# Qwen Code Review

> Qwen Code review: Open-source multi-provider agent from an open-weight model lab; also desktop app, web UI and VS Code/JetBrains/Zed plugins. Verified pricing.

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

Open-source multi-provider agent from an open-weight model lab; also desktop app, web UI and VS Code/JetBrains/Zed plugins

See pricing · Open source · facts verified Oct 2, 2026

## What we know about Qwen Code

Qwen Code sits in the ai coding agents category, where it is open-source multi-provider agent from an open-weight model lab; also desktop app, web UI and VS Code/JetBrains/Zed plugins. We keep this Qwen Code profile grounded in primary sources, each fact dated to when we last confirmed it.

Qwen Code does not publish a public per-minute rate we have been able to verify, so the price figure here stays blank until we can confirm one. We would rather show nothing than a guessed number; if you have a current Qwen Code quote, it is the fastest way for us to close that gap.

On capabilities, Qwen Code covers pick the model per task, runs local models, autonomous multi-file edits, runs terminal commands, parallel agents, and mcp support. Each of those is verified against Qwen Code's own docs or dashboard, not marketing copy.

In total we track 19 verified facts for Qwen Code today, each linking the primary source it came from so you can check our work - and vendor claims we have not measured ourselves are labeled as such on the Qwen Code fact sheet below.

## Fact sheet

### Pricing

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| How usage is metered | Own API key | Oct 2 | [source](https://qwenlm.github.io/qwen-code-docs/en/users/configuration/auth/) |
| What the free plan allows | None: Qwen OAuth free tier discontinued 2026-04-15 | Oct 2 | [source](https://qwenlm.github.io/qwen-code-docs/en/users/configuration/auth/) |
| Bring your own API key | Yes | Oct 2 | [source](https://qwenlm.github.io/qwen-code-docs/en/users/configuration/auth/) |

### Capabilities

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Pick the model per task | ✓  Yes | Oct 2 | [source](https://qwenlm.github.io/qwen-code-docs/en/users/configuration/auth/) |
| Runs local models | ✓  Ollama, vLLM | Oct 2 | [source](https://github.com/QwenLM/qwen-code) |
| Published benchmark | SWE-bench Verified 77.80% average (84.6% pass) on 500 cases | Oct 2 | [source](https://github.com/QwenLM/qwen-code) |

### Build experience

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Where it runs | CLI, desktop app (macOS/Windows/Linux) +3 more | Oct 2 | [source](https://github.com/QwenLM/qwen-code) |
| Editor support | VS Code, Zed, JetBrains | Oct 2 | [source](https://github.com/QwenLM/qwen-code) |
| Autonomous multi-file edits | ✓  Yes | Oct 2 | [source](https://github.com/QwenLM/qwen-code) |
| Runs terminal commands | ✓  Yes | Oct 2 | [source](https://qwenlm.github.io/qwen-code-docs/en/users/overview/) |
| Parallel agents | ✓  Yes | Oct 2 | [source](https://github.com/QwenLM/qwen-code) |
| MCP support | ✓  Yes | Oct 2 | [source](https://github.com/QwenLM/qwen-code) |
| Project rules files | QWEN.md, AGENTS.md (plus Auto-Memory, Auto-Skills) | Oct 2 | [source](https://qwenlm.github.io/qwen-code-docs/en/users/overview/) |
| Checkpoints / rollback | ✓  Yes | Oct 2 | [source](https://qwenlm.github.io/qwen-code-docs/en/users/overview/) |

### Commercial

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| License | Apache-2.0 | Oct 2 | [source](https://github.com/QwenLM/qwen-code) |
| GitHub stars | 28,300 | Oct 2 | [source](https://github.com/QwenLM/qwen-code) |
| Last release | v0.24.7 (2026-09-29) | Oct 2 | [source](https://github.com/QwenLM/qwen-code/releases) |
| Supported model providers | OpenAI, Anthropic, Gemini, Qwen APIs +2 more | Oct 2 | [source](https://github.com/QwenLM/qwen-code) |
| Hosted / paid option | Alibaba Cloud Coding Plan Pro $50/mo | Oct 2 | [source](https://www.alibabacloud.com/help/en/model-studio/coding-plan) |

## Qwen Code head-to-head

| Comparison | Record | Per use case |
| --- | --- | --- |
| [Qwen Code vs Claude Code](https://www.versusref.com/coding-agents/claude-code-vs-qwen-code/) | won 3 · lost 4 · tied 0 | Beginners: lost; Enterprise: lost; Free Plans: won; Local Models: won; Open Source: won; Terminal Workflows: lost; VS Code: lost |

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