cd /news/artificial-intelligence/i-built-2-telegram-bots-with-qwen3-8… · home topics artificial-intelligence article
[ARTICLE · art-98979] src=dev.to ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

🤖 I Built 2 Telegram Bots with Qwen3.8-Max — and the Results Were Seriously Impressive

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.

read2 min views1 publishedAug 16, 2026

💬 Following up on the story about the release of Qwen3.8-Max, I finally tried it on real-world tasks. Specifically, for building AI consultants for text channels (messengers) in my favorite programming language — Go.

Spoiler: it’s really good, especially for such a low price per 1M tokens! 😍

As a result, I built 2 demo Telegram bots, where GPT-4.1-mini acts as the brains 👇

1️⃣ A bot for qualifying a customer and booking a car repair appointment, which asks for details about the vehicle and the issue, answers questions about service pricing, and schedules a convenient visit time.

2️⃣ A bot for calculating kitchen pricing for furniture companies, 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.

Before implementation, of course, I wrote a detailed spec for each of these bots and connected MCP Context7.

I 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).

Token usage (input + output) totaled ~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.

By the way, the whole development process was done in the next-gen AI IDE Kodik, by our local guys — ArchiTech AI.

Highly recommend down 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 😏

...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!

😉 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

💡 Interesting to read? Follow me on all platforms so you don’t miss new posts 👉 Telegram, VK, TenChat, Dzen, Teletype, or vc.ru

── more in #artificial-intelligence 4 stories · sorted by recency
promptcube3.com · · #artificial-intelligence
Qwen 3.
── more on @qwen3.8-max 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/i-built-2-telegram-b…] indexed:0 read:2min 2026-08-16 ·