Quick start

Updated at:

Get started with Token Plan Personal Edition in three steps: choose a plan, obtain an API Key, and configure your AI tools.

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 Token Plan Personal Edition 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. This API Key starts with sk-sp- and is used for model calls, deducted from Credits. Harness benefits tools (such as Enhanced web search) use the Model Studio API Key (starting with sk-); see Connect Harness tools.
  • Base URL: Select the Base URL that corresponds to the protocol supported by your AI tool.

Protocol

Base URL

OpenAI-compatible

https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1

Anthropic-compatible

https://token-plan.cn-beijing.maas.aliyuncs.com/apps/anthropic

Step 3: Connect models

Enter the API Key and Base URL into your AI tool to call the models supported by Token Plan.

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 command-line AI coding tool

QwenPaw

Open-source personal AI assistant for local and cloud deployment

Cherry Studio

Multi-model desktop client

Chatbox

Cross-platform AI desktop client

Cline

VS Code extension for intelligent code completion and debugging

Qoder

Agentic coding platform for real-world software development

Lingma

Alibaba Cloud intelligent coding assistant with standalone IDE

Kilo CLI

Lightweight, high-performance command-line coding tool

DeepSeek Harness

Open-source AI agent framework by DeepSeek

More Tools

Other coding tools

Step 4: Connect Harness benefits tools

The Standard and Pro plans include Harness benefits tools (Enhanced web search, image generation, and other AgentStudio tools, not consuming Credits). On the My subscriptions page of the Model Studio console, switch to the Harness benefits tab. Common methods:

  • Quick connect: Click Quick connect, select the tools you need, and copy the configuration instruction to send to your local Agent (supports Qoder, QwenWork, Claude Code, and Codex). For first-time use, install the Bailian CLI, run bl auth login --console to log in, and then run bl config show to obtain the api_key.
  • Reference docs: On a tool card, click Documentation or AI Native access and follow the tool's integration guide.

For the full integration flow, see Connect Harness tools.

Optional: Integrate multimodal generation models

Multimodal generation models (wan2.7-image, happyhorse-1.1-t2v, etc.) require dedicated endpoints and are integrated through the Skill or extension mechanism of your AI tool. For details, see Integrate multimodal generation models.