Inception Launches Mercury 2.5, Its Strongest Diffusion LLM

Inception Labs launched Mercury 2.5, its strongest and largest diffusion LLM with 40% higher intelligence than Mercury 2, running at 1100 tokens/sec. OpenCall uses it for real-time voice agents with sub-1-second p99 latency.

2026-09-09 ~ 2026-09-09 · 4 related posts

• Inception ships Mercury 2.5: most capable diffusion LLM at 1,107 tokens/sec, 260K context — StefanoErmon · 2026-09-09
• OpenCall runs live voice agents on Mercury 2.5, cutting p99 latency to 1 second — StefanoErmon · 2026-09-09
• Mercury 2.5 diffusion LLM launches at 80% off, p99 voice latency cut from minutes to 1s — StefanoErmon · 2026-09-09

1 near-duplicate retellings: timshi_ai