api

• document.extract_text — Extract plain text from a PDF or image (base64-encoded). Use when you need raw text for downstream AI analysis (summarization, claim checking, structured extrac
• document.extract_tables — Extract tables and forms as Markdown from a PDF or image (base64-encoded). Use when the document contains structured tabular data such as financial statements,
• document.parse_invoice — Parse a receipt or invoice document into structured fields. Uses a quality AI model for accuracy. Use when you need to extract line items, totals, and merchant
• document.check_claims — Verify a list of factual claims against document text. Uses a quality AI model with citation-level evidence. Use after document.extract_text or url.extract when
• document.extract_structured — Extract typed fields from document text using a caller-defined schema. Uses a quality AI model with retry logic. Use when you need specific data points from a d
• document.summarize — Summarize document text into a prose summary and key points with citations. Use after document.extract_text or url.extract when you need a condensed understandi
• bundle.verify — Verify the cryptographic integrity of an evidence bundle (ev_...) owned by your API key. Checks manifest hash, EIP-191 signature, and R2 artifact hashes. Free —
• collection.create — Create a named document collection for cross-document semantic search and RAG-based Q&A. Free — no credits consumed. Use when you want to group related evidence
• collection.search — Semantic (vector) search across documents in a collection. Returns ranked text chunks with relevance scores. Free — no credits consumed. Use when you need raw m
• collection.ask — Answer a question using RAG over a document collection. Retrieves relevant chunks then synthesizes a cited answer with source attribution. Use when you need a d
• url.extract — Fetch a public HTTPS URL and return extracted text and page metadata. Lean mode — no evidence bundle stored, no bundle_id returned. Use for raw text extraction
• url.summarize

No long description beyond the summary.