---
title: 'Inception launches Mercury 3, its flagship diffusion LLM, at 1,068 tokens per second'
url: 'https://securteksecurity.com/news/inception-mercury-3-flagship-diffusion-llm'
markdown: 'https://securteksecurity.com/news/inception-mercury-3-flagship-diffusion-llm.md'
date: '2026-10-19'
description: 'Inception launched Mercury 3 on October 19, 2026, a diffusion language model that generates text in parallel rather than token by token. The company lists a speed of 1,068 tokens per second on NVIDIA GPUs, a 1 million token context window (up from 260,000 in Mercury 2.5), and a model more than 40 t…'
taxonomy:
  category:
    - AI
---

# [Inception launches Mercury 3, its flagship diffusion LLM, at 1,068 tokens per second](https://securteksecurity.com/news/inception-mercury-3-flagship-diffusion-llm)

   19th Oct 2026  

Inception launched Mercury 3 on October 19, 2026, a diffusion language model that generates text in parallel rather than token by token. The company lists a speed of 1,068 tokens per second on NVIDIA GPUs, a 1 million token context window (up from 260,000 in Mercury 2.5), and a model more than 40 times larger than Mercury 1. Launch pricing is $0.10 per million input tokens and $0.35 per million output tokens, half the list price. It is available through Inception, OpenRouter, Baseten and Vercel, and is OpenAI API compatible. Mercury 2 and 2.5 are closed to new users, with existing non-enterprise access ending November 15.

Inception says Mercury 3 beats GPT-6 Luna and Claude Haiku 5.5 across a range of benchmarks while running four to eight times faster. Those comparisons are the company's own; independent workloads have not yet settled them. The substantive claim is architectural: that diffusion scaling laws hold like autoregressive ones, so speed no longer has to be traded for capability at the fast model tier.

Sources: [Unite.AI](https://www.unite.ai/inception-releases-mercury-3-its-flagship-diffusion-llm/); [Interesting Engineering](https://interestingengineering.com/ai-robotics/mercury-3-diffusion-model-8-times-faster); [Business Wire](https://www.businesswire.com/news/home/20261019090400/en/Inception-Launches-Mercury-3-Setting-a-New-Pareto-Frontier-in-Speed-and-Intelligence)

---

## Navigation

- Parent: [News](https://securteksecurity.com/news.md)
- Previous: [IMF names an AI correction a top global financial-stability risk](https://securteksecurity.com/news/imf-ai-correction-top-financial-stability-risk.md)
- Next: [Initia halts Layer 1 and rollups after unauthorized mint exploit bridges out about $2.7 million](https://securteksecurity.com/news/initia-halts-layer-1-rollups-unauthorized-mint-2-7-million.md)