Inception Releases Diffusion Large Model Mercury 3 with 1 Million Token Context Support

Inception has launched the diffusion large language model Mercury 3, which supports a 1 million token context window. The company states that the model achieves a generation speed of 1068 tokens per second on NVIDIA GPUs, with performance across multiple benchmark tests exceeding that of GPT-6 Luna and Claude Haiku 5.5. Standard pricing is set at $0.20 per million input tokens and $0.70 per million output tokens, with a 50% discount available during the initial launch period. The model is now accessible via the Inception API, OpenRouter, Baseten, and Vercel, and maintains full compatibility with the OpenAI API.

Source: PANewsRead original