Setup guide - From Qwen and Goose docs
Use Qwen in Goose
goose documents custom providers (OpenAI, Anthropic or Ollama compatible) through goose configure, the Desktop UI, or a JSON file in ~/.config/goose/custom_providers/. Model Studio documents its OpenAI-compatible base URLs and Qwen model ids, so a custom OpenAI-compatible provider covers it.
Last verified 3 steps3 official sources
Steps
- Step 1.
CLI route: run goose configure, choose Custom Providers, then Add A Custom Provider. Pick API Type "OpenAI Compatible", give it a name, enter the Model Studio API URL, answer Yes to Authentication Required and enter your key, then list models (for example qwen3.7-plus,qwen3.6-plus).
Terminalgoose configure - Step 2.
Config file route: create a JSON file in ~/.config/goose/custom_providers/ (Windows: %APPDATA%\Block\goose\config\custom_providers\). Example with Model Studio values (replace {WorkspaceId}):
JSON{ "name": "model_studio", "engine": "openai", "display_name": "Alibaba Cloud Model Studio", "description": "Qwen models via Model Studio", "api_key_env": "MODEL_STUDIO_API_KEY", "base_url": "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions", "models": [ { "name": "qwen3.7-plus", "context_limit": 1000000 } ], "supports_streaming": true, "requires_auth": true } - Step 3.
Export the key named in api_key_env and start a session with the provider.
Terminalexport MODEL_STUDIO_API_KEY="your-api-key" goose session start --provider model_studio
Caveats
- Combined setup: goose's documented custom-provider mechanism plus Model Studio's documented base URLs and model ids. There is no goose-specific Model Studio guide and goose has no built-in Alibaba provider.
- goose's example base_url includes the full /v1/chat/completions path, so the Model Studio base URL above has /chat/completions appended. That path is our derivation from the goose example, not something Model Studio states.
- The provider name, display_name and MODEL_STUDIO_API_KEY are illustrative; goose derives nothing from them. The context_limit of 1000000 for qwen3.7-plus comes from Model Studio's Codex model catalog.
- The built-in OpenAI provider (OPENAI_HOST, OPENAI_BASE_PATH, OPENAI_API_KEY) is a documented alternative for a single endpoint.
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 Goose?
goose documents custom providers (OpenAI, Anthropic or Ollama compatible) through goose configure, the Desktop UI, or a JSON file in ~/.config/goose/custom_providers/. Model Studio documents its OpenAI-compatible base URLs and Qwen model ids, so a custom OpenAI-compatible provider covers it.
Which Qwen model ids work in Goose?
The official docs read for this guide list qwen3.7-plus, qwen3.6-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 Goose setup?
The steps draw on both Qwen's and Goose's docs. It was last checked against 3 official pages on October 17, 2026.
Sources
Last verified against 3 official pages.
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.