Token Plan edition selection, purchases and subscriptions, unsubscription and refunds, usage limits, and integration issues.
Product and editions
What is the difference between Personal Edition and Team Edition?
Personal Edition is designed for individual developers and is subscribed by plan tier. Team Edition is designed for teams and enterprises and is subscribed by seat, with seat management, member usage analytics, and SSO integration. The two editions also differ in quota mechanisms, data security, and peak-hour performance. For a complete comparison, see Personal Edition subscriptions and benefits and Team Edition subscriptions and benefits.
Can I purchase Personal Edition and Team Edition at the same time? Are quotas calculated separately or shared?
Yes. The same Alibaba Cloud account can hold both Personal Edition and Team Edition. They are billed independently, and quotas are not shared.
Can I upgrade or convert Personal Edition to a Team Edition seat?
No. Personal Edition and Team Edition are independent products with separate quotas, and Personal Edition cannot be upgraded or converted directly to a Team Edition seat. To use Team Edition, subscribe to it separately. Personal Edition does not support unsubscription at this time; simply stop renewing when the subscription expires.
Can a Team Edition API Key be used with Personal Edition?
No. Personal Edition and Team Edition generate separate API Keys that cannot be mixed. The system identifies the corresponding edition based on the API Key.
Will purchasing Team Edition conflict with an existing Personal Edition subscription?
No. Both can be held at the same time and are billed independently. The corresponding edition is matched automatically based on the API Key in use.
Which models does Token Plan support?
Token Plan supports models from Qwen, Wan, DeepSeek, Moonshot AI, Zhipu AI, MiniMax, HappyHorse, and others. The model scope differs between Personal Edition and Team Edition. For the complete list, see the models supported by Personal Edition and Team Edition.
Does Token Plan 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 a custom Base URL and API Key can connect. For configuration, see Quick start.
What are built-in model tools?
Built-in model tools are model-native extension capabilities, including web search, text-to-image search, image-to-image search, web scraping, and code interpreter. They are triggered automatically when models are called through the Responses API and are deducted from Credits. Both Personal Edition and Team Edition support them.
Built-in tools with the same names in Harness benefits are called through Model Studio API Keys starting with sk-, count toward the Harness benefits quota, and do not consume Credits. For details, see Harness benefits.
Do Harness benefits consume Credits?
No. Harness benefits are free quotas and discounts for AgentStudio tools included with Personal Edition Standard and Pro plans. They are metered independently and do not consume plan Credits or usage packs. Harness services use Model Studio API Keys (starting with sk-), while Token Plan dedicated API Keys (starting with sk-sp-) are used only for model calls. For details, see Harness benefits.
Does Token Plan provide a free trial quota or free Tokens?
Token Plan subscriptions do not include a trial quota or free Tokens. Model Studio provides separate free quotas for some models. You can check the list of models with available free quotas in the console.
Purchase and subscription
Can RAM users use Token Plan?
Yes. RAM users need Token Plan permissions and billing center permissions granted by the primary account. The billing center policy is AliyunBSSReadOnlyAccess for Personal Edition and AliyunBSSFullAccess for Team Edition. For complete authorization steps and the permission comparison, see Permissions and usage policies · RAM user authorization.
RAM authorization and seat assignment are separate concepts: RAM authorization determines who can manage the subscription, while seat assignment determines who can use models. Team Edition members still need a seat assigned in team management before they can obtain an API Key.
Can I upgrade? How is the quota calculated after an upgrade?
You can upgrade from a lower tier to a higher tier. Upgrades do not reset the current subscription cycle: you pay the price difference for the remaining days, and additional Credits for the current cycle are granted based on the monthly quota difference between the new and old tiers. From the next subscription month, the new tier's quota applies.
For the formulas and examples, see Usage and quota · Upgrade quota calculation.
Can I downgrade?
No. To switch to a lower tier or seat type, purchase or subscribe again after the subscription expires. For details, see Personal Edition · Other and Team Edition · Important notes.
How do I cancel auto-renewal?
- Personal Edition: Sign in to the Token Plan page in the Model Studio console and disable auto-renewal in subscription management.
- Team Edition: Sign in to Billing Center > 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, repurchasing after subscription expiration, and repurchasing after unsubscribing from a seat do not change the API Keys of assigned seats. The API Key is temporarily unavailable while the subscription is expired or unsubscribed, and becomes usable again after renewal or repurchase succeeds.
How do I view the effective time and remaining days of a subscription?
- Effective time: Sign in to the Token Plan page in the Model Studio console to view it.
- Remaining days: The remaining days shown in the console are the number of complete 24-hour periods after rounding down. For example, 22 days and 20 hours remaining is shown as 22 days. The actual validity period is based on the end time.
Can I purchase Token Plan with a student voucher?
No. Student vouchers apply only to the products specified on the promotion page and cannot be used to purchase Token Plan.
What are the billing rules for limited-time promotions?
Limited-time promotions apply to new purchases, renewals, auto-renewals, seat add-ons, and seat upgrades.
When adding or upgrading seats, fees are prorated by the remaining duration, and the actual charge is the lower of the prorated amount and the limited-time price.
Example: The Standard seat list price is CNY 198/month, and the limited-time price is CNY 150/month.
- If the prorated amount for the remaining duration is CNY 99, which is lower than the limited-time price, CNY 99 is charged.
- If the prorated amount for the remaining duration is CNY 165, which is higher than the limited-time price, CNY 150 is charged.
Unsubscription and refunds
Can I unsubscribe from Personal Edition?
Personal Edition does not support unsubscription at this time. You can stop renewing when the subscription expires.
Can I unsubscribe from Team Edition seats?
Yes, seats can be unsubscribed individually. Seats with consumed usage cannot be unsubscribed. Refunds are returned to the original payment account and are expected to arrive within 1-3 business days. For the operation, see Team Edition · Unsubscribe seats.
Usage limits
What does "production API automation is prohibited" mean exactly?
Token Plan Personal Edition is for individual interactive development through officially supported tools (such as Cursor and Claude Code). API Keys must not be used for automated services in production environments, batch scripts, background scheduled jobs, or other non-interactive scenarios.
Can team members view team usage?
No. Team members cannot view team subscriptions, seat quotas, or shared usage pack balances. The owner or administrator must view them. For details, see Team management · Roles and permissions.
Is data used to train models?
Personal Edition uses model inputs and generated content for service improvement and model optimization during use. Team Edition does not use conversation data to train models. For details, see Permissions and usage policies · Data usage policy.
Can multiple people share one account?
No. Token Plan Personal Edition is limited to a single person. Multiple people must not share the same account or API Key. For collaboration, use Token Plan Team Edition.
Can I use the same API Key on multiple devices?
Yes. The same API Key can be configured on multiple devices owned by the subscriber, but only the subscriber can use it. Resetting the API Key immediately invalidates the old Key, and you must update the new Key on all devices. Reset the Key only when it is leaked.
How many concurrent Agents are supported?
The concurrency capability of Personal Edition depends on the plan tier:
| Tier | Recommended concurrency |
|---|---|
| Lite | 1-2 Agents |
| Essential | 2-3 Agents |
| Standard | 3-4 Agents |
| Pro | 6-8 Agents |
Will responses slow down during peak hours?
Personal Edition may queue during peak hours. For more stable throughput, upgrade to a higher tier or use Team Edition. Team Edition uses a multi-tenant isolation architecture and does not queue during peak hours.
What is the rate limit threshold (TPM/RPM)? Can it be increased?
Rate limit thresholds are adjusted dynamically based on overall load to maintain service stability. Plan rate limits cannot be increased. When rate limited, reduce the context, lower task complexity, and retry after about 1 minute.
Does Team Edition have concurrency limits?
Yes. The platform adjusts the concurrency limit dynamically based on overall resource load. When the concurrency limit is triggered, wait a moment and retry.
Integration and errors
First distinguish between four cases
| Symptom | Cause | Resolution |
|---|---|---|
| 429 insufficient_quota | The plan quota or usage pack quota is used up | Wait for reset, upgrade, or purchase a usage pack or shared usage pack |
| 429 Requests rate limit exceeded | Requests are too frequent in a short period | Retry after about 1 minute and reduce the request frequency |
| Concurrency limit | The number of Agents running at the same time exceeds the recommended value for the tier | Reduce the number of Agents running at the same time, or upgrade to a higher tier |
| 401, 403, 404 | API Key, Base URL, or model configuration error | Check the Key prefix, Base URL, and model ID |
Troubleshooting order
- Confirm that the API Key starts with
sk-sp-and is used with the Token Plan Base URL. - Confirm that the model ID is in the models supported by Personal Edition and Team Edition and applies to the current edition.
- Check whether the quota is used up on the My Subscriptions and Usage Analysis pages in the console.
- Check whether the error is
insufficient_quota,Requests rate limit exceeded, or an authentication error.
Common errors
| 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 the tool |
401 InvalidApiKey: Invalid API-key provided. | A pay-as-you-go API Key or a Coding Plan Key is used by mistake; the subscription has expired; the Key is copied incompletely | Confirm that the Token Plan API Key is used and is complete with no spaces |
404 model_not_found: Model not exist. | The model name is misspelled or not in the supported list | Confirm that the model name is case-sensitive and matches a model ID supported by the plan |
404 model 'xxx' not found or not supported | The model name is misspelled or not in the supported list | Confirm that the model name is case-sensitive and matches a model ID supported by the plan |
403 AccessDenied.Unpurchased: Access to model denied. | The model is supported only by Team Edition, not Personal Edition | Use a model supported by Personal Edition, or use Token Plan Team Edition |
401 invalid access token or token expired | A Base URL for Coding Plan or another billing mode is used by mistake | Use the Token Plan Base URL |
401 Incorrect API key provided | The general Model Studio Base URL (dashscope.aliyuncs.com) is used by mistake | Use the Token Plan Base URL |
400 Range of input length should be [1, xxx] | The input exceeds the model's maximum context length | Start a new session to clear history, or use the tool's context compression command |
400 invalid_parameter_error: Unexpected item type in content. | Non-text content such as images is passed to a text-only model | Use a model that supports the modality, or confirm that the request content matches the model capabilities |
400 error when calling image or video generation models | Image and video generation models use separate endpoints and cannot be called directly through a text model's Base URL | Connect through the tool's Skill, Slash Command, or Agent extension mechanism |
429 Requests rate limit exceeded | Requests are too frequent in a short period; running multiple Agents in parallel may also trigger the concurrency limit | Retry after about 1 minute and reduce the request frequency and concurrency |
429 insufficient_quota: Your token-plan quota has been exhausted. | The plan quota or usage pack quota is used up | Purchase a usage pack, upgrade the plan, or wait for the quota to reset in the next subscription month |
502 Bad Gateway | An occasional server-side error | Retry later |
Quota exhausted
A 429 insufficient_quota response indicates that the quota is used up. Calls are blocked. For the deduction order and recovery options, see Usage and quota · Quota exhaustion and recovery.
Rate limiting and concurrency
A 429 Requests rate limit exceeded response indicates rate limiting, not quota exhaustion. Rate limit thresholds are adjusted dynamically based on overall load, and plan rate limits cannot be increased. Retry after about 1 minute, reduce the context, reduce concurrency, or lower the request frequency. Team Edition also has concurrency limits.
Authentication and configuration
The API Keys and Base URLs for Token Plan, Coding Plan, and pay-as-you-go are isolated and must be used in matching pairs:
- Token Plan: API Key starting with
sk-sp-+ Token Plan Base URL. - Coding Plan: Coding Plan API Key +
https://coding.dashscope.aliyuncs.com/v1. - Pay-as-you-go: Model Studio API Key (starting with
sk-) +https://dashscope.aliyuncs.com/compatible-mode/v1.