Kimi K2 Official High-Speed Version API Rolls Out Limited-Time 50% Discount
5 day ago / Read about 0 minute
Author:小编   

The kimi-k2-turbo-preview represents the high-speed iteration of the Kimi K2 model. It maintains identical model parameters to those of kimi-k2-0905, while boasting an expanded context window that can accommodate up to 256K. In terms of performance, this high-speed variant is capable of achieving an output speed ranging from 60 to 100 Tokens per second, which is roughly six times faster than its standard counterpart.