88Z AI, 15 June — The Kimi API Open Platform has launched the Kimi K2.7 Code High-Speed version, offering output speeds 5-6 times faster than the standard version at twice the price. Compared to K2.6, this model shows significant improvements in long-context programming and token efficiency, reducing average token consumption by 30% and boosting benchmark performance by 11%-31.5%.
At a glance
- Kimi K2.7 Code High-Speed launches with 5-6x speed increase at double the standard price
- Average token consumption drops 30% vs K2.6, with benchmark performance up 11%-31.5%
The update
The Kimi API Open Platform has officially launched the Kimi K2.7 Code High-Speed version, identified by the model ID kimi-k2.7-code-highspeed. Designed to enhance code generation efficiency, this version delivers output speeds 5 to 6 times faster than the standard version, with pricing set at twice that of the standard option. Compared to the previous K2.6 model, K2.7 Code achieves significant breakthroughs in long-context programming capabilities and token usage efficiency. Data indicates that the new model reduces average token consumption by 30% while improving performance in various benchmarks by 11% to 31.5%, providing developers with a more efficient and cost-effective programming assistance tool.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- Kimi开放平台Source published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.