Inception's Mercury 3 Hits 1,000 Tokens per Second With 1M Context

Inception's Mercury 3 is a diffusion-based language model that generates over 1,000 tokens per second while matching frontier speed-tier quality.

Source

Inception

Published

Oct 20, 2026, 4:53 PM

Author

AlphaSignal Newsroom

Read

1 min read

Inception's Mercury 3 is a diffusion-based language model that generates over 1,000 tokens per second while matching frontier speed-tier quality.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Next reads