. A diffusion LLM: it decodes tokens in parallel rather than one at a time. The gain is largest on code-heavy prompts. Use it here: https://t.co/xTId0uFKC8

#Mercury 2.5#diffusion LLM#OpenRouter

View original on X