Serverless Pricing

The Serverless Hosted API uses Roboflow's credit-based billing system. You are charged credits based on the processing time of each inference request.

How Credits Are Calculated

Each inference request consumes credits based on the server-side processing time:

  • Minimum billable time: 100ms
  • Credit formula: max(processing_ms, 100) / 500,000

For example, a request that takes 200ms to process would consume 200 / 500,000 = 0.0004 credits.

Limits

The Serverless Hosted API supports file uploads up to 20MB. You may run into limitations with higher resolution images.

Note

In cases where requests are too large, we recommend downsizing any attached images. This usually will not result in poor performance as images are downsized regardless after they have been received on our servers to the input size that the model architecture accepts.

Some of our SDKs, like the Python SDK, automatically downsize images to the model architecture's input size before they are sent to the API.

Credit Types

Credits are consumed in the following order:

  1. Included Credits: Credits included with your Roboflow plan are used first. They reset monthly or annually depending on your billing cycle.
  2. Prepaid Credits: Purchased in advance, consumed after included credits are exhausted.
  3. Flex Credits: Used when flex billing is enabled and both included and prepaid credits are exhausted. Billed monthly for the previous month's usage.
Note

Credits can be purchased in bulk at a discounted rate by talking with the Roboflow Sales team.

For the most up-to-date information on credits and their associated costs, see the Roboflow credits page.