Qwen Coding Plan
subscription
Getting credentials
plan-key
api_key via header (header Authorization: Bearer)
Key prefix: sk-sp-
Environment: BAILIAN_CODING_PLAN_API_KEY
Subscribe in Model Studio; plan keys (sk-sp-...) are separate from normal DASHSCOPE_API_KEY and only work on coding-plan endpoints. Configure tools via OPENAI_BASE_URL=https://coding-intl.dashscope.aliyuncs.com/v1 or the Anthropic-compatible /apps/anthropic route. The older Qwen OAuth free tier was discontinued 2026-04-15.
Endpoints
| ID | URL | Protocol | Auth |
|---|---|---|---|
| coding-chat | https://coding-intl.dashscope.aliyuncs.com/v1/chat/completions | openai-chat | any |
| coding-anthropic | https://coding-intl.dashscope.aliyuncs.com/apps/anthropic | anthropic-messages | any |
API surfaces
textstreaming
Plan
- Price
- $50 / monthly
- Quota
- Pro $50/mo: 6,000 requests / 5 rolling hours, 45,000/week, 90,000/month; slots restock daily 00:00 UTC+8
- Notes
- Strict model allowlist: qwen3.7-plus, qwen3.6-plus, qwen3.5-plus, qwen3-coder-next, qwen3-coder-plus, glm-5, glm-4.7, kimi-k2.5, MiniMax-M2.5. Interactive coding-tool use only. Lite discontinued: new subscriptions ended 2026-03-20, renewals ended 2026-04-13. No Max or Team tier exists on the Coding Plan (Token Plan Team is a separate product).
- Docs
- https://www.alibabacloud.com/help/en/model-studio/coding-plan
Quirks
- China base: https://coding.dashscope.aliyuncs.com/v1. Third-party models on the allowlist (glm-5, glm-4.7, kimi-k2.5, MiniMax-M2.5) are served through the same endpoints; their reasoning parameters follow the upstream models' conventions — offerings seeded only where wire behavior is verified. (docs)
Models offered
| Model | Wire ID | Endpoint | Status | Reasoning |
|---|---|---|---|---|
| alibaba/qwen3-7-plus | qwen3.7-plus | coding-chat | ga | toggle · default on · returns reasoning_content · round-trips reasoning_content |