Frequently asked questions about Token Plan Individual.
Quota and limits
What does the 7-day limit mean?
Token Plan Individual uses a 7-day fixed window quota, measured in Credits. When cumulative consumption within the window reaches the quota limit, the service is paused until that window ends and the quota resets. Unused quota within a window period does not carry over to the next cycle.
Example: The Standard plan has a 7-day limit of 10,000 Credits. You make your first call on July 20, starting the window (July 20-July 27). You consume 4,000 Credits on July 20 and 6,000 Credits on July 22, reaching the 10,000 Credits limit, so the service is paused. On July 27 the window ends, the quota resets to 10,000 Credits, and the service resumes.
Limits by plan:
| Plan | 7-day limit |
|---|---|
| Lite | 2,500 Credits |
| Standard | 10,000 Credits |
| Pro | 40,000 Credits |
Does the 7-day limit reset on a fixed date?
No. The 7-day limit uses a fixed window mechanism. A 7-day timer starts from your first invocation; when it elapses, the quota resets regardless of how much was consumed. It does not reset on a fixed calendar date (such as every Monday).
What happens when the quota runs out?
When the limit is reached, API calls are blocked (you will not be charged on a pay-as-you-go basis). To resume:
- Use the Reset Usage Limit benefit to instantly refresh your quota.
- Wait for the window period to end and the quota to reset.
- Upgrade your plan.
- Purchase a Credit Pack for additional Credits that are not subject to window limits.
What is a reset card and how do I use it?
A reset card is a one-time quota reset entitlement for Token Plan Personal Edition subscribers. In the plan quota area of the Token Plan subscription page, click Reset limit to reset the plan quota immediately. The button shows the number of available uses (for example, 1 available), and the info icon next to it displays the tooltip "Use a reset card to reset your plan quota immediately." A reset card is granted once rather than on a recurring basis, and no separate email notification is sent when it is granted.
Why am I still being charged on a pay-as-you-go basis after activating Token Plan?
This usually happens due to one of the following reasons:
- Calls before activation: Calls made before Token Plan took effect are billed independently and cannot be offset by the plan.
- Configuration error: You are not using the Token Plan dedicated API Key and Base URL (e.g., accidentally using the general
dashscope-intl.aliyuncs.comKey), causing requests to route through the pay-as-you-go billing channel. - Unsupported model: You called a model outside the Token Plan allowlist.
Why does the Credits consumption on my bill or in a plug-in differ from what I expect?
A difference between Credits consumption and what the bill or a plug-in reports is commonly caused by:
- Context cache hits: The deduction ratio is lower on a cache hit and higher on a miss.
- Model family differences: Different models (such as the Qwen series and the GLM series) have different Credits deduction ratios.
- Feature mode impact: Frequently switching tool calling or thinking mode can affect billing.
Does Token Plan offer a free trial quota or free Tokens?
The Token Plan itself does not offer a trial quota or free Tokens. QwenCloud provides a separate free quota for some models; you can check the console for the list of models with available free quota.
How can I reduce Token Plan Credits consumption?
- Compress message history or start a new conversation to avoid accumulated consumption from long context.
- Turn off Thinking Mode to reduce reasoning overhead.
- Switch to a lighter model (such as qwen3.6-plus instead of qwen3.7-max) for less complex tasks.
- Take advantage of caching — tokens that hit the cache are billed at a lower rate than regular input tokens.
- Monitor consumption details on the Usage Analysis page and adjust your usage accordingly.
Why does the Token usage shown by a third-party tool (such as Claude Code) differ from the console statistics?
- Different measurement scope: Third-party tools only display model-level input/output tokens; the console statistics include all consumption items.
- Hidden consumption items: System prompts, tool definitions (Schema), user configuration, project conventions, accumulated multi-turn conversation history, tool call parameters and return results, and model internal reasoning content are all counted toward Credits consumption but not displayed in third-party tools.
- Model unit price impact: Credits consumption is related to the model deduction coefficient; higher-priced models (such as qwen3.7-max) result in higher Credits consumption for the same number of tokens.
- Optimization suggestions: Check official statistics via the Token Plan subscription page's Usage Analysis; use
/compactto compress message history or/clearto start a new conversation to reduce context accumulation.
What is the relationship between Credit Packs and subscriptions? Do I need to subscribe first?
Credit Packs are a supplement to subscriptions, providing additional Credits that are not subject to subscription limits. You must subscribe to a plan before purchasing a Credit Pack. You can hold a maximum of 5 packs at a time.
Are Credit Pack Credits subject to window limits?
No. Credit Pack Credits are not subject to the subscription's window limits and can be used immediately after purchase.
How long is a Credit Pack valid, and where can I purchase one?
Credit Packs are valid for 1 month. Unused Credits expire automatically and are non-refundable. You can purchase one from the Token Plan Individual page in the console.
Where can I view my Token Plan usage?
On the Token Plan > My Subscriptions page in the console, you can view the Credits quota and consumption of your current subscription.
Connection errors
Common errors and solutions
| Error message | Possible cause | Solution |
|---|---|---|
| 401 InvalidApiKey: No API-key provided. | API Key not included in request header | Generate an API Key and configure it in your tool |
| 401 InvalidApiKey: Invalid API-key provided. | Using a pay-as-you-go or Coding Plan Key; subscription expired; Key copied incompletely | Confirm you are using the Token Plan Individual API Key |
| 404 model_not_found: Model not exist. | Model name is misspelled or not in the supported list | Verify the model name is case-sensitive and matches a supported model ID |
| 403 AccessDenied.Unpurchased: Access to model denied. | The model is supported only by Token Plan Team Edition, not Personal Edition | Switch to a model supported by Personal Edition, or use Token Plan Team Edition |
| 401 invalid access token or token expired | Using a Coding Plan or other billing mode Base URL | Use the Token Plan Individual Base URL |
| 401 Incorrect API key provided | Using the standard QwenCloud Base URL (dashscope-intl.aliyuncs.com) | Use the Token Plan Individual Base URL |
| 429 Requests rate limit exceeded | Too many requests in a short time | Wait one minute and retry with reduced frequency |
| 429 Allocated quota exceeded | 7-day limit reached | Use the Reset Usage Limit benefit, purchase a Credit Pack, or wait for the window period to end |
| 400 invalid_parameter_error: Unexpected item type in content. | Non-text content such as an image was passed to a text-only model | Switch to a model that supports the modality, or confirm the request content matches the model's capabilities |
| 502 Bad Gateway | Intermittent server-side error | Retry later |
Token Plan usage shows 0 or calls are still being charged — what should I do?
- Usage showing 0 is typically because no actual consumption has occurred yet, or you are using a non-Token Plan API Key.
- If calls are still deducting from your balance or generating arrears, it is because you configured a general API Key rather than the plan-dedicated Key.
Concurrency and performance
How many Agents can run concurrently?
Concurrency depends on your plan:
| Plan | Recommended concurrency |
|---|---|
| Lite | 1-2 concurrent Agents |
| Standard | 3-4 concurrent Agents |
| Pro | 6-8 concurrent Agents |
What is Token Plan's rate limit (TPM/RPM)? Can it be increased?
The exact TPM/TPS/RPM thresholds are not publicly disclosed; rate limits are adjusted dynamically based on overall load to maintain service stability. Plan rate limits cannot be increased.
Optimization suggestions: Trim your context and reduce task complexity to lower input tokens per call; if rate-limited, wait about 1 minute before retrying.
Will response times increase during peak hours?
Peak hours may cause queuing. For more stable throughput, upgrade to a higher plan or use the Team Edition.
Usage rules
What does "no automated API calls" mean?
Token Plan Individual is for personal interactive development through designated tools (such as Cursor, Claude Code, Windsurf, etc.). Using the API Key for production automation, batch scripts, or background scheduled tasks is not allowed.
Can multiple people share one account?
No. Token Plan Individual is for single-user use only. Sharing accounts or API Keys is prohibited. For team collaboration, use the Token Plan Team Edition.
Can I use the same API Key on multiple devices?
Yes. Each Token Plan Individual subscription corresponds to a dedicated API Key. Copy and save it securely as soon as it is generated. You can configure the same API Key on multiple devices (such as your home and office computers) without regenerating it for each device.
Resetting the API Key immediately invalidates the old Key. You must then update all devices with the new Key. We recommend resetting only when the Key is leaked.
Purchase and subscription
Can I upgrade? How is the quota adjusted?
You can upgrade from a lower plan to a higher one. Go to the Token Plan pricing page to select a target plan. The upgrade cost is prorated based on remaining time, and your limits are immediately raised to match the new plan.
Can I downgrade?
No. To switch to a lower plan, wait for your current subscription to expire and repurchase.
How do I cancel auto-renewal?
Go to the Token Plan page on the QwenCloud console and disable auto-renewal in subscription management.
How do I check the effective time and remaining days of my Token Plan?
- Effective time: Log in to the console Token Plan page to view when your plan took effect.
- Remaining days display logic: The remaining days shown in the console are rounded down to complete 24-hour periods; the actual validity is based on the exact end timestamp (for example, 22 days and 20 hours remaining is displayed as 22 days). This is expected behavior.