{"slug": "i-built-2-telegram-bots-with-qwen3-8-max-and-the-results-were-seriously", "title": "🤖 I Built 2 Telegram Bots with Qwen3.8-Max — and the Results Were Seriously Impressive", "summary": "A developer built two Telegram bots using Qwen3.8-Max, an AI model from Alibaba, and reported impressive results. The bots, one for car repair appointment booking and one for kitchen pricing, were developed in Go and used GPT-4.1-mini as the brain. The developer noted that Qwen3.8-Max used about 12.8 million tokens across 400 API requests, compared to over 15 million tokens for DeepSeek V4 Flash Latest on similar tasks.", "body_md": "💬 Following up on the [story about the release of Qwen3.8-Max](https://t.me/vic_makes_ai/1082), I finally tried it on real-world tasks.\n\nSpecifically, for building **AI consultants for text channels** (messengers) in my favorite programming language — **Go**.\n\nSpoiler: **it’s really good, especially for such a low price per 1M tokens**! 😍\n\nAs a result, I built 2 demo Telegram bots, where **GPT-4.1-mini** acts as the brains 👇\n\n1️⃣ [A bot for qualifying a customer and booking a car repair appointment](https://t.me/shostak_dev_demo_autoservice_bot), which asks for details about the vehicle and the issue, answers questions about service pricing, and schedules a convenient visit time.\n\n2️⃣ [A bot for calculating kitchen pricing for furniture companies](https://t.me/shostak_dev_demo_kitchen_bot), which уточняет kitchen parameters through guiding questions, calculates the cost, sends the final estimate, and books the client at the company office for a detailed design session.\n\nBefore implementation, of course, I wrote a detailed spec for each of these bots and connected MCP Context7.\n\nI also had to make 1–2 corrective prompts for code style and some business-logic details... but otherwise, Qwen3.8-Max worked fully autonomously in the engineering loop (questioning itself at every stage and adjusting its own reasoning and code).\n\nToken usage (input + output) totaled\n\n~12.8 million, across about 400 API requests to the Chinese model. That’s seriously impressive! For comparison, I ran the same task through DeepSeek V4 Flash Latest: with similar output results, it used over15 milliontokens.\n\nBy the way, the whole development process was done in the next-gen [AI IDE Kodik](https://kodik.ru/signup?ref=TVAF2JRH), by our local guys — **ArchiTech AI**.\n\nHighly recommend downloading and trying it. Not an Ad! I’ve been using it for over a month now, and it’s truly a very high-quality product, especially in the era of account bans from Anthropic and OpenAI 😏\n\n...and soon, a local model called **Qwen3.8-27b** is also expected to drop, which Alibaba has promised to release any day now... that’s definitely something that can make the big AI model vendors nervous!\n\n😉 *And if you need to design, build, and launch an AI solution for you and/or automate your business processes, feel free to DM me: t.me/koddr*\n\n💡 **Interesting to read?** Follow me on all platforms so you don’t miss new posts 👉 [Telegram](https://t.me/vic_makes_ai), [VK](https://vk.ru/vic_makes_ai), [TenChat](https://tenchat.ru/vic_makes_ai), [Dzen](https://dzen.ru/vic_makes_ai), [Teletype](https://teletype.in/@vic_makes_ai), or [vc.ru](https://vc.ru/id6063554)", "url": "https://wpnews.pro/news/i-built-2-telegram-bots-with-qwen3-8-max-and-the-results-were-seriously", "canonical_source": "https://dev.to/vic_makes_ai/i-built-2-telegram-bots-with-qwen38-max-and-the-results-were-seriously-impressive-4ceg", "published_at": "2026-08-16 18:20:52+00:00", "updated_at": "2026-08-16 18:42:35.623109+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "ai-tools", "developer-tools"], "entities": ["Qwen3.8-Max", "Alibaba", "GPT-4.1-mini", "DeepSeek V4 Flash Latest", "Telegram", "Go", "ArchiTech AI", "Kodik"], "alternates": {"html": "https://wpnews.pro/news/i-built-2-telegram-bots-with-qwen3-8-max-and-the-results-were-seriously", "markdown": "https://wpnews.pro/news/i-built-2-telegram-bots-with-qwen3-8-max-and-the-results-were-seriously.md", "text": "https://wpnews.pro/news/i-built-2-telegram-bots-with-qwen3-8-max-and-the-results-were-seriously.txt", "jsonld": "https://wpnews.pro/news/i-built-2-telegram-bots-with-qwen3-8-max-and-the-results-were-seriously.jsonld"}}