Introducing Page Extract API VectifyAI launched the Page Extract API, which takes a JSON Schema describing desired fields and returns values extracted from any PDF as JSON matching that schema, including long filings, scans and tables of thousands of rows. On ExtractBench's 370 documents, Page Extract pro scored 96.80 value F1 at $0.05 a page and Page Extract standard scored 96.37 at $0.03 a page, above LlamaExtract Agentic Plus (96.17 at $0.075), Reducto Deep Extract (96.08 at $0.0635) and Pulse (96.07 at $0.105), with VectifyAI noting standard costs 60% less per page than LlamaExtract Agentic Plus. The API is available through the PageIndex SDK via pip install -U pageindex, supports Pydantic models, page-level citations with cite_sources, page-range extraction and background jobs, and shares an account with the Page Search API. Today we are introducing Page Extract API : describe the fields you want in a JSON Schema, and get them back from any PDF as JSON that fits it. Long filings, scans, and tables of thousands of rows included. Page Extract is powered by PageIndex Agent https://pageindex.ai/blog/pageindex-agent . Where the agent answers a question, Page Extract fills a schema: it finds where each field lives in the document, reads those pages, and returns the values, in the shape you asked for. We ran Page Extract on ExtractBench https://github.com/run-llama/ExtractBench : 370 documents, from one page to 192, each with a schema and the values a careful reader would extract. The measure is value F1 over every field, next to what each method costs a page: | Method | Value F1 | Cost a page | |---|---|---| | Page Extract pro | 96.80 | $0.05 | | Page Extract standard | 96.37 | $0.03 | | LlamaExtract Agentic Plus | 96.17 | $0.075 | | Reducto Deep Extract | 96.08 | $0.0635 | | Pulse Effort | 96.07 | $0.105 | | LlamaExtract Agentic | 95.65 | $0.0312 | | Codex GPT-6.1 Sol | 95.31 | $0.0713 | Page Extract pro is the most accurate method on ExtractBench. Page Extract standard still scores above every other method, at $0.03 a page: 60% less than LlamaExtract Agentic Plus, the most accurate of the others. The other rows are from ExtractBench's leaderboard; ours are our runs of November 8, 2026, priced at what we charge. Every document's result and score, and a script to run it again, are on GitHub https://github.com/VectifyAI/pageindex-extract-benchmarks . Install the PageIndex SDK, describe what you want, and extract: pip install -U pageindex python from pageindex import PageIndexClient client = PageIndexClient index="cloud" reads PAGEINDEX API KEY schema = { "type": "object", "properties": { "company": {"type": "string", "description": "The company's name, as printed on the cover"}, "segments": { "type": "array", "description": "Each business segment in the segment results table", "items": { "type": "object", "properties": { "name": {"type": "string"}, "revenue usd millions": {"type": "number", "null" , "description": "Revenue, in millions of dollars"}, }, }, }, }, } job = client.extract "report.pdf", schema sends the file, waits for the result print job "extract result" The result fits the schema. A value the document does not give comes back as null , and every row of a list comes back, in the order printed, however many there are. In Python the schema can also be a Pydantic model, with the result parsed back into it. - Your schema is the instruction. Each field's description tells Page Extract what to look for; see Writing a schema https://pageindex.ai/docs/extract/schemas . Anything about the whole document, such as "amounts are in thousands", goes in the instructions. - Long tables, in full. A 13F filing's holdings table comes back as all of its 3,000-odd rows, not the first page of them. - The page each row came from. With cite sources , every list item carries the page it was read from, to check any value against its page. - Two tiers. standard $0.03 a page for most documents; pro $0.05 a page for the hardest: values worked out across many pages, diagrams, dense charts and long drawings. - Some pages only. Extract from a range of pages, and pay only for those. - In the background. Each extraction is a job: start it, come back for the result, or list, cancel and delete jobs. See Options and jobs https://pageindex.ai/docs/extract/options . - One account with Page Search. The same key, credit and documents work with Page Search API https://pageindex.ai/blog/page-search-api . Create a key in the Developer Dashboard https://developer.pageindex.ai/api-keys and follow the Quick start https://pageindex.ai/docs/extract/quick-start , or paste this into Claude Code, Cursor, or any coding agent that can read a URL: Read https://pageindex.ai/docs/extract/quick-start.md and follow it to set up Page Extract API in this project. Read more on the Page Extract API page https://pageindex.ai/extract .