Inception AI's Mercury 2.5 Hits Over 1,100 Tokens Per Second

Inception AI has released Mercury 2.5 Preview on OpenRouter, a diffusion-based LLM that achieves 1,107 tokens per second through parallel token generation.

2026-09-02 ~ 2026-09-02 · 2 related posts

• Mercury 2.5 Preview launches on OpenRouter with 1,107 tok/s speed — StefanoErmon · 2026-09-02

1 near-duplicate retellings: volokuleshov