Skip to content
aicoolies logo

Qwen Code Review: Alibaba's Open-Source Terminal Coding Agent in 2026

Qwen Code is an Apache-2.0 terminal coding agent from Alibaba's Qwen team that reads your codebase, edits files, and runs multi-step agentic workflows across Qwen, OpenAI, Anthropic, Gemini, third-party, or local backends; its former Qwen OAuth free tier ended on April 15, 2026.

reviewed by Raşit Akyol July 27, 2026

Documented evidence

rubric editorial-review-v1

This review is grounded in documented sources and repository analysis. It does not claim a unique hands-on reproducibility record.

Sources checked

Verdict

Qwen Code is a flexible Apache-2.0 terminal coding agent that has grown beyond its Gemini CLI roots into a multi-protocol front-end for Qwen, OpenAI-compatible, Anthropic, Gemini, third-party and local models. Its SubAgents, Agent Teams, MCP, built-in skills, IDE integrations and SDKs make it a strong pick for terminal-first developers who want openness and provider choice. The former Qwen OAuth free tier ended on April 15, 2026, so real cost and data governance now depend on the backend selected, while enterprise support remains a separate procurement concern.

84/100

overall

Speed85
Privacy80
Dev Experience85

What Qwen Code is and where it fits

Qwen Code is an open-source AI coding agent that runs in the terminal, developed by Alibaba's Qwen team as an agentic counterpart to tools like Claude Code. It reads your codebase, writes and edits files, executes shell commands, and drives multi-step workflows from the command line rather than from an editor sidebar. The project was originally based on Google's Gemini CLI v0.8.2 but stopped syncing with upstream from Qwen Code v0.1 and has since pursued independent development as a multi-protocol, multi-platform agent framework. It is released under the permissive Apache 2.0 license and is written mostly in TypeScript, with an active release cadence and a community above 26,000 GitHub stars at this refresh.

What has changed the tool's positioning is that it is no longer tied to Qwen's own models. Qwen Code supports OpenAI-compatible, Anthropic, Gemini, Qwen and Vertex AI protocols, built-in third-party providers, and local inference servers such as Ollama or vLLM, with model switching through `/model`. That makes it less "the Qwen CLI" and more a vendor-flexible agent front-end that happens to come from Alibaba and pairs naturally with the Qwen3-Coder model family. Its audience is terminal-first developers who want an open, hackable agent they can point at whichever cloud or local model fits their budget, privacy needs, and quality bar.

Key features

As an agent, Qwen Code covers the expected core loop — codebase comprehension, file editing, command execution, and multi-step task automation — and layers a broad feature set on top. It includes Auto-Memory and Auto-Skills for persistent context, SubAgents and Agent Teams for delegating work across multiple agent instances, and native Model Context Protocol integration for connecting external tools and data sources. Built-in skills such as `/review`, `/batch`, `/loop`, and `/bugfix` package common workflows into single commands, while plan mode, sandboxing, worktrees, LSP integration and computer-use automation extend the tool beyond a simple chat shell.

The surrounding platform is broader than a single binary. Qwen Code ships IDE integrations for VS Code, JetBrains and Zed, SDKs for TypeScript, Python and Java, a desktop app and daemon mode, plus messaging integrations for Telegram, DingTalk, WeChat and Feishu. For teams pairing it with Qwen models, the current Qwen3-Coder-Next model card documents 80B total parameters with 3B activated and a native 262,144-token context window. The same model card says performance is comparable to models using 10–20 times more activated parameters; that is the model maker's vendor claim, not an independent result. The separate Qwen3-Coder-480B-A35B model — not Coder-Next — is the variant the 2025 Qwen launch article associated with one-million-token extrapolation and Claude Sonnet 4 comparisons.

Developer experience

Installation is deliberately lightweight: Qwen Code supports a standalone installer, Homebrew and npm, then launches with the `qwen` command. Developers familiar with Gemini CLI or Claude Code will recognize the interaction model — a conversational terminal agent that proposes edits and commands, requests approval according to the configured mode, and iterates. The `/auth` command now offers Alibaba ModelStudio, third-party providers and custom providers, while `/model` switches among configured models. That lets a developer prototype against a hosted model and move the same workflow to another API or a local backend without replacing the agent.

The flip side of that flexibility is configuration surface. Getting the best results means selecting an authentication route, supplying provider credentials, and sometimes tuning models or endpoints, which is more setup than a single-vendor product with one login and one model family. The open-source nature is a genuine strength for developers who want to inspect the code, script the SDKs, extend the agent, or connect it to messaging and CI workflows, but support remains community-led rather than an enterprise SLA bundled with the client. For hackers and platform teams that is useful control; for teams wanting turnkey procurement and support it is a real consideration.

Pricing and licensing

The Qwen Code client is free and open source under Apache 2.0, and Qwen3-Coder-Next is published under Apache 2.0, so teams can run the client with a self-hosted compatible model without a per-seat client license. Hosted convenience is no longer free through Qwen OAuth. The project's April 2026 policy notice reduced the remaining OAuth allowance from 1,000 to 100 requests per day on April 13 and closed the Qwen OAuth free entry point on April 15. The current `/auth` interface no longer offers Qwen OAuth as a selectable option.

Current cost depends on the backend. Alibaba ModelStudio offers Coding Plan, Token Plan and standard API-key routes; Qwen Code also supports built-in third-party providers, custom OpenAI-compatible endpoints, direct Anthropic or Gemini configurations, and local servers such as Ollama or vLLM. Buyers therefore need to price the specific provider, region and model they choose rather than assume a universal Qwen Code subscription. Local inference avoids metered API billing but transfers cost to hardware, operations and model-serving capacity.

Limitations and who it is not for

Data handling depends on the selected backend. Qwen Code's current privacy documentation says the client itself does not use prompts, code or model responses for training, and its optional usage statistics do not include code content, prompts, responses or personal information. That statement does not override the model provider's terms: Alibaba ModelStudio, a third-party API, Vertex AI or another endpoint applies its own retention, privacy and training policies. Privacy-sensitive teams should review the chosen provider's contract or use a controlled local endpoint rather than assume the open-source client alone determines data governance.

Beyond data considerations, the limitations are those of a fast-moving open-source project: authentication paths and product terms have changed, community support is not an enterprise SLA, and the configuration burden assumes comfort with providers, keys, endpoints and the command line. It is not the right pick for non-technical users, for teams that need one fixed price with no backend decisions, or for organizations that require contractual support from the client vendor. Vendor-published model performance claims are not independent benchmarks and should be validated against a team's own repositories, languages and approval requirements before standardization.

Verdict

Qwen Code has evolved into a capable, genuinely open agentic coding tool: Apache 2.0 licensed, multi-protocol, equipped with SubAgents, Agent Teams, MCP, skills, IDE integrations and SDKs, and compatible with both cloud and local models. For terminal-first developers who value openness and want one agent front-end across providers, it is one of the more flexible options available. Running the client with a local compatible model also provides a credible path to keeping code inside infrastructure the team controls without a per-seat client fee.

The asterisk is procurement and operational choice. The former Qwen OAuth free tier ended in April 2026, so practical cost now depends on Alibaba ModelStudio, another API provider or self-hosted inference, and privacy terms follow that backend. Developers comfortable selecting and operating a provider will get strong flexibility; teams needing turnkey support, guaranteed pricing and contractual data protections must treat those as separate procurement requirements. Confirm the chosen provider's current price, model availability and data terms at setup time because they are not fixed by the open-source client.

Pros

  • Apache 2.0 client that can be inspected, extended and run without a per-seat client license
  • Multi-protocol support across Qwen, OpenAI-compatible, Anthropic, Gemini, third-party and local endpoints
  • Deep agent feature set: SubAgents, Agent Teams, MCP integration and built-in /review, /batch, /loop, /bugfix skills
  • Broad platform reach with VS Code, JetBrains and Zed integrations plus TypeScript, Python and Java SDKs
  • Compatible with Apache-2.0 Qwen3-Coder-Next, whose vendor model card documents 256K native context
  • Privacy documentation says client telemetry excludes code, prompts and responses, with an opt-out for usage statistics

Cons

  • Qwen OAuth free access ended on April 15, 2026
  • Real cost and data handling depend on the selected backend rather than one fixed client plan
  • Community-led support rather than an enterprise SLA bundled with the open-source client
  • Provider, credential and model-routing setup assumes command-line comfort
  • Vendor model-performance claims are not independent benchmarks and need workload-specific validation

View Qwen Code on aicoolies

Pricing, platforms, and community stacks — explore the full tool page

Comparisons with Qwen Code

Qwen Code logo
Qwen Code
vs
Cursor logo
Cursor

Qwen Code vs Cursor: Open-source terminal agent or complete AI coding environment?

Qwen Code and Cursor now overlap more than a simple CLI-versus-editor label suggests, but they still optimize for different buyers. Qwen Code is an Apache-2.0, terminal-first coding agent with flexible provider configuration, local-model support through OpenAI-compatible endpoints, and optional IDE integrations. Cursor is a commercial AI coding environment that combines Tab predictions, an autonomous multi-file Agent, semantic codebase indexing, and cloud execution. Qwen Code gives experienced teams more control over models and deployment; Cursor gives most developers a more cohesive daily workflow. For the general buyer choosing one primary coding environment, Cursor is the stronger default.

Codex logo
Codex
vs
Qwen Code logo
Qwen Code

Codex vs Qwen Code: OpenAI’s Managed Coding Workflow vs an Open Provider-Flexible Agent Stack

Codex and Qwen Code are Apache-2.0 coding-agent products with terminal, IDE, and desktop surfaces, repository tools, approval controls, sandbox options, MCP support, and unattended execution. The important difference is commercial and operational: Codex centers an OpenAI-managed workflow with ChatGPT identity and credit accounting, while Qwen Code centers an open, provider-flexible agent stack whose operator chooses the model endpoint, credentials, policies, and supporting infrastructure.

OpenCode logo
OpenCode
vs
Qwen Code logo
Qwen Code

OpenCode vs Qwen Code — Model-Agnostic Control vs Qwen-Native Agent Workflow

OpenCode and Qwen Code are both open-source terminal coding agents, but they optimize for different decisions. OpenCode is the stronger default when you want provider choice, local/BYOK flexibility, and a mature multi-model terminal workflow. Qwen Code is compelling when your team wants a Qwen3-Coder-optimized agent with a generous free request story and an Alibaba-aligned model path.

Qwen Code logo
Qwen Code
vs
gemini cli
Gemini CLI

Qwen Code vs Gemini CLI: Alibaba Coding Agent or Google’s Terminal AI Workflow?

Qwen Code vs Gemini CLI for terminal agents: Alibaba’s open-weight coding CLI versus Google’s terminal AI workflow. As of 18 June 2026, free and Google AI Pro/Ultra individual accounts use Antigravity CLI; Gemini CLI remains on supported Standard/Enterprise/Google Cloud and paid API paths. Both are rising command-line options for developers who want AI help without moving every task into a full IDE. Gemini CLI benefits from Google’s model ecosystem, docs, and broader developer-tool distribution, with that individual-access boundary. Qwen Code is interesting for teams watching open-weight coding models and Alibaba’s fast-moving agent tooling. This comparison explains which CLI is safer for everyday developer adoption, when Qwen Code is worth testing, and how teams should think about model access, repo context, and automation risk.

View 1 more comparisons

Alternatives to Qwen Code

Open-source AI coding agent for the terminal

Open-source (MIT) AI coding agent from Anomaly for the terminal, desktop and web. It works with many LLM providers via /connect, local models through Ollama, the pay-as-you-go OpenCode Zen gateway and OpenCode Go subscriptions. OpenCode 2.0 runs one shared background service for all clients and adds the @opencode/client package and Code Mode, which composes MCP and OpenAPI tools in a single script.

Open Source

AI coding agent by Moonshot AI

Kimi Code is Moonshot AI's AI coding agent, available as an open-source (MIT) terminal CLI, a desktop app and IDE extensions. It reads and edits code, runs shell commands, searches files, fetches web pages and plans multi-step work, and now runs Kimi K3.1 Pro with a 1M-token context window. Sign in with a Kimi membership (Plus and above) or a Kimi API key; the CLI can also use other compatible providers, supports MCP servers and plugins, and accepts video input.

freemiumOpen Source

FAQ

How does Qwen Code compare architecturally to Gemini CLI and Claude Code?

Originating as a Gemini CLI fork, Qwen Code has evolved into an independent multi-protocol TypeScript agent framework supporting OpenAI, Anthropic, Gemini, and Qwen APIs with dynamic model switching via /auth.

How do SubAgents, Agent Teams, and MCP integrations coordinate in Qwen Code?

Qwen Code splits complex tasks into subagents using /batch and /loop routines. Native MCP client integration connects external databases and documentation dynamically to prevent context window bloat.

What is the role of Qwen3-Coder MoE models in terminal agent performance?

Qwen3-Coder MoE models activate a subset of expert parameters per token (~3B of 80B), delivering high inference speeds with a 256K native context window for repository-wide dependency graph comprehension.

What is the licensing, data privacy, and Free Tier status of Qwen Code?

The core CLI is Apache 2.0 open-source. API access operates via Alibaba Cloud Model Studio pay-as-you-go keys, OpenRouter gateways, or local self-hosted open weights on vLLM/Ollama.

Sources & verification

Sources checked
Content verified

Verification dates are editorial checks. Routine CMS saves and automatic updatedAt timestamps do not advance them.