Inception releases Mercury 3 diffusion LLM on OpenRouter
What happened
A report at 00:54 on October 20 said Inception's diffusion model Mercury 3 is live on OpenRouter, generating over 1,000 tok/s with a 1M context, four times the context of Mercury 2.5. A later report at 01:27 covered Inception's release of Mercury 3 and its push to scale text diffusion models larger. Inception claims the model beats GPT-6 Luna and Claude Haiku 5.5 on several benchmarks and runs 4 to 8 times faster. Coverage so far covers the release, the OpenRouter listing, context size, generation speed and the vendor's benchmark claims.
Written by AI from the coverage · updated 34 minutes ago
Developments
- Oct 20 01:27 · 1 reportInception releases Mercury 3, scaling its text diffusion model past 40x Mercury 1Hacker News front page
- Oct 20 00:54 · 1 reportInception 扩散模型 Mercury 3 上线 OpenRouterAI HOT · Products
Coverage
Follow the reports to see the story from different sides.
- Hacker News front pagePickInception releases Mercury 3, scaling its text diffusion model past 40x Mercury 1
Inception released Mercury 3, a diffusion-based large language model. The company says it beats GPT-6 Luna and Claude Haiku 5.5 on several benchmarks and runs 4–8x faster.
- AI HOT · ProductsInception 扩散模型 Mercury 3 上线 OpenRouter
Inception 的扩散模型 Mercury 3 上线 OpenRouter，生成速度超 1,000 tok/s，支持 1M 上下文，为 Mercury 2.5 的 4 倍。
Heat over time
Not enough continuous observations to draw a trend yet.