Skip to main content
Chinese AI Tools
ProductsModelsIntegrationsRankingsLatest changes
TopicsAvailability TrackerUse casesSubmit a toolAccount
ZHSearch

Chinese AI Tools

Independent directory for Chinese AI products. Product availability, pricing and terms can change. Verify before commercial use.

Editorial standardsClaim productUpdate infoGet featuredAdvertise

Alibaba Cloud

Qwen Code

Qwen's open-source terminal coding agent for Qwen-series models, with Skills, SubAgents and IDE integrations.

Globally availableFull English UIPublic APIFree

Quick answer

Qwen Code is a distinct AI coding product and should be tracked separately from Qwen Cloud models or token plans.

Official sitePricing
Pricing
Open-source CLI; model/provider costs depend on the chosen API or Qwen OAuth path
Availability
Globally available
API
Public API
Last checked
2026-08-04
Pricing detailsUse-case fitSource evidence

The official Qwen Code page positions Qwen Code as an open-source AI agent for the terminal, optimized for Qwen series models. It highlights an agentic workflow with built-in Skills and SubAgents, multi-protocol support through OpenAI, Anthropic and Gemini-compatible APIs, or Qwen OAuth sign-in, and editor integration for VS Code, Zed and JetBrains IDEs. The page also exposes terminal-first usage paths, a headless mode for scripts and CI/CD, and a developer SDK for building agents on top of the same CLI engine.

Topic guide

Qwen models, coding and multimodal ecosystem

A source-backed map of Qwen3.8 and Qwen3.7 models, open weights, Qwen Cloud APIs, Qwen Code, Token Plan and multimodal products.

Editorial verdict

Best for

Developers who want a terminal coding agent for Qwen models and prefer open-source tooling with editor integrations.

Avoid if

Avoid it if you need a hosted turnkey coding IDE with bundled billing and team management out of the box.

Why it matters

Qwen Code is a distinct AI coding product and should be tracked separately from Qwen Cloud models or token plans.

Trust: 3/3 sources verified, recently checkedCoverage: 100/100

Pricing

Open-source CLI; model/provider costs depend on the chosen API or Qwen OAuth path

Payment

Qwen OAuth, OpenAI-compatible API, Anthropic-compatible API, Gemini-compatible API

Commercial use

Commercial use should follow the current product, API, model license and billing terms.

Privacy

Review prompt, file, media upload, retention and training-use terms before sensitive workloads.

Use-case fit

Terminal coding agent

Strong

Run Qwen Code in a project folder for interactive coding, file inspection and contextual assistance.

Scripted and CI/CD workflows

Strong

Use headless mode when the same agent should run in automation pipelines.

IDE-assisted coding

Medium

Pair it with VS Code, Zed or JetBrains when developers want terminal and editor workflows together.

Custom agent development

Strong

Install @qwen-code/sdk to build agents and tools on the same engine used by the Qwen Code CLI.

Global user checklist

RegistrationConfirmedThe official page exposes Linux/macOS and Windows entry points, GitHub Repository and Documentation links.
English UIConfirmedThe public Qwen Code page is English-facing.
API and docsConfirmedThe page documents terminal usage, headless mode, IDE integration and the developer SDK.
International paymentPartialCode access itself is open-source, but backend model costs and provider billing depend on the route you choose.
Commercial usePartialCommercial use depends on the Qwen Code license and the provider terms for the connected model path.

Model names, quotas, release status, regional access and commercial terms can change quickly; recheck official sources before procurement or production use.

Pros

  • - Terminal-first agent optimized for Qwen series models
  • - Supports Skills, SubAgents and headless mode for scripts and CI/CD
  • - Works in VS Code, Zed and JetBrains IDEs
  • - The @qwen-code/sdk package exposes the CLI engine for custom agents and tools

Cons

  • - Model and provider costs depend on the backend you connect
  • - The product surface is coding-agent focused, so it is not a generic assistant

Decision paths

atomcode

kimi-code

qoder

trae

codebuddy

Sources

Qwen Code official page

Official · EN · verified 2026-08-04

Confirms the Linux/macOS installer, Windows entry, interactive qwen command, @ file references, qwen -p headless mode, OpenAI/Anthropic/Gemini-compatible APIs, Qwen OAuth, Skills, SubAgents, IDE integrations and @qwen-code/sdk.

Qwen API platform

Official · EN · verified 2026-05-20

Confirms Qwen's OpenAI-compatible API surface and coding-related model access context.

Qwen Cloud Token Plan

Pricing · EN · verified 2026-05-17

Shows Qwen Code as a supported coding-tool path inside the broader Qwen Cloud ecosystem.

Last checked: 2026-08-04

Reviews

No approved reviews yet.

Availability snapshot

Availability
Globally available
English UI
Full English UI
API
Public API
Rating
4.2 (0)

Latest updates

Latest changes
API · 2026-09-07

Qwen3.8 platform snapshot aligned with current official surfaces

Qwen's current official surfaces now need to be read as two separate layers: Qwen3.8-Max is listed as the flagship model in Qwen Studio, while the August 26 Qwen release describes Qwen3.8-Flash-Next as an open architecture preview and Qwen3.8-Flash as the production hosted line. The release lists Qwen3.8-Flash at $0.16 per million input tokens and $0.47 per million output tokens, with API access still marked as coming soon. This directory keeps the preview, hosted model and open-weight variants separate instead of treating them as one product.

Open source · 2026-08-28

Qwen3.8-Flash-Next open weights added

Qwen3.8-Flash-Next is now tracked as the experimental open architecture behind the production Qwen3.8-Flash line. The official model card documents 125B total parameters with 6B activated, a vision encoder, 262,144-token native context extendable to 1M, and qwen-community-1.0 weights.

Pricing · 2026-08-28

Qwen Cloud Token Plan individual pricing changed

The current individual Token Plan page lists Lite at $6/month with 2,500 credits per 7 days, Standard at $18 with 10,000 credits per 7 days and Pro at $68 with 40,000 credits per 7 days. The supported surface includes Qwen3.8-Max, GLM-5.2, DeepSeek V4 Pro and Wan2.7 Image plus Qwen Code, Cline, Claude Code, Cursor, OpenCode, Codex, Kilo CLI and OpenClaw. Checkout prices and eligibility remain subject to the live page.

Open source · 2026-08-14

Qwen opens 2.4T MoE and 27B multimodal Qwen3.8 models

Qwen released Qwen3.8-2.4T-A95B on August 12 as its first open Max-class text model, with 2.4T total and 95B active parameters under the custom Qwen3.8 Max license. It followed with Apache-2.0 Qwen3.8-27B on August 14, a dense multimodal model accepting text, image and video. Both publish official weights and inference guidance; their licenses and hardware requirements differ materially.

Submit a review