--- format: "aidr-story-markdown/v1" id: "6d78c9b6cbe5da726b6be889ca358fbf073b84ebf3cf8aa818925850225d87c9" canonical_url: "https://aidr.today/6d78c9b6?lang=en" title: "Meituan Integrates LongCat-2.5 AI Model Into Agentic Coding Tools" lang: "en" requested_lang: "en" available_langs: ["en"] translation_fallback: null fallback_fields: [] published_at: "2026-11-03T00:23:04.000Z" category: "Tools" topics: ["agent","devtools","coding"] source_urls: ["https://marketbrief.now/ai/meituan-integrates-longcat-25-ai-model-into-agentic-coding-tools-eb8af2e4","https://huggingnews.com/ai/meituan-integrates-longcat-25-ai-model-into-agentic-coding-tools-eb8af2e4"] summary: "The Chinese company's newest multimodal model has been made available for use inside developer tools such as Claude Code, Codex, and Hermes to assist with high-complexity software projects. To support these agentic tasks, LongCat-2.5 now features a 1M-token context window and is offered at promotional API rates of $0.30 per million uncached input tokens and $1.20 per million output tokens. The system utilizes a mixture-of-experts architecture with 1.6T total parameters, of which approximately 48B are active during operations. Designed for long-horizon tasks including 3D creative design and visual coding, the model is now available to developers via APIs and is positioned as a competitor to other large-scale systems like GPT-5.5 and Claude-Opus-5." --- # Meituan Integrates LongCat\-2\.5 AI Model Into Agentic Coding Tools > [Open the canonical story]() **Published:** 2026-11-03T00:23:04.000Z **Category:** Tools **Topics:** agent, devtools, coding ## Summary The Chinese company's newest multimodal model has been made available for use inside developer tools such as Claude Code, Codex, and Hermes to assist with high\-complexity software projects\. To support these agentic tasks, LongCat\-2\.5 now features a 1M\-token context window and is offered at promotional API rates of $0\.30 per million uncached input tokens and $1\.20 per million output tokens\. The system utilizes a mixture\-of\-experts architecture with 1\.6T total parameters, of which approximately 48B are active during operations\. Designed for long\-horizon tasks including 3D creative design and visual coding, the model is now available to developers via APIs and is positioned as a competitor to other large\-scale systems like GPT\-5\.5 and Claude\-Opus\-5\. ## Sources - [Story source]() - [Story source]()