Forkast·
Inception’s Mercury 3 Undercuts the Speed-Optimized Frontier at 1,068 Tokens per Second
2 outlets reporting
1,068 tokens/sec
model throughput
At 1,068 tokens per second on NVIDIA GPUs, Inception Labs’ Mercury 3, released October 19, 2026, establishes a new performance baseline that renders the existing fast-cheap tier of frontier models obsolete. By utilizing a diffusion-based…