OpenRouter launches Extractions API: typed JSON field extraction from text, images and PDFs
michellechen · x · 2026-11-12
OpenRouter's Extractions API is now in alpha: you name the fields you want, and a model returns one typed JSON value per field from text, images, or PDFs — no parsing needed. It launches with three extraction models from Cloudflare, Inception, and ScaleDown.
Design highlights:
- Nine field types (text, number, date, time, datetime, list, estimate, etc.), each mapping directly to a storable JSON type
- Pass document content as state; declare each field's type and optional instructions in fields
- A demo invoice request returns six fields at once — invoice number, total, due date, contacts list, and more — with value provenance highlighted
The post's author notes Cloudflare's clairic pioneered this paradigm and that OpenRouter adopting it confirms the industry pain point. It pairs with OpenRouter's earlier Decisions API: one for closed-set judgments, one for structured extraction.
More from coding & agent
- Stanford NLP course's best homework: build your own agent harness — stanfordnlp · 2026-11-12
- Anthropic details agent memory: dreaming organizes Claude's memory, wiki+search hits 61% — RLanceMartin · 2026-11-12
- Talk preview: scaling 1,000 Fable 5.2 agents to formalize Fermat's Last Theorem — RLanceMartin · 2026-11-12
- Opinion: AI infra is becoming a coding runtime as intelligence units outgrow tokens — prateekj · 2026-11-12
- Claude Docs/Slides block external MCP clients: no public API, export only — steipete · 2026-11-12
- Three AI game dev competitions land this month, one with a $47,800 prize pool — Promptmethus · 2026-11-12