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:
-
In the RAM console, grant the RAM user the
AliyunTokenPlanReadOnlyAccess(read-only) orAliyunTokenPlanFullAccess(full access) system policy. -
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 |
|
|
Anthropic compatible |
|
Token Plan API Keys start with sk-sp-, which differs from the standard Model Studio API Keys (starting with sk-). The two types cannot be used interchangeably. The API Keys and Base URLs for Token Plan, Coding Plan, and pay-as-you-go are completely isolated and must be used in matching pairs.
Step 3: Configure your AI tools
Enter the API Key and Base URL into your AI tool to start using the service.
Optional: Integrate multimodal generation models
Token Plan Personal 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: Integrate 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.