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
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
Why it matters
Diffusion-based decoding offers a genuinely different latency profile than autoregressive models, worth testing for code-generation workloads where tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition →-by-token decoding is the bottleneck.
