On August 22, Moonshot AI announced another major breakthrough in the output speed of its Kimi K2 model. After the relentless efforts of the engineering team, the Kimi-K2-Turbo-Preview model's output speed has been improved to 60 Tokens per second, with a maximum of up to 100 Tokens per second. This significant speed improvement will further optimize the user experience and meet the efficient needs of more scenarios.
Currently, the Kimi-K2-Turbo-Preview model is still available at a special discounted price. The input price per million Tokens (cache hit) is 2.00 yuan, the input price (cache miss) is 8.00 yuan, and the output price is 32.00 yuan. This promotional price will continue until September 1st, after which it will return to the original price.
Moonshot AI stated in the announcement that they appreciate the continuous support and trust from users, and the company will continue to focus on optimizing model performance and further improving the output speed of the Kimi K2 model. Users can visit the Moonshot AI official website (https://platform.moonshot.cn) for more detailed information.
This speed improvement is not only a technological advancement but also a proactive response to user needs by Moonshot AI. As the model's performance continues to improve, Kimi K2 will provide users with a more efficient and smooth AI experience, helping users achieve higher efficiency and creativity in their work and daily life.
