Mercury 3
Mercury 3 is a cutting-edge diffusion-based large language model that offers superior intelligence and speed compared to other frontier models. It supports real-time applications including voice and chat support, interactive education, search agents, and customer support, providing up to 1,000+ tokens per second throughput and context windows up to 1 million tokens. Available via API with OpenAI compatibility, it enables fast, scalable AI solutions for developers and enterprises.
Ratings & Reviews
Write a reviewBe the first to share a thoughtful review.
Information
Website checks
Automated checks of the public website by Google Lighthouse 13.5.0. Scores can vary between runs.
Checked Oct 24, 2026
Test this website on PageSpeedWebsite checks refresh automatically each week.
- Performance
- 72 out of 100, Needs improvement
- Accessibility
- 89 out of 100, Needs improvement
- Best Practices
- 100 out of 100, Good
- SEO
- 100 out of 100, Good
Around the Web
The browser-agent example is where the speed story gets interesting. I would be curious to see end-to-end task timings with the tool calls included.
oleksii_sekundant · Imported from Product Hunt
Congrats team! 40x scale with no slowdown on a diffusion LLM is a serious claim, I'd love to see latency side by side with autoregressive models at the same quality. Big fan of the approach, good luck today.
jean_bonnenfant_tinct · Imported from Product Hunt