Quick start

​

Step 1: Subscribe to Token Plan Personal Edition

Visit the Token Plan Personal Edition purchase page, select a plan tier and subscription period, and complete the subscription. Purchase notes:

• 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 (full access) 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: Obtain your API Key and Base URL

• API Key: After subscribing, generate an API Key on the My Subscription page in the Token Plan console. The API Key is displayed in full only once when generated — copy and securely store it immediately.
• 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: Configure your AI tools

Enter the API Key and Base URL into your AI tool to start using the service.

OpenClawOpen-source, self-hosted personal AI assistant	Hermes AgentOpen-source AI agent framework with built-in self-learning loop	Claude CodeAI terminal coding assistant with natural language programming
OpenCodeOpen-source AI coding agent tool	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 intelligent code completion and debugging	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 coding tools

​

Optional: Integrate multimodal generation models

Token Plan Personal Edition supports multimodal generation models (wan2.7-image, happyhorse-1.1-t2v, etc.). Multimodal generation models are not compatible with the standard text generation endpoint (/api/v1/services/aigc/text-generation/generation) or the OpenAI-compatible endpoint (/compatible-mode/v1/chat/completions). You must call them through their dedicated endpoints. For example, video generation models such as happyhorse-1.1-t2v use the /api/v1/services/aigc/video-generation/video-synthesis endpoint. Integrate them through the Skill or extension mechanism of your AI tool. For details, see Integrate multimodal generation models.

​

FAQ

What should I do if calling a multimodal generation model returns a url error or a model_not_supported error? Multimodal generation models do not support the standard text generation endpoint or the OpenAI-compatible endpoint. Calling them through the wrong endpoint returns an InvalidParameter error with the message "url error", or a model_not_supported error. Switch to the dedicated endpoint: video generation models use /api/v1/services/aigc/video-generation/video-synthesis, and image generation models use /api/v1/services/aigc/image-generation/generation.

​

Optional: Integrate Harness tools

Some Qwen models (qwen3.7 and qwen3.8 series) have built-in Harness tools that extend capabilities such as web search, text-to-image search, reverse image search, web scraping, and code interpreter during conversations. Harness tools can only be invoked through the Responses API, and Credits are deducted based on the number of successful invocations. For details, see Integrate Harness tools.