Start using Token Plan (Team Edition) in three steps: subscribe, get your API key, and set up your AI tool.
Step 1: Subscribe to Token Plan (Team Edition)
Go to the Token Plan pricing page, select a seat type, and subscribe.
Step 2: Obtain your dedicated API Key and Base URL
- Go to the Token Plan Management Console. On the Members page, click Assign Seat, select a seat type, and click Confirm.
- After the seat is assigned, click Generate for the member to create the dedicated API Key (format:
sk-sp-xxxxx, displayed only once -- save it immediately). - On the API Keys page, view the plan-specific Base URL.
- Generate the API Key only after assigning a seat to the member on the Members page.
- The Token Plan dedicated API Key is displayed in full only once at creation or reset. The console shows only a masked version (e.g.
sk-sp-****) afterward. Copy and save it immediately. - Token Plan API Keys start with
sk-sp-and are different from regular QwenCloud API Keys (sk-ws-prefix). They are not interchangeable. See the difference between API key types for details.
| Protocol | Base URL |
|---|---|
| OpenAI compatible | https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1 |
| Anthropic compatible | https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic |
Token Plan and pay-as-you-go API Keys and Base URLs are completely separate and must be used together. Do not mix them.
- Token Plan Team Edition: Use the
sk-sp-dedicated API Key + the Base URLs above. - Pay-as-you-go: Use regular QwenCloud API Key (
sk-ws-prefix) + the Base URL shown on the API Key page.
dashscope-intl.aliyuncs.com Key), your calls will route through the pay-as-you-go billing channel causing unexpected charges, or return 401/403 authentication errors.Step 3: Set up your AI tool
OpenClaw
Open-source, self-hosted personal AI assistant
Hermes Agent
Open-source AI agent framework with built-in self-learning loop
Claude Code
AI terminal coding assistant with natural language programming
OpenCode
Open-source AI coding agent tool
Cursor
AI-native code editor
Codex
Command-line coding tool by OpenAI
Qwen Code
Open-source CLI coding tool
QwenPaw
Open-source personal AI assistant for local and cloud deployment
Qoder
Agentic coding platform for real-world software development
Cherry Studio
Multi-model desktop client
Chatbox
Cross-platform AI desktop client
Cline
VS Code extension for intelligent code completion and debugging
Lingma
Alibaba Cloud intelligent coding assistant with standalone IDE
Kilo CLI
Lightweight, high-performance command-line coding tool
More tools
Other programming tools
Optional: Set up image generation models
Token Plan Team Edition supports image generation models such as qwen-image-2.0 and wan2.7-image. These models use separate APIs and require integration through your AI tool's Skill or extension mechanism.
For configuration details, see Integrate multimodal generation models.
Optional: Tool calling
Through Harness tool calling, models can invoke extended capabilities such as web search, text-to-image search, reverse image search, web scraping, and code interpreter during conversations. Currently, qwen3.8-max, qwen3.7-max, and qwen3.7-plus support native tool calling through the Responses API. Harness tools are billed per successful invocation, and fees are deducted from your plan Credits.
- Other models: Connect tools via MCP services.