Inception launches Mercury 3 at 1,068 tokens per second

Inception launched Mercury 3 on October 19th, a diffusion-based language model that CEO and co-founder Stefano Ermon says delivers 1,068 tokens per second, a 1-million-token context window and benchmark gains over rival models, with launch pricing at half off. Inception positions Mercury 3 as a faster alternative to conventional systems that generate text one token at a time, and the company is testing whether diffusion can scale into general agent and business workloads while keeping its speed advantage. The published results and partner examples are company-reported, so adoption will depend on how the model performs in developers' own tasks.

Inception launches Mercury 3 at 1,068 tokens per second Stefano Ermon's diffusion model claims a 1-million-token context window and benchmark gains over rival models, with launch pricing half off. By Ryan Merket https://runtimewire.com/author/ryan-merket · Published Primary source: X https://x.com/StefanoErmon/status/2112222911218291051 Why it matters Mercury 3 tests whether diffusion can scale into general agent and business workloads while keeping its speed advantage. Its published results and partner examples are company-reported, so adoption will depend on how the model performs in developers' own tasks. Inception https://www.inceptionlabs.ai/blog/introducing-mercury-3 launched Mercury 3 on October 19th, pitching its diffusion-based language model as a faster alternative to conventional systems that generate text one token at a time. CEO and co-founder Stefano Ermon @StefanoErmon https://x.com/StefanoErmon says it delivers more than 1,000 tokens per second while improving on the company's earlier models. When you purchase through links in our articles, we may earn a small commission https://runtimewire.com/affiliate-monetization-standards . This doesn’t affect our editorial independence.