Skip to main content
Report generator turns extracted data into a written report. You give it a Markdown template. After Extract finishes, the node fills the template with the extracted values and stores the result as a Markdown file you can download. Saving the workflow stores the template only. No model runs until a document does.

The node

Options

The schema the API accepts is generated from the same source: Report generator node schema.

Cost

A report costs 25 credits, per report written and not per page. A run that writes one report adds 25 credits to usage.credits. Behind a Split node the Report generator writes one report per split, so N reports cost 25N credits. A report that is not written costs nothing, and a failed report ends the run in error, which is not charged. See How credits work.

Connects to

Report generator reads the Extract node that feeds it, through exactly one incoming edge. The Python and TypeScript builders add it only to a workflow with a single Extract; send the node in the API JSON to attach it to one branch of a classified workflow.

What it returns

The node fills the reports section of the run results: one entry per split the node generated a report for.
status is pending, succeeded or failed. download_url is valid for 15 minutes from the moment the response was built, so re-read the run for a fresh link. In the SDKs, result.reports holds the same entries, in Python and in TypeScript.