--- site_search: "GET /ask?q={query} (read-only search over extend.ai and docs.extend.ai; returns links and quoted passages, not generated answers)" title: "Parse API: Layout-Aware Document Parsing to Markdown | Extend" description: "Vision models go beyond OCR to turn PDFs, scans, images, and Office files into LLM-ready markdown and typed blocks with bounding boxes. 95.7% field-level Q&A accuracy on RealDoc-Bench." canonical: https://www.extend.ai/parse --- # Parse API: Layout-Aware Document Parsing to Markdown | Extend > Search this site and the docs: [`/ask?q=…`](/ask?q=webhook+retries) returns matching pages from extend.ai and docs.extend.ai, with quoted passages. Parse API ## Turn any document into markdown your agents can read State of the art vision models to turn any file into LLM-ready markdown and typed blocks with bounding boxes, so checkboxes, tables, and handwriting keep their structure. [Try for free](https://dashboard.extend.ai/) · [Book a demo](https://www.extend.ai/get-started) ## What it does ### Reads every page, keeps the layout Goes beyond OCR: vision models read printed text, handwriting, checkboxes, and multilingual pages, then rebuild reading order, tables, and key-value pairs. ### Markdown plus typed blocks Each page returns markdown chunks and blocks typed as text, table, figure, or key-value, each with a bounding box for citations. ### Three engines Performance for the hardest pages, Light for high-volume ingestion, and Auto to route each page by difficulty. Chunk by page, section, or document. ## Under the hood Convert unstructured documents into context for agents. ### Layout detection Advanced layout model detects tables, checkboxes, images, handwriting, and signatures on every page. ### Specialized vision models A hybrid computer vision + vision-language model pipeline routes each element to purpose-built models. ### Multiple performance modes Toggle between performance modes optimized for speed, cost, or accuracy. ### Handle every file 35+ file types, 100+ languages, and 4 chunking strategies — all through one API. ## Benchmarks ### RealDoc-Bench: 95.7% Field-level document Q&A accuracy, Performance Parse 1,359 Q&A prompts across 581 real documents in four regulated industries. Source: [RealDoc-Bench report](https://www.extend.ai/resources/realdocbench.md) ### RealDoc-Bench: 90.5% Per-field accuracy, Light Parse at $0.005 per page The most accurate parser with no agentic configuration enabled. Source: [Light Parse launch post](https://www.extend.ai/resources/introducing-light-parse.md) ### OpenBenchmarks: 93.1% Downstream answer accuracy on redlined contracts, ranked #1 Third-party benchmark Independent benchmark: 1,500 questions on 94 contracts from RedlineBench, parsed with Performance Parse. Results updated October 25, 2026. Source: [OpenBenchmarks leaderboard](https://openbenchmarks.com/document-processing/best-document-parsing-apis) ## How to get started ### 1. Create an account Sign up at dashboard.extend.ai. New accounts get 10,000 free credits. Copy an API key from the Developers page and export it as EXTEND_API_KEY. [Sign up](https://dashboard.extend.ai/) · [Developers page](https://dashboard.extend.ai/developers) ### 2. Choose how to call Parse Studio: try Parse in the browser with no code. MCP: connect Claude, Cursor, or any MCP client to https://mcp.extend.ai/mcp. CLI: install with curl -fsSL https://extend.ai/install.sh | sh, then run extend setup. SDKs: pip install extend-ai or npm install extend-ai; Java and Go SDKs are also available. [Open Studio](https://dashboard.extend.ai/studio) · [MCP setup](https://www.extend.ai/agents/mcp.md) · [CLI setup](https://www.extend.ai/agents/cli.md) · [SDK docs](https://docs.extend.ai/sdks) ### 3. Process your first document Send a file URL and get back markdown chunks and blocks for every page. ```bash curl -X POST https://api.extend.ai/parse \ -H "Authorization: Bearer $EXTEND_API_KEY" \ -H "x-extend-api-version: 2026-02-09" \ -H "Content-Type: application/json" \ -d '{ "file": { "url": "https://extend-public-files.s3.us-east-2.amazonaws.com/bank_statement_example.pdf" } }' ``` ### 4. Move to production Send production traffic to POST /parse_runs; the synchronous POST /parse times out after 5 minutes. [Parse File API reference](https://docs.extend.ai/api-reference/endpoints/parse/parse-file) ## Pricing From $5 per 1,000 pages with Light Parse, and $20 with Performance Parse. [See full pricing](https://www.extend.ai/pricing.md) ## Documentation - [Parsing overview](https://docs.extend.ai/parsing/overview) - [Parse File API reference](https://docs.extend.ai/api-reference/endpoints/parse/parse-file) - [API quickstart](https://docs.extend.ai/api-quickstart) ## Related reading - [Introducing Parse 2.0 and RealDoc-Bench](https://www.extend.ai/resources/parse-2-and-realdocbench-launch.md) - [Introducing Light Parse](https://www.extend.ai/resources/introducing-light-parse.md) - [Introducing Auto-Router for Parsing](https://www.extend.ai/resources/introducing-auto-router-for-parsing.md) ## Use cases ### Receipts & expenses Read merchants, line items, and totals from receipts, including phone photos. [Brex case study](https://www.extend.ai/resources/how-brex-reached-99-accuracy-across-millions-of-financial-documents.md) ### Loan packets & tax forms Turn bank statements, W-2s, and 1099s into layout-aware markdown for downstream agents. [Financial services](https://www.extend.ai/financial-services.md) ### Invoices across vendor layouts Keep tables and totals intact when every vendor formats invoices differently. [Logistics](https://www.extend.ai/logistics.md) ### Medical records & EOBs Parse claims, EOBs, and charts with dense tables and checkboxes into clean blocks. [Healthcare](https://www.extend.ai/healthcare.md) ### RAG ingestion Section-level chunks with bounding boxes feed retrieval and page citations. [Parse 2.0 launch post](https://www.extend.ai/resources/parse-2-and-realdocbench-launch.md) ### Handwritten & scanned forms Vision models read handwriting and low-quality scans without losing the form's structure. [RealDoc-Bench report](https://www.extend.ai/resources/realdocbench.md) ## More products - [Extract](https://www.extend.ai/extract.md) - [Split](https://www.extend.ai/split.md) - [Verify](https://www.extend.ai/verify.md) - [Classify](https://www.extend.ai/classify.md) - [Edit](https://www.extend.ai/edit.md)