The Data Extraction API stores processing runs as a product feature. A run includes the input document and extracted output.
Use run history to view and manage stored runs. Delete runs you no longer need. Runs remain in your run history until you delete them.
Some plans enable data retention. For those plans, we retain an internal copy of run data to operate, improve, and develop our services. This use includes model training and evaluation.
The internal copy differs from the run history you can view and delete. For plans without data retention, we don’t retain documents for those purposes.
The API also returns extracted content directly in the API response.
For full details, including the legal basis, product storage, internal retention, and deletion requests, refer to the Nutrient API Privacy Policy.
Refer to these guides for related Data Extraction API setup and policy details:
- Getting started for your first extraction request.
- API overview for request and response fundamentals.
- Data Extraction API overview for product scope and concepts.
- Pricing for credit and plan details.
- Security for security controls and practices.