{"id":54662,"date":"2026-07-13T09:57:46","date_gmt":"2026-07-13T01:57:46","guid":{"rendered":"https:\/\/www.1ai.net\/?p=54662"},"modified":"2026-07-13T09:57:46","modified_gmt":"2026-07-13T01:57:46","slug":"%e6%9c%88%e4%b9%8b%e6%9a%97%e9%9d%a2-k2-7-code-%e9%ab%98%e9%80%9f%e7%89%88%e6%a8%a1%e5%9e%8b%e6%ad%a3%e5%bc%8f%e7%99%bb%e9%99%86-kimi-code%ef%bc%8c%e6%88%90%e4%b8%ba%e5%b8%b8%e9%a9%bb%e5%8f%af","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/54662.html","title":{"rendered":"On the dark side of the moon, K2.7 Code, the high-speed model officially landed at Kimi Code, becoming a permanent optional mode"},"content":{"rendered":"<p>The news of July 13th<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e6%9c%88%e4%b9%8b%e6%9a%97%e9%9d%a2\" title=\"[Sees articles with labels]\" target=\"_blank\" >Dark Side of the Moon<\/a>Official announcement:<strong>K2.7 Code High-speed end Beta as an optional permanent mode<\/strong>.<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2026\/01\/016f590ej00t9as9y002bd000qo00f0p.jpg\" alt=\"Zhang Jae-chul, President of the Dark Side of the Moon: Kimi uses only the resources of the top American lab, 1%\" \/><\/p>\n<p>Users who subscribe to the Allegretto membership scheme and above can directly call K2.7 Code HighSpeed without any application for programming using Coding Plan in Kimi Code CLI or other tools\u3002<\/p>\n<p>Officially, K2.7 Code HighSpeed\u00a0<strong>Consumption in Coding Plan is 3 times more than in a normal version of the model<\/strong>I don't know. Users can choose whether to open a high-speed mode based on actual mission needs and current usage\u3002<\/p>\n<p>It is described that K2.7 Code uses the same model as the general version<strong>The output speed is about 5-6 times the normal version<\/strong>I don't know. General programming scene, take a median input length with an output speed of about 180 Token\/s; short context scenario can reach 260 Token\/s\u3002<\/p>\n<p>Kimi K2.7 Code is twice as high as Kimi K2.7 Code:<strong>The standard input and output prices for 1M tokens were $13 and $54, respectively; the input price for the hit cache was 2.6<\/strong>.<\/p>\n<p>According to 1AI, the Kimi K2.7 Code programming model was published on 12 June. The internal and external baseline assessment showed that Kimi K2.7 Code significantly improved the performance of the long context programming scenario ' s command compliance, long-range programming tasks compared to the K2.6 model, and significantly improved overthinking in long-range missions, with an average token consumption reduction of 301 TP3T\u3002<\/p>","protected":false},"excerpt":{"rendered":"<p>On July 13th, the dark side of the month officially announced that the K2.7 Code high-speed version had ended in Beta and became an optional permanent model. Users who subscribe to the Allegretto membership scheme and above can directly call K2.7 Code HighSpeed without any application for programming using Coding Plan in Kimi Code CLI or other tools. Officially, K2.7 Code HighSpeed consumes three times as much as the normal version of the model as it consumes in Coding Plan. Users can choose whether to open a high-speed mode based on actual mission needs and current usage. According to K2.7 Code High-speed and Pu<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[1168],"collection":[],"class_list":["post-54662","post","type-post","status-publish","format-standard","hentry","category-news","tag-1168"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/54662","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=54662"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/54662\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=54662"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=54662"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=54662"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=54662"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}