AIHacker Newsabout 3 hours ago
Inception Launches Mercury 3 Diffusion LLM
4 min read
Inception introduces Mercury 3, a diffusion-based large language model that processes 1,068 tokens per second on NVIDIA GPUs. The model handles 1M tokens of context and costs $0.20 per million input tokens at standard pricing. Early partners deploy it for voice support, tutoring, and real-time search, with a launch discount of 50% off.
Level
Hype check
Tap to vote and see what everyone thinks.