FAQ
Frequently asked questions about Token Plan Team Edition, covering product selection, Credits billing and quota, model and tool compatibility, usage restrictions, purchasing, renewal, and cancellation.
Product positioning and plan selection
What is the difference between Individual Edition and Team Edition? Which one should I choose?
Comparison | Individual Edition | Team Edition |
|---|---|---|
Use cases | Individual developers | Teams / Enterprises |
Quota mechanism | 7-day fixed window quota | Fixed monthly quota |
Team management | Not supported | Seat assignment and revocation, member usage analysis, SSO integration |
Data security | Data usage is governed by the service agreement | Committed to not using conversation data for model training |
Peak-time performance | Possible waiting during peak hours | Multi-tenant isolation, no queuing during peak hours |
For individual developers or day-to-day use of AI coding tools, the Individual Edition is sufficient. For teams that need multi-member collaboration, centralized seat and usage management, and higher data security requirements, choose the Team Edition.
Can I purchase both Individual Edition and Team Edition at the same time? Are the quotas separate or shared?
Yes, you can purchase both. The same Alibaba Cloud account can hold both Individual Edition and Team Edition simultaneously. Each is billed independently and the quotas are not shared.
Can I upgrade or convert an Individual Edition subscription to a Team Edition seat?
No. Individual Edition and Team Edition are separate products with no shared quota, and an Individual Edition subscription cannot be upgraded or converted to a Team Edition seat. To use the Team Edition, subscribe to it separately. You can hold both editions at the same time, each billed independently. Individual Edition does not currently support unsubscribing; you can simply stop renewing it when the subscription expires.
Credits billing and quota
How does the Team Edition quota mechanism work?
The Team Edition uses a fixed monthly quota with no 7-day window restrictions. Monthly quota by seat type:
- Standard seat: 25,000 Credits/seat/month
- Advanced seat: 100,000 Credits/seat/month
- Premium seat: 250,000 Credits/seat/month
Seat quotas reset at the end of each subscription month. Unused quota does not carry over to the next month.
What happens when the seat quota is exhausted?
When the seat quota is exhausted, API calls are blocked and no pay-as-you-go charges apply. To restore service:
- Wait for the quota to reset automatically at the next subscription month.
- Purchase a shared quota pack (625,000 Credits each, valid for 1 month), shared among all team members.
- Upgrade a seat or purchase additional seats. An upgrade takes effect immediately and the quota follows the new seat type (you pay the price difference, prorated by the remaining days). Additional seats are also charged based on the remaining subscription period.
Model and tool compatibility
Which models does Token Plan Team Edition support?
The Team Edition supports text generation, reasoning, visual understanding, image generation, video generation, and speech recognition. For the specific model list, see the model list page in the console.
Does it support third-party tools such as Cursor, Claude Code, and Cline?
Yes. Token Plan is compatible with the OpenAI and Anthropic protocols. Any tool that supports custom Base URL and API Key can be integrated, including Cursor, Claude Code, Qwen Code, Qoder, Qoder CN, Cline, OpenClaw, Cherry Studio, Chatbox, and more. For specific configuration instructions, see the AI tool integration section in the Quick Start guide.
Can the Team Edition API Key be used with the Individual Edition?
No. The Individual Edition and Team Edition each generate independent API Keys that cannot be used interchangeably. The system automatically identifies the corresponding plan based on the API Key.
What are Harness tools?
Harness tools are built-in extended capabilities of models, including web search, text-to-image search, image-to-image search, web scraping, code interpreter, and more. The Team Edition supports Harness tools, and Credits are consumed based on the tool deduction coefficient when called. Currently, only the qwen3.7 and qwen3.8 series models support native Harness tool calls.
Usage restrictions
How is peak-time performance?
The Team Edition is built on a multi-tenant isolation architecture, with no queuing during peak hours.
Does the Token Plan Team Edition have a concurrency limit?
Yes. The platform dynamically adjusts the concurrency limit based on the overall resource load to prevent resource contention during peak hours and to keep response speed and inference quality stable for each agent. If you reach the concurrency limit, wait a moment and then retry.
Purchasing, renewal, and cancellation
Can RAM sub-accounts make purchases?
Yes. The primary account must complete the following authorization before a RAM user can use Token Plan:
- Grant the RAM user the
AliyunTokenPlanReadOnlyAccess(read-only) orAliyunTokenPlanFullAccess(management) system policy in the RAM console. - Assign the Administrator or Subscribe Plan role to the RAM user on the Account Management page of the Bailian console.
NoteRAM sub-account authorization and seat assignment are two independent concepts: RAM authorization determines who can manage the Token Plan subscription (purchase, renew, and configure) in the Alibaba Cloud console, whereas seat assignment determines who can use the models (that is, who gets an API key). Even if a RAM sub-account has management permissions, a team member still needs to be added and assigned a seat as described in Team management before they can obtain an API key and call models.
How can a member with an assigned seat view their own usage? Why is Token Plan not visible under their own account?
A Team Edition subscription belongs to the purchaser's account. Members with an assigned seat cannot view the Token Plan subscription or usage details under their own account, because usage analysis is an owner-only capability. The purchaser (owner) views each member's Credits consumption on the Usage Analysis page of the Token Plan console. For more information, see Team management. When a seat is assigned, the system automatically generates an individual API key for the member. The member uses that key to call models and does not need to view the subscription under their own account.
Can I upgrade? How is the quota calculated after an upgrade?
Seat upgrades are supported. The upgrade takes effect immediately, and the quota is applied based on the new seat type. You need to pay the price difference (prorated based on remaining days).
Can I downgrade?
Downgrades are not supported. If you need a lower seat type, you can resubscribe after your current subscription expires.
How do I cancel auto-renewal?
Sign in to Billing Management > Renewal Management, find the Token Plan Team Edition order, and disable auto-renewal.
Do I need to reconfigure the API key after renewal?
No. Renewal only extends the validity period of the current subscription. It does not affect the API key or base URL of an assigned seat, so members do not need to reconfigure their tools. A new API key and base URL are generated only when you repurchase after the subscription expires, or repurchase after unsubscribing from a seat. In those cases, reconfigure the tool with the new values, which you can obtain from the API Key section of the My Subscriptions page in the console.
How does promotional pricing work?
Promotional pricing applies to new purchases, renewals, auto-renewals, seat additions, and seat upgrades.
When adding or upgrading seats mid-cycle (for example, upgrading a Standard seat to an Advanced seat), the fee is prorated by remaining days, and the actual charge is the lower of the prorated amount and the promotional price.
Example: The standard seat has an original price of ¥198/month and a promotional price of ¥150/month.
- The prorated fee for remaining days is ¥99, which is lower than the promotional price, so ¥99 is charged.
- The prorated fee for remaining days is ¥165, which exceeds the promotional price, so ¥150 is charged.
Relationship with existing products
Will purchasing Team Edition conflict with an existing Individual Edition?
No conflict. Both can be held simultaneously and are billed independently. The corresponding plan is automatically matched based on the API Key.
Connection errors
Common errors and solutions
Error message | Possible cause | Solution |
|---|---|---|
401 InvalidApiKey: No API-key provided. | The request header does not include an API Key | Generate an API Key and configure it in your tool |
401 InvalidApiKey: Invalid API-key provided. | Used a pay-as-you-go API Key or a Coding Plan Key by mistake; subscription expired; Key copied incompletely | Confirm you are using the Token Plan Team Edition API Key, and ensure it is complete with no spaces |
404 model 'xxx' not found or not supported | Model name is misspelled or not in the supported list | Confirm that the model name is case-sensitive and matches the model ID supported by the plan |
401 invalid access token or token expired | Used the Base URL for Coding Plan or another billing mode by mistake | Use the Token Plan Team Edition Base URL |
401 Incorrect API key provided | Used the Model Studio general-purpose Base URL (dashscope.aliyuncs.com) by mistake | Use the Token Plan Team Edition Base URL |
400 Range of input length should be [1, xxx] | Input content exceeds the model's maximum context length | Start a new session to clear history, or use the tool's context compression command |
400 error when calling image/video generation models (e.g., qwen-image-2.0, wan2.7-image) | Image and video generation models use separate endpoints and cannot be called directly through the text model's Base URL. | Integrate via the tool's Skill, Slash Command, or Agent extension mechanism. See Integrate multimodal generation models. |
429 Requests rate limit exceeded | Too many requests in a short period triggered the model rate limit. Running multiple agents in parallel can also trigger the token concurrency limit, because the requests from all parallel sessions are counted together. | Wait one minute and retry, and reduce the request frequency. If you are running multiple agents in parallel, reduce the number of agents that run at the same time. |
429 Allocated quota exceeded | Seat monthly quota exhausted | Purchase a shared quota pack or wait for the quota to reset next month |