Setup guide - Documented by Qwen
Use Qwen in Kilo Code
Model Studio documents Kilo CLI, the command-line client for Kilo Code, using a custom provider in ~/.config/kilo/config.json. Pay-as-you-go uses @ai-sdk/openai-compatible against /compatible-mode/v1; the Coding Plan and Token Plan use @ai-sdk/anthropic against /apps/anthropic/v1. Model Studio also lists the Kilo Code extension as supported in VS Code and JetBrains IDEs.
Last verified 5 steps2 official sources
Steps
- Step 1.
Install Kilo CLI (Node.js v18.0 or later) and verify.
Terminalnpm install -g @kilocode/cli kilo --version - Step 2.
Pay-as-you-go: add to ~/.config/kilo/config.json, replacing YOUR_API_KEY and {WorkspaceId}. Region baseURLs: Beijing
https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1, Singaporehttps://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1, US (Virginia)https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/compatible-mode/v1.JSON{ "$schema": "https://kilo.ai/config.json", "provider": { "bailian": { "npm": "@ai-sdk/openai-compatible", "name": "Alibaba Cloud Model Studio", "options": { "baseURL": "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "apiKey": "YOUR_API_KEY" }, "models": { "qwen3.7-plus": { "name": "Qwen3.7 Plus", "modalities": { "input": ["text", "image"], "output": ["text"] }, "options": { "thinking": { "type": "enabled", "budgetTokens": 1024 } } }, "qwen3.6-plus": { "name": "Qwen3.6 Plus", "modalities": { "input": ["text", "image"], "output": ["text"] }, "options": { "thinking": { "type": "enabled", "budgetTokens": 1024 } } } } } } } - Step 3.
Coding Plan alternative: provider bailian-coding-plan with "npm": "@ai-sdk/anthropic" and the baseURL below, using the Coding Plan key (models qwen3.7-plus, qwen3.6-plus, qwen3.5-plus, MiniMax-M2.5, glm-5, kimi-k2.5).
JSON"options": { "baseURL": "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic/v1", "apiKey": "YOUR_API_KEY" } - Step 4.
Token Plan alternative: "npm": "@ai-sdk/anthropic" with baseURL https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1 (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 Kilo CLI, type /models, search for Alibaba Cloud Model Studio, and select a model.
Snippet/models
Caveats
- The Alibaba guide covers Kilo CLI specifically; for the Kilo Code IDE extension, the Model Studio More tools page lists it as supported but links back to the Kilo CLI page.
- The pay-as-you-go section uses @ai-sdk/openai-compatible but links to the Anthropic-compatible models list; both endpoints are documented on the More tools page.
- The API key goes inline in config.json in the example; no env var is documented.
- Replace {WorkspaceId}; keys are plan- and region-specific.
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 Kilo Code?
Model Studio documents Kilo CLI, the command-line client for Kilo Code, using a custom provider in ~/.config/kilo/config.json. Pay-as-you-go uses @ai-sdk/openai-compatible against /compatible-mode/v1; the Coding Plan and Token Plan use @ai-sdk/anthropic against /apps/anthropic/v1. Model Studio also lists the Kilo Code extension as supported in VS Code and JetBrains IDEs.
Which Qwen model ids work in Kilo Code?
The official docs read for this guide list qwen3.7-plus, qwen3.6-plus, qwen3.5-plus, qwen3.8-max, qwen3.8-flash, qwen3.7-max and qwen3.6-flash. Requests go to https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1.
Is this an official Qwen and Kilo Code 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/kilo-cli
- alibabacloud.comhttps://www.alibabacloud.com/help/en/model-studio/more-tools
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.