[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-openrouter":3},{"tag":4,"articles":11,"peer_article_count":95},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"102f17eb-8fee-4572-9006-fc7d6a57f195","OpenRouter","openrouter",3,"OpenRouter 是一個統一多家模型供應商的 API 路由層，常被用來切換 OpenAI、Anthropic、Google、開源模型與不同價格方案。這個主題關注模型選型、成本控制、延遲、相容性與供應鏈風險，特別適合代理、編碼助手和多模型編排場景。","OpenRouter is a routing layer that lets developers call many model providers through one API, from OpenAI and Anthropic to open-source and lower-cost options. It matters for model switching, pricing, latency, compatibility, and supply-chain risk in agents, coding tools, and multi-model workflows.",[12,21,28,36,43,50,57,65,72,79,87],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"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","Kimi K2.7 adds a fresh option for long-context, Chinese, and agentic coding workflows.","model-release","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781791374284-re3e.png","en","2026-06-18T14:02:25.334347+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":17,"image_url":26,"cover_image":26,"language":19,"created_at":27},"e7f37851-7b5f-429c-9a71-3e4a2d4b9c70","mimo-v2-flash-openrouter-benchmarks-pricing-en","MiMo-V2-Flash hits top open-source SWE-bench scores","Xiaomi’s MiMo-V2-Flash tops open-source SWE-bench scores while OpenRouter lists it at $0.10\u002F$0.30 per 1M tokens.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781321563162-27yb.png","2026-06-13T03:32:17.731154+00:00",{"id":29,"slug":30,"title":31,"summary":32,"category":33,"image_url":34,"cover_image":34,"language":19,"created_at":35},"072db467-c073-42e5-b723-5b1888304902","mimo-v25-pro-turns-agent-work-into-one-api-call-en","MiMo-V2.5-Pro turns agent work into one API call","A practical breakdown of Xiaomi’s MiMo-V2.5-Pro on OpenRouter, plus a copy-ready setup for agentic tool workflows.","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781320696191-vzza.png","2026-06-13T03:17:48.852122+00:00",{"id":37,"slug":38,"title":39,"summary":40,"category":17,"image_url":41,"cover_image":41,"language":19,"created_at":42},"768b8352-3611-4527-99b1-dd1c87c45fea","claude-opus-4-8-api-pricing-benchmarks-openrouter-en","Claude Opus 4.8: $5\u002F$25 API pricing, 1M context","OpenRouter lists Anthropic’s Claude Opus 4.8 at $5 per million input tokens and $25 per million output tokens with a 1M-token context window.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781086675114-cu4j.png","2026-06-10T10:17:25.12768+00:00",{"id":44,"slug":45,"title":46,"summary":47,"category":33,"image_url":48,"cover_image":48,"language":19,"created_at":49},"9db77f6f-0d31-4686-86d9-16eb9615633d","ollama-best-free-ai-path-2026-en","Ollama is the best free AI path in 2026 for real work","Ollama is the strongest free AI option in 2026 for teams that need private, unlimited, local inference.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781056075632-qzpq.png","2026-06-10T01:47:25.10989+00:00",{"id":51,"slug":52,"title":53,"summary":54,"category":17,"image_url":55,"cover_image":55,"language":19,"created_at":56},"12af5a0d-1bbf-4a50-a391-b53f8003f234","gemini-35-flash-pricing-benchmarks-en","Gemini 3.5 Flash Pricing, Context, Benchmarks","Google’s Gemini 3.5 Flash costs $1.50 per million input tokens and $9 output, with a 1,048,576-token context window.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780840981235-e7hm.png","2026-06-07T14:02:30.280485+00:00",{"id":58,"slug":59,"title":60,"summary":61,"category":62,"image_url":63,"cover_image":63,"language":19,"created_at":64},"f89355bb-7095-4791-8bcf-13303ccd7e6b","why-model-release-feeds-matter-more-en","Why model-release feeds matter more than model-launch posts","Model-release feeds are the best way to track real AI progress and pricing shifts.","industry","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780611464470-pz16.png","2026-06-04T22:17:15.959267+00:00",{"id":66,"slug":67,"title":68,"summary":69,"category":62,"image_url":70,"cover_image":70,"language":19,"created_at":71},"81a4ae33-2e6b-4cf6-918e-9e80091a9768","chinese-ai-models-tokens-price-jpmorgan-2026-en","Chinese AI models are winning on tokens and price","JPMorgan data shows Chinese AI models taking over OpenRouter usage in 2026, driven by lower prices, open weights, and agentic workflows.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780428789317-thlj.png","2026-06-02T19:32:37.708667+00:00",{"id":73,"slug":74,"title":75,"summary":76,"category":33,"image_url":77,"cover_image":77,"language":19,"created_at":78},"00b87494-6cb6-4997-9a39-2478720de55f","nous-portal-lets-hermes-use-one-login-en","Nous Portal lets Hermes use one login","I break down Nous Portal so you can wire Hermes Agent to one subscription, one key, and bundled tools instead of provider sprawl.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779413787835-cazx.png","2026-05-22T01:35:58.849621+00:00",{"id":80,"slug":81,"title":82,"summary":83,"category":84,"image_url":85,"cover_image":85,"language":19,"created_at":86},"a62c627d-73cd-484d-b0d2-e8da92f6c59b","how-to-run-openclaw-with-open-source-models-en","How to Run OpenClaw with Open-Source Models","Set up OpenClaw with open-source LLMs like Kimi-K2.5 through OpenRouter.","ai-agent","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777975843199-wtuz.png","2026-05-05T10:10:24.244006+00:00",{"id":88,"slug":89,"title":90,"summary":91,"category":17,"image_url":92,"cover_image":93,"language":19,"created_at":94},"f063d8d1-41d1-4de4-8ebc-6c40511b9369","xiaomi-mimo-v2-pro-1t-moe-agents-en","Xiaomi MiMo-V2-Pro: 1T MoE Model for Agents","Xiaomi’s MiMo-V2-Pro packs 1T parameters, 42B active, and 1M context, with SWE-bench results close to Claude Sonnet 4.6.",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1774619185536-iewn.png","2026-03-28T03:06:19.238032+00:00",11]