[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-kimi-k27-whats-new-and-how-to-run-it-en":3,"article-related-kimi-k27-whats-new-and-how-to-run-it-en":31,"series-model-release-952ab890-dacd-429b-93d2-3821a5dc00bc":78},{"id":4,"slug":5,"title":6,"content":7,"summary":8,"source":9,"source_url":10,"author":11,"image_url":12,"cover_image":12,"category":13,"language":14,"translated_content":11,"related_article_id":15,"keywords":16,"key_takeaways":23,"views":27,"created_at":28,"published_at":29,"topic_cluster_id":30},"952ab890-dacd-429b-93d2-3821a5dc00bc","kimi-k27-whats-new-and-how-to-run-it-en","Kimi K2.7: What Changed and How to Run It","\u003Cp data-speakable=\"summary\">Kimi K2.7 is a new Moonshot model for long-context, Chinese, and \u003Ca href=\"\u002Ftag\u002Fagentic-coding\">agentic coding\u003C\u002Fa> workflows.\u003C\u002Fp>\u003Cp>This guide is for developers who want to evaluate \u003Ca href=\"\u002Ftag\u002Fmoonshot-ai\">Moonshot AI\u003C\u002Fa>’s Kimi K2.7 in a real \u003Ca href=\"\u002Ftag\u002Fagent\">agent\u003C\u002Fa> workflow, especially if they already use Kimi K2.6, OpenRouter, or an always-on assistant stack. By the end, you will know what K2.7 carries over, what to test before upgrading, and how to switch it into a live agent without rebuilding your app.\u003C\u002Fp>\u003Cp>You will also get a practical checklist for choosing between K2.7 and your current model based on your own prompts, documents, and coding tasks. If your workload involves long files, Chinese text, or multi-step tool use, this guide shows you the fastest path to an evidence-based decision.\u003C\u002Fp>\u003Ch2>Before you start\u003C\u002Fh2>\u003Cul>\u003Cli>An OpenRouter account with API access\u003C\u002Fli>\u003Cli>A valid OpenRouter API key\u003C\u002Fli>\u003Cli>Node.js 20+ or Python 3.11+ for local testing\u003C\u002Fli>\u003Cli>An agent app or playground that can select models by name\u003C\u002Fli>\u003Cli>A small evaluation set of real prompts, files, or tickets\u003C\u002Fli>\u003Cli>Access to the \u003Ca href=\"https:\u002F\u002Fopenclawlaunch.com\u002Fblog\u002Fkimi-k2-7-release\">OpenClaw Launch Kimi K2.7 release post\u003C\u002Fa> and the \u003Ca href=\"https:\u002F\u002Fopenrouter.ai\u002Fmodels\">OpenRouter model list\u003C\u002Fa>\u003C\u002Fli>\u003Cli>The \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FOpenRouterTeam\u002Fopenrouter-sdk\">OpenRouter SDK\u003C\u002Fa> if you want to script comparisons\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>Step 1: Confirm the K2.7 model ID\u003C\u002Fh2>\u003Cp>Goal: identify the exact OpenRouter model name before you wire it into an agent, because Moonshot model IDs can change as releases are updated.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781791374284-re3e.png\" alt=\"Kimi K2.7: What Changed and How to Run It\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>Open the OpenRouter model list and copy the current Kimi K2.7 entry, then note the pricing, context length, and any multimodal details shown there. Treat that listing as the source of truth rather than relying on blog post text alone.\u003C\u002Fp>\u003Cpre>\u003Ccode>curl https:\u002F\u002Fopenrouter.ai\u002Fapi\u002Fv1\u002Fmodels | jq '.data[] | select(.name | test(\"Kimi.*K2.7\"; \"i\")) | {id, name, context_length, pricing}'\u003C\u002Fcode>\u003C\u002Fpre>\u003Cp>Verification: you should see one Kimi K2.7 model entry with an ID you can paste into your app config.\u003C\u002Fp>\u003Ch2>Step 2: Build a small A\u002FB prompt set\u003C\u002Fh2>\u003Cp>Goal: create a realistic test pack so you can compare K2.7 against K2.6 or your current model on the tasks that matter.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781791373682-tx6v.png\" alt=\"Kimi K2.7: What Changed and How to Run It\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>Use 5 to 10 prompts that reflect your actual workload: a long document summary, a Chinese rewrite, a code change request, a multi-step debugging task, and one image or mixed-input prompt if your stack supports vision. Keep the prompts fixed so each model sees the same inputs.\u003C\u002Fp>\u003Cp>Store the prompts in plain files or JSON so your agent can replay them automatically. If you already have production traces, reuse those instead of inventing synthetic examples.\u003C\u002Fp>\u003Cp>Verification: you should have a repeatable prompt set that produces comparable outputs across models.\u003C\u002Fp>\u003Ch2>Step 3: Switch your agent to Kimi K2.7\u003C\u002Fh2>\u003Cp>Goal: point your existing agent at K2.7 with the smallest possible change so you can test it in production-like conditions.\u003C\u002Fp>\u003Cp>If you use \u003Ca href=\"\u002Ftag\u002Fopenclaw\">OpenClaw\u003C\u002Fa> or Hermes Agent, pick K2.7 from the model dropdown and add your OpenRouter key. If you call the \u003Ca href=\"\u002Ftag\u002Fapi\">API\u003C\u002Fa> directly, update the model field in your request and keep all other parameters unchanged for the first pass.\u003C\u002Fp>\u003Cpre>\u003Ccode>import OpenAI from \"openai\";\n\nconst client = new OpenAI({\n  baseURL: \"https:\u002F\u002Fopenrouter.ai\u002Fapi\u002Fv1\",\n  apiKey: process.env.OPENROUTER_API_KEY,\n});\n\nconst response = await client.chat.completions.create({\n  model: \"moonshot\u002Fkimi-k2-7\",\n  messages: [\n    { role: \"system\", content: \"You are a coding agent.\" },\n    { role: \"user\", content: \"Review this repo and propose a fix.\" }\n  ]\n});\n\nconsole.log(response.choices[0].message.content);\u003C\u002Fcode>\u003C\u002Fpre>\u003Cp>Verification: you should get a valid completion from K2.7 without changing your app’s routing, tools, or storage.\u003C\u002Fp>\u003Ch2>Step 4: Run a task-by-task comparison\u003C\u002Fh2>\u003Cp>Goal: measure whether K2.7 is actually better for your workload, not just newer.\u003C\u002Fp>\u003Cp>Run each prompt set through K2.7 and your baseline model, then score the outputs for correctness, usefulness, tool-call quality, and edit distance if you are evaluating code. For long-context tasks, check whether the model preserves details from early parts of the input and whether it follows instructions across the entire conversation.\u003C\u002Fp>\u003Cp>Keep the comparison simple at first: the same temperature, the same max tokens, and the same tool configuration. Change only one variable at a time if you need to troubleshoot a difference.\u003C\u002Fp>\u003Cp>Verification: you should be able to say which model wins for summaries, Chinese writing, and agentic coding on your own data.\u003C\u002Fp>\u003Ch2>Step 5: Put the winner into your always-on agent\u003C\u002Fh2>\u003Cp>Goal: promote the better model into the workflow that runs on Telegram, Discord, WhatsApp, WeChat, or the web.\u003C\u002Fp>\u003Cp>Once you have a clear winner, update the default model in your agent config and keep the baseline as a fallback. If your platform supports a dropdown, make K2.7 the default for long-document or Chinese tasks and leave your smaller model for quick, cheap requests.\u003C\u002Fp>\u003Cp>Roll the change out gradually so you can watch latency, cost, and answer quality under real traffic. If K2.7 is better but slower, reserve it for the prompts where the quality gain matters most.\u003C\u002Fp>\u003Cp>Verification: you should see live requests flowing through K2.7 with no user-facing breakage and a clear fallback path.\u003C\u002Fp>\u003Ch2>Common mistakes\u003C\u002Fh2>\u003Cul>\u003Cli>Using the blog post instead of the live model list. Fix: copy the current model ID from OpenRouter before you ship.\u003C\u002Fli>\u003Cli>Comparing models with different prompts or settings. Fix: lock your test set, temperature, and tool config so the results are fair.\u003C\u002Fli>\u003Cli>Upgrading every task to K2.7 by default. Fix: reserve it for long-context, Chinese, or agentic jobs where the quality gain justifies the cost.\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>What's next\u003C\u002Fh2>\u003Cp>After you validate K2.7, extend the same A\u002FB method to other models in your stack, then document which workloads belong to each tier so your team can switch models with confidence.\u003C\u002Fp>","Kimi K2.7 adds a fresh option for long-context, Chinese, and agentic coding workflows.","openclawlaunch.com","https:\u002F\u002Fopenclawlaunch.com\u002Fblog\u002Fkimi-k2-7-release",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781791374284-re3e.png","model-release","en","2495916e-6109-4bd6-a948-f118ebd948ca",[17,18,19,20,21,22],"Kimi K2.7","OpenRouter","OpenClaw","Hermes Agent","long-context models","agentic coding",[24,25,26],"Kimi K2.7 is best evaluated on real long-context, Chinese, and coding tasks.","Use OpenRouter as the source of truth for the current model ID and pricing.","A simple A\u002FB test is the fastest way to decide whether to upgrade.",0,"2026-06-18T14:02:25.334347+00:00","2026-06-18T14:02:25.325+00:00","1bae1133-d241-4581-9332-fbf39690c319",{"tags":32,"relatedLang":37,"relatedPosts":41},[33,35],{"name":18,"slug":34},"openrouter",{"name":19,"slug":36},"openclaw",{"id":15,"slug":38,"title":39,"language":40},"kimi-k27-whats-new-and-how-to-run-it-zh","Kimi K2.7 上線與驗證清單","zh",[42,48,54,60,66,72],{"id":43,"slug":44,"title":45,"cover_image":46,"image_url":46,"created_at":47,"category":13},"35368396-f604-46b7-9aa3-35ea227c99da","google-gemini-35-live-translate-audio-model-en","Google launches Gemini 3.5 Live Translate audio model","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781807575345-04yn.png","2026-06-18T18:32:29.328812+00:00",{"id":49,"slug":50,"title":51,"cover_image":52,"image_url":52,"created_at":53,"category":13},"d18e6176-7ba9-4460-8230-425e3aeaeb86","kimi-k27-code-highspeed-mode-skips-benchmarks-en","Kimi K2.7-Code Adds HighSpeed Mode, Skips Benchmarks","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781795890377-d0e8.png","2026-06-18T15:17:41.403224+00:00",{"id":55,"slug":56,"title":57,"cover_image":58,"image_url":58,"created_at":59,"category":13},"1b2d4bc4-b90d-4a10-a9e9-99f5e56a4719","linux-kernel-7-1-fred-ntfs-amd-fixes-en","Linux Kernel 7.1 adds FRED, NTFS, and AMD fixes","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781787775484-40k3.png","2026-06-18T13:02:25.315681+00:00",{"id":61,"slug":62,"title":63,"cover_image":64,"image_url":64,"created_at":65,"category":13},"4515e89e-6fbd-4dd8-a5fa-bbd2bcf6425a","fable-5-drew-rare-praise-ai-voices-en","Fable 5 drew rare praise from top AI voices","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781748174800-46t2.png","2026-06-18T02:02:31.145023+00:00",{"id":67,"slug":68,"title":69,"cover_image":70,"image_url":70,"created_at":71,"category":13},"a6017fa4-a339-4a83-b086-16a69dbde34d","devin-pricing-june-2026-plans-limits-en","Devin pricing in June 2026: plans, limits, tradeoffs","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781735574969-l960.png","2026-06-17T22:32:28.222997+00:00",{"id":73,"slug":74,"title":75,"cover_image":76,"image_url":76,"created_at":77,"category":13},"ccc46975-50d1-4ece-8fd3-c082bf4858ae","self-host-minimax-m3-gpu-cloud-en","Self-host MiniMax M3 on GPU cloud","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781716680837-ikof.png","2026-06-17T17:17:35.800599+00:00",[79,84,89,94,99,104,109,114,119,124],{"id":80,"slug":81,"title":82,"created_at":83},"d4cffde7-9b50-4cc7-bb68-8bc9e3b15477","nvidia-rubin-ai-supercomputer-en","NVIDIA Unveils Rubin: A Leap in AI Supercomputing","2026-03-25T16:24:35.155565+00:00",{"id":85,"slug":86,"title":87,"created_at":88},"eab919b9-fbac-4048-89fc-afad6749ccef","google-gemini-ai-innovations-2026-en","Google's AI Leap with Gemini Innovations in 2026","2026-03-25T16:27:18.841838+00:00",{"id":90,"slug":91,"title":92,"created_at":93},"5f5cfc67-3384-4816-a8f6-19e44d90113d","gap-google-gemini-ai-checkout-en","Gap Teams Up with Google Gemini for AI-Driven Checkout","2026-03-25T16:27:46.483272+00:00",{"id":95,"slug":96,"title":97,"created_at":98},"f6d04567-47f6-49ec-804c-52e61ab91225","ai-model-release-wave-march-2026-en","Navigating the AI Model Release Wave of March 2026","2026-03-25T16:28:45.409716+00:00",{"id":100,"slug":101,"title":102,"created_at":103},"895c150c-569e-4fdf-939d-dade785c990e","small-language-models-transform-ai-en","Small Language Models: Llama 3.2 and Phi-3 Transform AI","2026-03-25T16:30:26.688313+00:00",{"id":105,"slug":106,"title":107,"created_at":108},"38eb1d26-d961-4fd3-ae12-9c4089680f5f","midjourney-v8-alpha-features-pricing-en","Midjourney V8 Alpha: A Deep Dive into Its Features and Pricing","2026-03-26T01:25:36.387587+00:00",{"id":110,"slug":111,"title":112,"created_at":113},"bf36bb9e-3444-4fb8-ab19-0df6bc9d8271","rag-2026-indispensable-ai-bridge-en","RAG in 2026: The Indispensable AI Bridge","2026-03-26T01:28:34.472046+00:00",{"id":115,"slug":116,"title":117,"created_at":118},"60881d6d-2310-44ef-b1fb-7f98e9dd2f0e","xiaomi-mimo-trio-agents-robots-voice-en","Xiaomi’s MiMo trio targets agents, robots, and voice","2026-03-28T03:05:08.899895+00:00",{"id":120,"slug":121,"title":122,"created_at":123},"f063d8d1-41d1-4de4-8ebc-6c40511b9369","xiaomi-mimo-v2-pro-1t-moe-agents-en","Xiaomi MiMo-V2-Pro: 1T MoE Model for Agents","2026-03-28T03:06:19.238032+00:00",{"id":125,"slug":126,"title":127,"created_at":128},"a1379e9a-6785-4ff5-9b0a-8cff55f8264f","cursor-composer-2-started-from-kimi-en","Cursor’s Composer 2 started from Kimi","2026-03-28T03:11:59.132398+00:00"]