Quick start

​

Step 1: Subscribe to Token Plan Team Edition

Go to the Token Plan Team Edition purchase page, select a seat tier and subscription period, and complete the subscription. Both primary accounts and RAM users can subscribe.

• RAM user authorization: Before a RAM user can use Token Plan, the primary account must complete the following authorization:
  1. In the RAM console, grant the RAM user the AliyunTokenPlanReadOnlyAccess (read-only) or AliyunTokenPlanFullAccess (management) system policy, and also grant the AliyunBSSReadOnlyAccess system policy.
  2. In the Model Studio console Account Management page, assign the Administrator or Subscribe Plan role to the RAM user.

​

Step 2: Get the API Key and Base URL

• API Key: On the Member Management page or Admin Platform in the Token Plan console, create member accounts, assign seats, and generate API Keys for members. For details, see Team Management. API Key usage notes:
  • Before generating an API Key, you must assign a seat to the corresponding account on the Member Management page.
  • Token Plan API Keys are displayed in full only once when created or reset. After that, the console only shows masked information (e.g., sk-sp-****). Copy and save the key immediately when it is generated.
  • Token Plan API Keys start with sk-sp-, which differs from the standard Model Studio API Key format (starting with sk-). The two types are not interchangeable.
• Base URL: Select the Base URL that corresponds to the protocol supported by your AI tool.

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

​

Step 3: Connect to an AI tool

Configure the API Key and Base URL in your AI tool to start using the service.

OpenClawOpen-source, self-hosted personal AI assistant	Hermes AgentOpen-source AI agent framework with self-learning loop	Claude CodeAI terminal coding assistant with natural language programming
OpenCodeOpen-source AI coding agent	CursorAI-native code editor	CodexCommand-line coding tool by OpenAI
Qwen CodeOpen-source command-line AI coding tool	QwenPawOpen-source personal AI assistant for local and cloud deployment	Cherry StudioMulti-model desktop client
ChatboxCross-platform AI desktop client	ClineVS Code extension for AI code completion	QoderAgentic coding platform for real-world software development
LingmaAlibaba Cloud intelligent coding assistant with standalone IDE	Kilo CLILightweight, high-performance command-line coding tool	DeepSeek HarnessOpen-source AI agent framework by DeepSeek
More ToolsOther programming tools

​

Optional: Connect to multimodal generation models

Token Plan Team Edition supports multimodal generation models (wan2.7-image, happyhorse-1.1-t2v, etc.). Multimodal generation models use a separate API and need to be integrated through the Skill or extension mechanism of your AI tool. For details, see Integrate multimodal generation models.

​

Optional: Connect to Harness tools

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 only qwen3.7 and qwen3.8 support native tool calling through the Responses API. Harness tools consume Credits based on a deduction coefficient. For details, see Integrate Harness tools.