Setup guide - From Qwen and Cline docs
Use Qwen in Cline
Both sides document it. Model Studio's Cline guide uses Cline's OpenAI Compatible provider with Model Studio base URLs. Cline's own docs also include a native "Alibaba Qwen" provider with an International/China region switch.
Last verified 7 steps4 official sources
Steps
- Step 1.
Install VS Code, search for Cline in the extension marketplace, and install it.
- Step 2.
Click the Cline icon in the sidebar, click Bring my own API key, and select OpenAI Compatible as the API Provider (or open the settings icon if Cline is already set up).
- Step 3.
Pay-as-you-go: Base URL for your region (replace {WorkspaceId}), API Key = Model Studio key for that region, Model ID = a supported model such as qwen3.7-plus.
SnippetChina (Beijing): https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1 Singapore: https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1 US (Virginia): https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/compatible-mode/v1 - Step 4.
Coding Plan: Base URL below with the Coding Plan dedicated key and a Coding Plan model id.
Snippethttps://coding-intl.dashscope.aliyuncs.com/v1 - Step 5.
Token Plan (Personal or Team): Base URL below with the Token Plan dedicated key.
Snippethttps://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1 - Step 6.
If you use Qwen3 (thinking mode) or QwQ, click MODEL CONFIGURATION in settings and check Enable R1 messages format.
- Step 7.
Alternative from Cline's docs (native provider): open Cline Settings, choose "Alibaba Qwen" from the API Provider dropdown, choose "International" or "China" for region, paste the key into "Qwen API Key", then pick a model from the Model dropdown.
Caveats
401 Incorrect API key providedmeans the key and base URL come from different plans, or (pay-as-you-go) different regions.400 InternalError.Algo.InvalidParameter: enable Enable R1 messages format under MODEL CONFIGURATION.- Cline's native Alibaba Qwen provider page links to the China Bailian console and does not list a base URL or model ids; the Model Studio OpenAI Compatible path is the more fully documented one.
- Model ids are not named on the Cline page itself; the ones listed come from the Model Studio Coding Plan and Kilo/Codex pages for the same endpoints.
More setup guides
Same tool, other providers
Related reading
- Run Qwen3.8-Flash-Next on a Gaming PC With StrataRun Qwen3.8-Flash-Next locally with Strata on a 12 GB GPU: hardware needs, speeds by quant, the license catch, and when the hosted API is the better call.
- Terminal-Universe Turns Agent Traces Into Training EnvironmentsTerminal-Universe, Qwen's paper on rebuilding terminal-agent trajectories into reusable environments, and why agent teams should keep replayable workspaces.
- Qwen3.8-27B vs Opus 4.6 Max: Local Agentic Coding BenchmarksQwen3.8-27B is a 27B dense Apache-2.0 model that beats Opus 4.6 Max on SWE-bench Pro (61.7 vs 53.4). Benchmarks, hardware, cost and when to run it.
- Qwen 3.8 Max Ships: 2.4T MoE, 1M Context, $2/$6 per MTok, Open Weights Next WeekQwen 3.8 Max is a 2.4T-parameter MoE with 95B active, a 1M context window and $2/$6 per million tokens on QwenCloud, with open weights promised next week.
- Qwen-UI-Agent Points at the Next GUI Agent RuntimeQwen-UI-Agent, Alibaba's GUI agent report, reads best as a product spec: mobile, desktop, browser, CLI and DeepSearch combined in one stateful agent runtime.
- $500 RL Fine-Tune of a 9B Open Model Beat GPT-5.6 Sol and Claude Opus 4.8 on Catalog ReviewA $500 GRPO fine-tune of Qwen 3.5 9B beat GPT-5.6 Sol and Opus 4.8 on catalog review, hitting 97% accuracy at a fraction of the cost per listing.
FAQ
How do I use Qwen in Cline?
Both sides document it. Model Studio's Cline guide uses Cline's OpenAI Compatible provider with Model Studio base URLs. Cline's own docs also include a native "Alibaba Qwen" provider with an International/China region switch.
Which Qwen model ids work in Cline?
The official docs read for this guide list qwen3.7-plus, qwen3.6-plus, qwen3.5-plus and qwen3.7-max. Requests go to https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1.
Is this an official Qwen and Cline setup?
The steps draw on both Qwen's and Cline's docs. It was last checked against 4 official pages on October 17, 2026.
Sources
Last verified against 4 official pages.
- alibabacloud.comhttps://www.alibabacloud.com/help/en/model-studio/cline
- github.comhttps://github.com/cline/cline/blob/main/docs/provider-config/qwen.mdx
- github.comhttps://github.com/cline/cline/blob/main/docs/provider-config/openai-compatible.mdx
- alibabacloud.comhttps://www.alibabacloud.com/help/en/model-studio/coding-plan
Newsletter
New models, set up the day they ship
One email per week. New model releases, the coding tools that support them and how to wire them up.