The Prediction API (a.k.a. PAPI) provides a programmatic way to generate predictions using your Analyses from external applications such as Business Intelligence (BI) platforms, business rules engines, CRM systems and many more.
NOTE: When using the Prediction API to generate predictions, the Prediction API input data records must have the same columns (and respective column types) as your training dataset as it exists AFTER any Data Pipeline steps are applied. For example, if your training dataset has a column called "Territory" that you rename to "State" in a Data Pipeline step, your Prediction API input data should have a column called "State" (NOT "Territory") since Data Pipeline steps are not applied to your Prediction API input data records.
The current version of the API is 1.0.
Authentication is managed using an API key that must be included in the authorization header for every call as a token.
Authorization: token [API key here]
HTTP Return Codes
- 200 will be returned if the call was successful
- 301 will be returned if the URL is incorrect. This is likely if the URL is using http:// and not https://
- 400 if there is an error with the request
- 404 will be returned if the URL is incorrect. This is likely if the URL is using http:// and not https://
Currently, there is no rate limit for the API. However, if we find that this is being abused with an extremely excessive amount of API calls, we will block the API key and IP address if necessary.
The base URL for all calls is: