
Qwen Code
situationalOpen-source terminal coding agent from Alibaba, forked from Gemini CLI.
Visit github.com →> **Qwen Code** — situational > Verified 2026-08-24 > Limitation: Free hosted inference was cut to roughly 100 requests/day in April 2026. > > https://noemium.com/tools/qwen-code/Add to kitOpen in NoemiumFact-check this catalog entry for Qwen Code (coding). Verdict: situational Verdict text: The CLI is free and open source, so it costs nothing to try with your own keys. The hosted free tier is basically gone, and the paid coding plan is mid-priced. Best for teams that already use Qwen or want a Gemini-CLI-like workflow. Limitations: - Free hosted inference was cut to roughly 100 requests/day in April 2026. - Less mature agent ecosystem than Claude Code or Kimi Code. - Configuration surface is larger than single-vendor tools. - Strongest when paired with Qwen models; other providers are supported but less optimized. Receipts: https://github.com/QwenLM/qwen-code https://aicoolies.com/reviews/qwen-code-review https://aiidelist.com/ide/qwen-code https://inventivehq.com/blog/qwen-code-still-free-2026-shutdown Last verified: 2026-08-24 Find outdated prices, wrong claims, or missing limitations. Cite primary sources (docs, pricing pages, benchmarks, model cards). Do not use marketing pages.[](https://noemium.com/tools/qwen-code/)
ledger entry · observed by @whysanesanders
The CLI is free and open source, so it costs nothing to try with your own keys. The hosted free tier is basically gone, and the paid coding plan is mid-priced. Best for teams that already use Qwen or want a Gemini-CLI-like workflow.
Strengths
- CLI is free and open source — costs nothing to try with your own keys.
- Gemini-CLI-shaped workflow if that is already how you work.
- Strongest on Qwen models; BYOK keeps the hosted plan optional.
Known limitations
- Free hosted inference was cut to roughly 100 requests/day in April 2026.
- Less mature agent ecosystem than Claude Code or Kimi Code.
- Configuration surface is larger than single-vendor tools.
- Strongest when paired with Qwen models; other providers are supported but less optimized.
Use it when
- Teams already on Qwen who want a terminal agent, not another IDE.
- Self-hosted / BYOK coding where a $50 plan is the fallback, not the start.
Skip it when
- You expected a generous hosted free tier — that was cut in April 2026.
- You need the mature agent ecosystem around Claude Code or Kimi Code.
- You do not want to operate a larger config surface.
Buy-check
- ·Price — freemium, CLI is free/open source; hosted free tier restricted to ~100 requests/day as of April 2026; Coding Plan Pro ~$50/month (~90K requests/month); BYOK available as of 2026-08-24. Open the pricing page, not a screenshot.
- ·Free tier — Free tier exists — burn it first.
- ·Cancel fallout — What happens to your data/projects on cancel — check the ToS, not the FAQ.
- ·Seat math — Per-seat pricing multiplies quietly. Count seats before the annual plan.
- ·Who skips it — Also skipped when: You expected a generous hosted free tier — that was cut in April 2026.; You need the mature agent ecosystem around Claude Code or Kimi Code..
Price trailchangelog →
No price move in this repo yet.
Facts
- pricing
- freemium1
- price note
- CLI is free/open source; hosted free tier restricted to ~100 requests/day as of April 2026; Coding Plan Pro ~$50/month (~90K requests/month); BYOK available
- free tier
- yes
- open source
- yes
- api
- yes
- self-host
- yes
- category
- coding
- evidence
- source-verified
- Models
- BYOK
Data: trains on inputs unknown · local processing yes
Sources
- 1github.com/QwenLM/qwen-code[snapshot]
- 2aicoolies.com/reviews/qwen-code-review[snapshot]
- 3aiidelist.com/ide/qwen-code[snapshot]
- 4inventivehq.com/blog/qwen-code-still-free-2026-shutdown[snapshot]
No source, no number.
Similar joball alternatives →
| tool | verdict | price | oss | self-host |
|---|---|---|---|---|
| Qwen Code | situational | freemium | yes | yes |
| Claude Code | ship | paid | no | no |
| Cursor | ship | freemium | no | no |
| Aider | ship | free | yes | yes |
Facts from the catalog files — not scores you can buy. Quality and speed stay in the briefing, not in a fake 1–5 grid.
Claude Codeanchor
Anthropic's terminal agent that edits, runs and tests code in your repo.
API
paidincluded in Claude Pro $20/mo ($17/mo yearly) and Max 5x $100 / Max 20x $200; shares the plan usage pool; extra usage at API rates
Cursoranchor
AI-first code editor (VS Code fork) with agent mode and inline edits.
FREE TIER
freemiumHobby free; Pro $20/mo; Pro+ $60/mo (3× Agent limits); Ultra $200/mo (20×); Teams from $40/user/mo
Aider
Open-source pair programming in the terminal — git-native, works with any model.
OSSAPIFREE TIER
freefree, open source; bring your own API key