In MonkeyLearn, each classification or extraction task is considered a query, whether or not it’s done by the API, via the interface, or from any other integration.

A single API request can consume multiple queries (classifications or extractions). That is, if a classifier model is called with 150 texts, it will perform 150 classifications and will consume 150 queries.

Not every API request consumes queries: getting model details, training, deploying, uploading text data, etc, do not consume queries.

Every call to the API returns an X-Query-Limit-Request-Queries parameter which tells how many queries were consumed by that call. The API Reference documentation details how many queries consumes each API call.

Did this answer your question?