Key Info
OpenRouter has launched the Extractions API in alpha, allowing users to pull specific details out of text, images, and PDFs by describing the fields they need, with each field returned as structured data.
Highlights
- Users describe desired fields, such as names in an email or the total on a receipt, and get structured results back.
- ScaleDown Extract supports text, PDFs, and images.
- Inception's Mercury Decide supports text input.
- A guide is available for getting started.