Setup guide - Documented by Qwen
Use Qwen in OpenCode
Model Studio's OpenCode guide adds a custom provider to ~/.config/opencode/opencode.json using the @ai-sdk/anthropic package against Model Studio's Anthropic-compatible endpoint (/apps/anthropic/v1), with Qwen models declared in the models map.
Last verified 5 steps2 official sources
Steps
- Step 1.
Install OpenCode (Node.js 18.0 or later) and verify.
Terminalnpm install -g opencode-ai opencode -v - Step 2.
Open (or create) ~/.config/opencode/opencode.json (Windows: C:\Users\<Your-Username>\.config\opencode\opencode.json). Pay-as-you-go config: replace YOUR_API_KEY and {WorkspaceId}. Region baseURLs: Beijing
https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/apps/anthropic/v1, Singaporehttps://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1, US (Virginia)https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/apps/anthropic/v1.JSON{ "$schema": "https://opencode.ai/config.json", "provider": { "bailian-payg": { "npm": "@ai-sdk/anthropic", "name": "Alibaba Cloud Model Studio", "options": { "baseURL": "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1", "apiKey": "YOUR_API_KEY" }, "models": { "qwen3.7-max": { "name": "Qwen3.7 Max", "options": { "thinking": { "type": "enabled", "budgetTokens": 8192 } } }, "qwen3.7-plus": { "name": "Qwen3.7 Plus", "modalities": { "input": ["text", "image"], "output": ["text"] }, "options": { "thinking": { "type": "enabled", "budgetTokens": 8192 } } }, "qwen3.6-plus": { "name": "Qwen3.6 Plus", "modalities": { "input": ["text", "image"], "output": ["text"] }, "options": { "thinking": { "type": "enabled", "budgetTokens": 8192 } } } } } } } - Step 3.
Coding Plan alternative: use provider id bailian-coding-plan with baseURL https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1 and the Coding Plan key; the Alibaba page lists qwen3.7-plus, qwen3.6-plus, qwen3.5-plus, MiniMax-M2.5, glm-5 and kimi-k2.5 (thinking budgetTokens 1024).
JSON"options": { "baseURL": "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1", "apiKey": "YOUR_API_KEY" } - Step 4.
Token Plan alternative: baseURL https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1 with the Token Plan key; models include auto, qwen3.8-max, qwen3.8-flash, qwen3.7-max, qwen3.7-plus, qwen3.6-flash.
JSON"options": { "baseURL": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1", "apiKey": "YOUR_API_KEY" } - Step 5.
Verify: restart OpenCode, enter /models, search for Alibaba Cloud Model Studio, then select a model.
Snippet/models
Caveats
- The API key is stored inline in opencode.json in the Alibaba example; no environment variable is documented.
- Note the /v1 suffix on the Anthropic base URL for OpenCode, unlike Claude Code's /apps/anthropic.
- Replace {WorkspaceId}; the key must match the region.
- Plan keys (Coding Plan sk-sp-..., Token Plan) and the general pay-as-you-go key are not interchangeable.
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 OpenCode?
Model Studio's OpenCode guide adds a custom provider to ~/.config/opencode/opencode.json using the @ai-sdk/anthropic package against Model Studio's Anthropic-compatible endpoint (/apps/anthropic/v1), with Qwen models declared in the models map.
Which Qwen model ids work in OpenCode?
The official docs read for this guide list qwen3.7-max, qwen3.7-plus, qwen3.6-plus, qwen3.5-plus, qwen3.8-max, qwen3.8-flash and qwen3.6-flash. Requests go to https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1.
Is this an official Qwen and OpenCode setup?
Qwen documents this setup in its own docs. It was last checked against 2 official pages on October 17, 2026.
Sources
Last verified against 2 official pages.
- alibabacloud.comhttps://www.alibabacloud.com/help/en/model-studio/opencode
- 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.