Search Results
6/29/2025, 2:45:37 PM
https://openrouter.ai/inception/mercury
>Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like GPT-4.1 Nano and Claude 3.5 Haiku while matching their performance.
>10 input 10 output (~4pus prices for input, ~4nnet prices for output)
Someone test it thx.
>Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like GPT-4.1 Nano and Claude 3.5 Haiku while matching their performance.
>10 input 10 output (~4pus prices for input, ~4nnet prices for output)
Someone test it thx.
Page 1