Qwen Code
Hacker ApprovedShares rank 10 of 41 coding agents by recommenders
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.
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.
35 people gave an opinion
- recommend it
- 25
- criticize it
- 10
- approval share
- 71%
Recommended in 10 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 25 people recommend itNeeds 10 or more, met.
- 2.5 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 10 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Generous free tier
“Qwen CLI is a great alternative if you want an OpenAI-compatible API with a generous free tier”
Comment from 20 Jan 2026 in “Show HN: AgentCommander - workflow engine for evolutionary code optimization” “allows a thousand free requests a day. In practice it's about ~300M tokens for me”
Comment from 3 Apr 2026 in “Qwen3.6-Plus: Towards Real World Agents” “You can give their hosted versions a go using one of the free clis.”
Comment from 4 Jan 2026 in “NSFW Acronyms for Programmers (Free eBook)” - Comment from 1 Nov 2025 in “Claude Code can debug low-level cryptography”
- Comment from 13 Dec 2025 in “Ask HN: How can I get better at using AI for programming?”
Capable on hobby and game projects
“it was powerful enough to complete 95% of a small hobby project involving coding, reverse engineering and debugging”
Comment from 16 Apr 2026 in “Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All” “Together with Qwen Code (fork of Gemini) it is actually pretty capable.”
Comment from 5 Feb 2026 in “Claude Code: connect to a local model when your quota runs out” “I made this 3D game in a day on the same setup with Qwen Code as agent”
Comment from 17 Sep 2026 in “Xiaomi Mimo 2.6 live post-training dashboard” - Comment from 8 Oct 2026 in “Why isn't the industry freaking out about DeepSeek 4.1 Flash?”
Works well with Qwen models
“I tried finally Qwen Code CLI assuming that it would run well with a Qwen model and it does.”
Comment from 21 Feb 2026 in “Ggml.ai joins Hugging Face to ensure the long-term progress of Local AI” “the tool use with Qwen models at least has been great”
Comment from 20 Apr 2026 in “Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving” “perform best in their own harness, Qwen-Code”
Comment from 4 Mar 2026 in “Something is afoot in the land of Qwen” Fast and token efficient
“it seems a heck of a lot faster that Claude and feels better to work with”
Comment from 17 May 2026 in “Zerostack – A Unix-inspired coding agent written in pure Rust” “since it is far more token efficient than claude-code”
Comment from 7 May 2026 in “ZAYA1-8B: An 8B Moe Model with 760M Active Params Matching DeepSeek-R1 on Math”
What people warn about
Each mark is one comment
Failed tool calls
“A common problem I keep running into is failed tool calls, regardless of the model.”
Comment from 12 Jul 2026 in “Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k” “it often fails during `write_file` tool calls, even with Qwen Code”
Comment from 12 Jul 2026 in “Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k” Rated behind rival coding agents
“far superior to Qwen CLI in my opinion”
Comment from 22 Dec 2025 in “A guide to local coding models” “Codex is 2x better than Qwen code”
Comment from 10 Mar 2026 in “No, it doesn't cost Anthropic $5k per Claude Code user”
Other coding agents people recommend
The four most recommended other coding agents, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| GitHub Copilot | 571 | 993 | 37% | 12 | 1 yr46 owners | — |
| oh-my-pi | 104 | 28 | 79% | 9 | 2 mo5 owners | Approved |
| Grok Build CLI | 66 | 114 | 37% | 6 | — | — |
| DeepSeek Harness | 63 | 28 | 69% | 4 | 1 mo5 owners | Approved |
| Qwen CodeThis page | 25 | 10 | 71% | 10 | — | Approved |
What people said
34 of the 42 comments that mention it, newest first. Each links to the original comment.
“because it made life miserable for other OpenCode users”
“I made this 3D game with it in two days using Qwen Code as agent”
“slightly faster and better quality output from qwencloud”
“I made this 3D game in a day on the same setup with Qwen Code as agent”
“Having audited one code harness (Qwen Code) in the past on telemetry.”
“Tried it with a coding plan and it 401'd.”
“it often fails during `write_file` tool calls, even with Qwen Code”
“A common problem I keep running into is failed tool calls, regardless of the model.”
“it seems a heck of a lot faster that Claude and feels better to work with”
“there are many non-US harnesses (Qwen code) that are available”
“qwen code (non local) was the only time I managed to lose some work as it got confused when I ran out of tokens”
“since it is far more token efficient than claude-code”
“the tool use with Qwen models at least has been great”
“it was powerful enough to complete 95% of a small hobby project involving coding, reverse engineering and debugging”
“Once it can search for factual information online the smaller model size becomes less noticeable”
“allows a thousand free requests a day. In practice it's about ~300M tokens for me”
“Codex is 2x better than Qwen code”
“Right now I'm getting good cost/benefit results with the qwen cli with coder-model in the cloud”
“fired up the qwen code CLI and gave it two prompts”
“perform best in their own harness, Qwen-Code”
“qwen-cli, Qwen, in general, has a tendency to pendulate too much”
“I am really annoyed by the silly jokes”
“I tried finally Qwen Code CLI assuming that it would run well with a Qwen model and it does.”
“I very much like a) to have an idea how much tokens I use”
“Together with Qwen Code (fork of Gemini) it is actually pretty capable.”
“maybe try Qwen CLI (was planning to make a guide for it as well)”
“Qwen CLI is a great alternative if you want an OpenAI-compatible API with a generous free tier”
“You can give their hosted versions a go using one of the free clis.”
“far superior to Qwen CLI in my opinion”
“use Gemini or Qwen if you want to do it for free”
“it gave me a better sense of reasoning and structure”
“it does most of what I want with the models of my choice”
“none of the "supported" tools I tried were able to use it”
“They are also free if you use Gemini CLI or Qwen Code.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.