# Qwen Code

25 Hacker News commenters recommended Qwen Code and 10 criticized it, November 2025 to November 2026. It was recommended in 10 of 13 months. It meets the Hacker Approved badge rule.

**Verdict:** Recommended as a free-tier coding agent that works well with Qwen models and uses fewer tokens than Claude Code; the common caveat is failed tool calls.

## Why people recommend it

- Generous free tier (5 comments): "Qwen CLI is a great alternative if you want an OpenAI-compatible API with a generous free tier" ([source](https://news.ycombinator.com/item?id=46691372)) "allows a thousand free requests a day. In practice it's about ~300M tokens for me" ([source](https://news.ycombinator.com/item?id=47623102)) "You can give their hosted versions a go using one of the free clis." ([source](https://news.ycombinator.com/item?id=46493642))
- Capable on hobby and game projects (4 comments): "it was powerful enough to complete 95% of a small hobby project involving coding, reverse engineering and debugging" ([source](https://news.ycombinator.com/item?id=47794211)) "Together with Qwen Code (fork of Gemini) it is actually pretty capable." ([source](https://news.ycombinator.com/item?id=46897429)) "I made this 3D game in a day on the same setup with Qwen Code as agent" ([source](https://news.ycombinator.com/item?id=49736415))
- Works well with Qwen models (3 comments): "I tried finally Qwen Code CLI assuming that it would run well with a Qwen model and it does." ([source](https://news.ycombinator.com/item?id=47097289)) "the tool use with Qwen models at least has been great" ([source](https://news.ycombinator.com/item?id=47838414)) "perform best in their own harness, Qwen-Code" ([source](https://news.ycombinator.com/item?id=47252913))
- Fast and token efficient (2 comments): "it seems a heck of a lot faster that Claude and feels better to work with" ([source](https://news.ycombinator.com/item?id=48167934)) "since it is far more token efficient than claude-code" ([source](https://news.ycombinator.com/item?id=48049546))

## What people warn about

- Failed tool calls (2 comments): "A common problem I keep running into is failed tool calls, regardless of the model." ([source](https://news.ycombinator.com/item?id=48883634)) "it often fails during `write_file` tool calls, even with Qwen Code" ([source](https://news.ycombinator.com/item?id=48884516))
- Rated behind rival coding agents (2 comments): "far superior to Qwen CLI in my opinion" ([source](https://news.ycombinator.com/item?id=46352475)) "Codex is 2x better than Qwen code" ([source](https://news.ycombinator.com/item?id=47320576))

## Alternatives hackers recommend

- [Hax coding agent](https://hackerapproved.com/p/hax.md): 28 recommend
- [Roo Code](https://hackerapproved.com/p/roo-code.md): 26 recommend
- [MiMo Code](https://hackerapproved.com/p/mimo-code.md): 24 recommend
- [GitHub Copilot Chat](https://hackerapproved.com/p/github-copilot-chat.md): 10 recommend
- [Mysti](https://hackerapproved.com/p/mysti.md): 10 recommend

## Cite as

Hacker Approved, "Qwen Code", https://hackerapproved.com/p/qwen-code/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).
