Skip to main content
Qwen Cloud home page
Docs
Billing

Billing and cost management

Analyze and manage costs

Learn how to query detailed bills, view invoices, and stop billing to avoid charges. For details on billing types and pricing, see Pricing.

Pay-as-you-go billing

The Pay-as-you-go page shows your current month's billed amount and spending limit at the top. Below, you can view detailed bills in Chart or List view, and access invoices. On the Pay-as-you-go page, the Spending Trends section lets you analyze costs by different dimensions:
  1. Toggle between Chart and List views:
    • Chart: Visualize spending trends as a bar chart. Use the Group by selector to choose a grouping dimension:
      • Production Steps: Group by production stage (such as Inference)
      • API Key: Group by API key
      • Model: Group by model
    • List: View itemized billing records with columns: Billing Month, Production Steps, Job ID, Model, Usage, Amount, Workspace Name, API Key, Line Item
  2. Use filters to narrow down records:
    • All Production Steps: Filter by specific production stage
    • All API Keys: Filter by specific API key
    • All Models: Filter by specific model
    • By Month/By Day: Switch time granularity
    • Time range: Select billing period (such as Last 12 months)

View invoices

On the Pay-as-you-go page:
  1. Navigate to the Invoices section
  2. Select a month from the date picker to view invoices for that period
  3. View invoice details:
    • Month: Billing period
    • Amount (Incl. Tax): Total amount including tax
    • Status: Invoice status
    • Action: Download or view invoice

Coding Plan billing

The Coding Plan is a subscription plan. On the Coding Plan page:
  • Plan details: View current plan type, status (Active), auto renewal settings, and subscription period
  • Usage Consumption: View request quota usage and reset timers for 5-hour, weekly, and monthly windows
  • Subscription History: View and filter past subscription orders, download invoices
Quota usage varies by task complexity. Simple tasks use ~5–10 invocations; complex tasks use 10–30+. For plan details and pricing, see Coding Plan overview.

Cost management

Set spending limit and alerts

On the Pay-as-you-go page, click the settings icon next to Limit to open the Spending Limit & Alerts dialog:
  1. Enable Monthly Spending Limit
  2. Set your spending limit in the New Limit field
  3. Configure alert settings:
    • Alert Threshold: Drag the slider to set the percentage (for example, 80%) at which you want to be notified
    • Notification Methods: Add email addresses to receive alerts
  4. Click Save Settings
You will receive notifications when your spending reaches the alert threshold. Alerts are typically sent within 15 minutes, though the exact timing may vary.
The spending limit helps you control costs and receive alerts before charges exceed your budget. For additional cost-saving strategies, see Cost optimization.

Stop billing

To avoid charges when you no longer need Qwen Cloud:
  • Stop using Try AI or making API calls.
  • Delete your API key on the API Key page to prevent accidental calls.
For information about service suspension during overdue payments, see Overdue payment protection.

FAQ

Why can't I find the bill right after calling a model?

  1. Bill delay: Bills update hourly but may lag during peak hours (costs from 16:00-17:00 might appear at 19:30).
  2. Free tier: No charges or bills are generated for usage within free quota or when calling free models.

Is Pay-as-you-go billed in real time?

No. Qwen Cloud uses a "reserve and settle monthly" model for pay-as-you-go billing. The system reserves an amount from your available balance to cover usage, and then generates a final bill and deducts the actual cost at the end of the billing cycle (early in the next month).

Why do I have an overdue payment even though I have barely used the service?

Some features of Qwen Cloud, such as web search, are billed separately (post-paid) based on the number of calls and are invoiced separately from model inference fees. Even if you have not actively used the console recently, if the enable_search parameter is enabled in your application code, web search fees are still incurred for each call. Solution:
  1. In your bill details, check the model name and invocation channel that incurred the cost.
  2. Check whether enable_search is enabled in your application code. If you no longer need web search, set this parameter to false or remove it.
  3. If you have stopped all calls but are still being charged, check if other API keys or applications are still running. You can find and delete unused keys on the API Key page.

Where can I see model call counts and statistics?

You can query model call statistics on the Analytics page.