Introduction
IDPForge turns unstructured documents into structured, validated data — through pipelines you configure, review queues your team works, and an API you call from anywhere.
What IDPForge does
You point IDPForge at documents — uploaded, emailed, dropped in storage, or posted to the API. It splits packages into individual documents, classifies each one, extracts the fields your schema defines, validates them, and delivers the result to a destination system. Anything the model is not confident about becomes an exception that a person clears in a review queue.
Pick your path
Sandbox and production
Every workspace has two environments. Sandbox is free, rate-limited, and seeded with sample documents — use it for development and for anything you would not want billed. Production is metered in pages against your plan allowance. Keys, pipelines, schemas and webhooks are environment-scoped and never cross over.
Every example in these docs runs against sandbox with the sample corpus. No production data or billing is involved.
Accounts and billing
Work is metered in credits — every job reserves credits, settles to what it used, and returns the rest, so a failed job costs nothing. You can run inference on IDPForge's models or bring your own provider key.
Conventions in these docs
- How-to pages walk one task in the product UI, screen by screen.
- Reference pages describe what a thing is and every option it takes.
- Scenario pages follow one realistic end-to-end job from intake to delivery.
- Values you replace are written like
{workspace_id}. Anything in a code block is copy-safe.