# Claude Code vs Qwen Code

> Claude Code vs Qwen Code: Claude Code is our pick, leading for beginners and enterprise. They split on editor support and project rules files. Verified October.

![Claude Code logo](https://www.versusref.com/logos/claude-code.png) ![Qwen Code logo](https://www.versusref.com/logos/qwen-code.png)

Claude Code (Terminal-first coding agent included in Claude Pro/Max/Team/Enterprise plans or billed via API; also IDE extension, desktop app and cloud sessions (cloud_agent).) and Qwen Code (Open-source multi-provider agent from an open-weight model lab; also desktop app, web UI and VS Code/JetBrains/Zed plugins) are AI coding agents platforms, priced from $17/mo and $0 + your model API bill respectively. Below: the bottom line, verified head-to-head facts, and real production costs.

AI coding agents platforms · 39 facts compared · all sourced · pricing verified Oct 2, 2026

## Bottom line

Claude Code takes four of seven use cases: Beginners, Enterprise, Terminal Workflows and VS Code. It publishes a clear price, $20/mo or $17/mo billed annually, and a full enterprise record with self-hosted or VPC deployment, SSO on Team and Enterprise, zero data retention, SOC 2 and audit logs, none of which Qwen Code publishes. In the shell, it adds background agents to its terminal CLI. Qwen Code wins Free Plans, Local Models and Open Source on the strength of its Apache-2.0 license and local model support, so it suits teams that want an open, self-run agent. For most buyers, Claude Code is the more complete package.

## Verdict summary

| Use case | Winner | Why |
| --- | --- | --- |
| Beginners | Claude Code | A predictable bill matters most for newer developers. |
| Enterprise | Claude Code | Claude Code publishes a full enterprise record and Qwen Code publishes none of it. |
| Free Plans | Qwen Code | Neither tool has a free plan: Claude Code is not included on the Free plan, and Qwen Code's free tier was discontinued on 2026-04-15. |
| Local Models | Qwen Code | Local model support is the deciding factor, and Qwen Code states it runs local models while Claude Code does not publish that. |
| Open Source | Qwen Code | The license matters most here. |
| Terminal Workflows | Claude Code | Both are built for the shell: Claude Code lists a terminal CLI plus nine more surfaces, and Qwen Code lists a CLI, a desktop app and three more. |
| VS Code | Claude Code | Both support VS Code: Claude Code lists VS Code and Cursor through its VS Code extension, and Qwen Code lists VS Code, Zed and JetBrains. |

## Claude Code vs Qwen Code: head-to-head facts

| Fact | Claude Code | Qwen Code | Verified |
| --- | --- | --- | --- |
| How usage is metered | Time windows + per-token ([source](https://claude.com/pricing)) | Own API key ([source](https://qwenlm.github.io/qwen-code-docs/en/users/configuration/auth/)) | Oct 2 |
| What the free plan allows | Claude Code not included on the Free plan ([source](https://claude.com/pricing)) | None: Qwen OAuth free tier discontinued 2026-04-15 ([source](https://qwenlm.github.io/qwen-code-docs/en/users/configuration/auth/)) | Oct 2 |
| Cheapest paid plan (monthly) | $20 ([source](https://claude.com/pricing)) | n/a | Oct 2 |
| Top individual plan | $200 ([source](https://support.claude.com/en/articles/11049741-what-is-the-max-plan)) | n/a | Oct 2 |
| Rate-limit window | Rolling five-hour session window + weekly limit ([source](https://claude.com/pricing)) | n/a | Oct 2 |
| Bring your own API key | true ([source](https://code.claude.com/docs/en/overview)) | Yes ([source](https://qwenlm.github.io/qwen-code-docs/en/users/configuration/auth/)) | Oct 2 |
| Models available | Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5 +1 more ([source](https://code.claude.com/docs/en/model-config)) | n/a | Oct 2 |
| Pick the model per task | ✓  Yes ([source](https://code.claude.com/docs/en/model-config)) | ✓  Yes ([source](https://qwenlm.github.io/qwen-code-docs/en/users/configuration/auth/)) | Oct 2 |
| Runs local models | n/a | ✓  Ollama, vLLM ([source](https://github.com/QwenLM/qwen-code)) | Oct 2 |
| Where it runs | Terminal CLI +9 more ([source](https://code.claude.com/docs/en/overview)) | CLI, desktop app (macOS/Windows/Linux) +3 more ([source](https://github.com/QwenLM/qwen-code)) | Oct 2 |
| Autonomous multi-file edits | ✓  Yes ([source](https://code.claude.com/docs/en/overview)) | ✓  Yes ([source](https://github.com/QwenLM/qwen-code)) | Oct 2 |
| Runs terminal commands | ✓  Yes ([source](https://code.claude.com/docs/en/permission-modes)) | ✓  Yes ([source](https://qwenlm.github.io/qwen-code-docs/en/users/overview/)) | Oct 2 |
| Background / cloud agents | ✓  Yes ([source](https://code.claude.com/docs/en/claude-code-on-the-web)) | n/a | Oct 2 |
| Opens PRs from issues | ✓  Yes ([source](https://code.claude.com/docs/en/github-actions)) | n/a | Oct 2 |
| MCP support | ✓  Yes ([source](https://code.claude.com/docs/en/mcp)) | ✓  Yes ([source](https://github.com/QwenLM/qwen-code)) | Oct 2 |
| Trains on your code? | Consumer (Free, Pro, Max): user choice ([source](https://code.claude.com/docs/en/data-usage)) | n/a | Oct 2 |
| Zero data retention option | ✓  Yes ([source](https://code.claude.com/docs/en/data-usage)) | n/a | Oct 2 |
| Self-hosted / VPC deployment | ✓  Yes ([source](https://code.claude.com/docs/en/self-hosted-environments-deploy)) | n/a | Oct 2 |
| License | Proprietary ('SEE LICENSE IN README.md' on the npm package) ([source](https://www.npmjs.com/package/@anthropic-ai/claude-code)) | Apache-2.0 ([source](https://github.com/QwenLM/qwen-code)) | Oct 2 |
| Supported model providers | n/a | OpenAI, Anthropic, Gemini, Qwen APIs +2 more ([source](https://github.com/QwenLM/qwen-code)) | Oct 2 |

## Claude Code vs Qwen Code pricing: true cost at 3 usage tiers

Real monthly cost at 3 developer profiles: hobbyist (~5 h/week), full-time developer (~25 h/week of daily agent use), team of 5. Most vendors do not publish how much usage a plan covers, so the full-time row spans the cheapest to the top individual plan unless the vendor publishes its own guidance for daily users. Bring-your-own-key and open-source agents show the model bill you pay the provider, never $0.

| Volume | Buyer | Claude Code | Qwen Code | Note |
| --- | --- | --- | --- | --- |
| ~5 h/week of agent use | Hobbyist | $17/mo | Free + your model API bill | Side projects and evenings. Priced at each vendor's cheapest paid plan (annual billing where offered), the tier every vendor sells for light use. |
| ~25 h/week, daily multi-file agent tasks | Full-time developer | $17-$200/mo | Free + your model API bill | Daily agent use. Most vendors do not publish how much usage a plan covers, so this shows the span from the cheapest to the top individual plan; where a vendor publishes its own guidance for daily agent users, that figure is used instead. |
| 5 seats | Team of 5 | $125/mo | Free + your model API bill | Priced from each vendor's own team plan: per-seat prices x 5, flat team plans as published. A tool with no published team price shows that rather than a guess. |

## Claude Code vs Qwen Code: verdicts by use case

### Beginners → Claude Code

A predictable bill matters most for newer developers. Claude Code publishes a cheapest paid plan of $20/mo, or $17/mo billed annually, while Qwen Code publishes no paid plan of its own and is metered through your own API key, which makes costs harder to predict. Neither publishes an entry-tier usage allowance, and neither has a usable free plan: Claude Code is not included on the Free plan, and Qwen Code's free tier was discontinued on 2026-04-15. Both offer checkpoints and rollback, though Qwen Code's is vendor claimed.

### Enterprise → Claude Code

Claude Code publishes a full enterprise record and Qwen Code publishes none of it. On training, Claude Code gives consumer plans a user choice; Qwen Code publishes no training policy. Claude Code offers a self-hosted or VPC deployment, SSO on Team and Enterprise, a zero data retention option, SOC 2 and admin audit logs. Qwen Code does not publish self-hosting, SSO, zero retention, SOC 2 or audit logs, so a security review has nothing to work with.

### Free Plans → Qwen Code

Neither tool has a free plan: Claude Code is not included on the Free plan, and Qwen Code's free tier was discontinued on 2026-04-15. Both support bringing your own API key. The difference is what you can do without paying a subscription: Qwen Code runs local models, so it can do real work at no per-token cost, while Claude Code does not publish local model support and its cheapest paid plan is $20/mo.

### Local Models → Qwen Code

Local model support is the deciding factor, and Qwen Code states it runs local models while Claude Code does not publish that. Qwen Code also lists OpenAI, Anthropic, Gemini and Qwen APIs among its providers and is Apache-2.0 licensed, while Claude Code is proprietary. Both support bringing your own API key. For running against models on your own machine, Qwen Code is the clear pick.

### Open Source → Qwen Code

The license matters most here. Qwen Code is Apache-2.0 licensed, while Claude Code is proprietary, referring to its README on the npm package. Qwen Code calls OpenAI, Anthropic, Gemini and Qwen APIs among other providers, runs local models, and has 28,300 GitHub stars. If you want a hosted option, the Alibaba Cloud Coding Plan Pro costs $50/mo.

### Terminal Workflows → Claude Code

Both are built for the shell: Claude Code lists a terminal CLI plus nine more surfaces, and Qwen Code lists a CLI, a desktop app and three more. Both run terminal commands, support MCP and read project rules files, CLAUDE.md for Claude Code and QWEN.md or AGENTS.md for Qwen Code. The difference is background or cloud agents, which Claude Code offers and Qwen Code does not publish, useful for CI-style work away from the laptop. That gives Claude Code a narrow edge.

### VS Code → Claude Code

Both support VS Code: Claude Code lists VS Code and Cursor through its VS Code extension, and Qwen Code lists VS Code, Zed and JetBrains. Both make autonomous multi-file edits. Rollback separates them slightly: Claude Code's checkpoints and rollback are verified, while Qwen Code's are vendor claimed. Neither publishes codebase indexing or entry-tier included usage. Claude Code's support for a VS Code fork and its verified rollback give it a narrow edge for staying in VS Code.

## Claude Code vs Qwen Code: common questions

### Is Claude Code cheaper than Qwen Code?

It depends on how you run Qwen Code. Claude Code's cheapest paid plan is $20/mo, or $17/mo billed annually. Qwen Code has no plan of its own and is metered through your own API key, so cost depends on your provider; it can also run local models. If you want Qwen's hosted option, the Alibaba Cloud Coding Plan Pro costs $50/mo.

### Claude Code vs Qwen Code: which is better for beginners?

Claude Code is the safer pick for most beginners because its bill is predictable: its cheapest paid plan is $20/mo, or $17/mo billed annually. Qwen Code is metered through your own API key and its free tier was discontinued on 2026-04-15. Claude Code is also not included on the Free plan. Both offer checkpoints and rollback, though Qwen Code's is vendor claimed.

### Is Claude Code or Qwen Code open source?

Qwen Code is Apache-2.0 licensed and has 28,300 GitHub stars. Claude Code is proprietary, with its npm package pointing to the license in its README.

### Can Claude Code or Qwen Code run local models?

Qwen Code runs local models and supports providers including OpenAI, Anthropic, Gemini and Qwen APIs. Claude Code does not publish local model support. Both support bringing your own API key.

### Is Claude Code or Qwen Code better for enterprise teams?

Claude Code offers a self-hosted or VPC deployment, SSO on Team and Enterprise, zero data retention, SOC 2 and admin audit logs, plus a team plan at $25/user/mo and an Enterprise plan through contact sales. Qwen Code does not publish these enterprise controls.

### Do Claude Code and Qwen Code have a free plan?

No. Claude Code is not included on the Free plan, and Qwen Code's OAuth free tier was discontinued on 2026-04-15. Qwen Code is metered through your own API key instead.

### What benchmark has Qwen Code published?

Qwen Code reports a SWE-bench Verified average of 77.80%, with an 84.6% pass rate, across 500 cases. This is a vendor claim.

### What are Claude Code's usage limits?

Claude Code uses a rolling five-hour session window plus a weekly limit. Beyond the plan, usage credits are billed at standard API rates. Its top individual plan is $200/mo.

### Which models does Claude Code use?

Claude Code offers Claude Fable 5.1, Claude Opus 5.5 and Claude Sonnet 5.5, among others, with Claude Opus 5.5 as the default. You can pick the model per task, and it publishes a 1,000,000 token maximum context.

Source: https://www.versusref.com/coding-agents/claude-code-vs-qwen-code/