Inception launches Mercury 3 diffusion LLM with 1M-token context
Inception Labs released Mercury 3, a diffusion-based large language model that refines multiple token positions in parallel rather than generating text one token at a time. The company reported 1,068 tokens per second on NVIDIA GPUs and a 1-million-token context window. Inception said Mercury 3 outperformed GPT-6 Luna and Claude Haiku 5.5 on eight of 12 internal tests and ran four to eight times faster; another report said it beat GPT-6 Luna, Claude Haiku 5.5 and GLM-5.3 Flash across a range of tests. These figures are vendor-reported and have not been independently validated. Mercury 3 is available through Inception’s API, OpenRouter, Baseten and Vercel, with standard rates of $0.20 per million input tokens and $0.70 per million output tokens.
The release is notable because Inception says Mercury 3 combines diffusion-style parallel generation with a million-token context and high throughput. The reports also emphasize its potential for applications such as agents, search, customer support and tutoring, where repeated model calls can add up to delays. Its benchmark and speed claims remain unverified outside Inception’s own testing.
Today we’re introducing Mercury 3, the most capable diffusion-based LLM released to date. Across a range of benchmarks, Mercury 3 outperforms GPT-6 Luna and Claude Haiku 5.5, while running 4–8x faster at 1,000+ tokens per second.
Mercury 3 demonstrates that text diffusion scales. It’s more than 40x larger than Mercury 1 and is vastly more intelligent, but just as fast.
Early-access partners already use Mercury 3 for voice and chat support, real-time tutoring, data engineering, and web navigation:
Mercury 3 at a glance
- Quality: On par or better than frontier speed-optimized models like GPT-6 Luna and Claude Haiku 5.5.
- Speed: 1,068 tokens per second on NVIDIA GPUs.
- Context: 1M tokens, up from 260K for Mercury 2.5
- Price: $0.20 per million input and $0.70 per million output tokens.
- At launch, Mercury 3 is 50% off at $0.10 per 1M input and $0.35 per 1M output. Cached tokens are 90% off the input price.
#Inception Labs#Mercury 3#NVIDIA#GPT-6 Luna#Claude Haiku 5.5#GLM-5.3 Flash#OpenRouter#Baseten#Vercel