Rate Limits

You can call the Einstein Platform Services APIs as often as you need to create datasets, add examples, and train models. However, there are limits to the number of prediction calls you can make.

Einstein Platform Services provides two tiers of usage: free and paid. Each tier gives you a specific number of prediction calls. These limits apply only to predictions. A prediction is any POST call to these endpoints:

  • /vision/predict
  • /vision/detect
  • /vision/ocr
  • /language/intent
  • /language/entities
  • /language/sentiment

A prediction call includes both predictions made from custom classifiers and predictions made from the pre-built classifiers.

When you sign up for an Einstein Platform Services account, you get 2,000 free predictions each calendar month. You get 2,000 predictions on the first of every month to be used by the last day of the month.

When you exceed the maximum number of predictions for the current calendar month, you receive an error message when you call one of the prediction resources.

If you need more predictions than are available in the free tier, you can purchase them. Purchased predictions are also provisioned on a calendar month basis.

  • Heroku—If you signed up for an account using the Heroku add-on, you can purchase more add-on credits. See the Einstein Vision and Language add-on page for more information about plans and pricing.

  • Salesforce—If you signed up for an account using Salesforce, contact your account executive to purchase predictions for Einstein Vision and Language. To add predictions to an existing account, you must provide the organization ID for your Einstein Platform Services account. To get your Einstein Platform Services organization ID, call the usage API. See Get API Usage.

If you’re not sure what method you used to sign up or if you have any questions, post on the Einstein Platform developer forum.

There are two ways you can get your prediction usage information from the Einstein Platform Services APIs.

  • Response headers—headers that contain basic rate limit information are returned by a call to any of the prediction resources. These headers give you a way to monitor your prediction usage as prediction calls are made.
  • The /apiusage resource—contains detailed information about your limits and prediction usage.

Any time you make an API call to the prediction resources, rate limit information is returned in the header. The rate limit headers specify your prediction usage for the current calendar month only.

If you want to see detailed plan information, make an explicit call to the /apiusage resource. See Get API Usage.