For AI agents: The documentation index is at https://docs.digitalocean.com/llms.txt. Markdown versions of pages use the same URL with index.html.md in place of the HTML page (for example, append index.html.md to the directory path instead of opening the HTML document).

Serverless Inference requires a positive prepaid account balance before you can send inference requests. DigitalOcean deducts usage charges from this balance as you incur them. The balance is shared across your entire account, so charges from other DigitalOcean products also draw from it. When your balance reaches $0, DigitalOcean suspends your access to Serverless Inference until you replenish it. For details, see How Other Products Affect Your Prepayment Balance.

On the Serverless Inference page, a banner displays your current account prepayment balance and whether auto-reload is enabled. To keep inference running, you can add a prepayment balance manually or enable auto-reload to replenish your balance automatically.

Add a Prepayment Balance

A prepayment is a one-time payment that adds funds to your account balance ahead of your usage. To add a prepayment balance, on the Serverless Inference page, click Add prepayment in the banner. This opens the Make a payment page, where you can enter an amount and pay with a saved payment method or a third-party provider.

After your payment processes, your account prepayment balance updates and Serverless Inference access resumes if it was suspended.

How Other Products Affect Your Prepayment Balance

Your prepayment balance applies to your entire account (your current team), not only Serverless Inference. Usage charges from all DigitalOcean products, such as Droplets or Managed Databases, draw from the same balance.

Serverless Inference is currently the only product DigitalOcean suspends when your balance reaches $0. Other products continue running as usual, even if their charges are what depleted the balance.

For example, if you add a $500 prepayment to your account:

1. You run Serverless Inference workloads that cost $100, leaving a balance of $400.
2. Your Droplets accrue $250 in usage charges, leaving a balance of $150.

Only the remaining $150 is available for Serverless Inference. If charges from other products bring the shared balance down to $0, DigitalOcean suspends your access to Serverless Inference until you add more funds, but your Droplets and other resources continue running without interruption.

To avoid interruptions, size your prepayments to cover everything running on your account, or enable auto-reload to replenish your balance automatically.

To keep a separate budget for Serverless Inference, create a dedicated team for those workloads. Each team maintains its own prepayment balance, so charges from resources on your other teams do not draw it down.

Enable Auto-Reload

Auto-reload keeps Serverless Inference running by automatically adding to your account prepayment when your balance runs low. When you enable it, you agree to recurring charges on the payment method on file whenever your balance reaches the threshold you set.

To enable auto-reload:

1. On the Serverless Inference page, click Turn on auto-reload in the banner to open the Serverless Inference auto-reload window.

2. Select the Enable Serverless Inference auto-reload checkbox.

3. Under Reload when balance reaches or goes below, choose the balance threshold that triggers a reload. You can select $5, $10, or $25, or click Custom to enter your own amount.

4. Under Reload amount, choose how much to add to your balance each time auto-reload runs. You can select $5, $25, or $100, or click Custom to enter your own amount.

5. Click Enable auto-reload to save your settings. Changes take effect immediately and apply to all future reloads.

DigitalOcean charges your primary payment method first. If that payment fails, we may attempt your backup payment method. You can review, modify, or pause your auto-reload settings at any time from the Serverless Inference page.