OpenRouter launches the Extractions API in alpha for pulling typed fields from documents
AIOpenRouter launches the Extractions API in alpha, which pulls named, typed fields such as totals, dates, and contacts from text, images, and PDFs. Clairic returns spans, p_null, and confidence for single values, while Extract returns a confidence per value and no p_null.
AIWhy it matters.
The post shows how a field-typed request returns values with spans, p_null, and confidence, so readers can check where each answer came from.
Loading source posts…
Source details
OpenRouter Blog · openrouter.aiPublished · added here
Original title: Introducing the Extractions API