PANews October 20 news: According to Inception's official announcement, the company has released the diffusion-based large language model Mercury 3, supporting a 1 million Token context. The company states that its generation speed on NVIDIA GPUs reaches 1,068 Tokens per second, and its performance on multiple benchmarks exceeds GPT-6 Luna and Claude Haiku 5.5. Standard pricing is $0.20 per million input Tokens and $0.70 per million output Tokens, with half price during the launch period. The model is now available through the Inception API, OpenRouter, Baseten, and Vercel, and is compatible with the OpenAI API.
Article / PANews