Mercury 3 brings million-token context to diffusion LLMs
Inception’s Mercury 3 gives latency-sensitive apps a diffusion LLM that runs at 1,068 tokens per second on NVIDIA GPUs, with a 1M-token context window and launch pricing of $0.10 per million input tokens and $0.35 per million output tokens. The model generates text through diffusion rather than one token at a time, and Inception says it is more than 40x larger than Mercury 1 while reaching comparable or better quality than GPT-6 Luna and Claude Haiku 5.5. In a 50-task web-navigation test, it completed 50% of tasks.