# Best document parsing, OCR and extraction APIs for AI agents (slim)

> Google Cloud Document AI (BB), Amazon Textract (BB) and LandingAI Agentic Document Extraction (B) lead the 16 ranked document parsing, OCR and extraction APIs. Picks by need, strengths, weaknesses and prices from the Anchor benchmark.

- Full: https://www.anchorterminal.com/best/document-extraction/index.md (~6,350 tokens) · this version ~1,580 tokens · JSON https://www.anchorterminal.com/best/document-extraction/index.json · canonical https://www.anchorterminal.com/best/document-extraction/
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

The 10 highest-scoring of 16 document parsing, OCR and extraction APIs on the Anchor benchmark, with a pick for each need and where each one falls short. Scores come from public evidence, re-checked as vendors change.

- Ranked: 16 · agent-ready (BB or better): 2 · accept x402: 0 · hosted endpoints: 14
- Full ranked table: https://www.anchorterminal.com/categories/document-extraction.md
- Head-to-head comparisons: https://www.anchorterminal.com/compare/document-extraction/index.md (109)
- Methodology: https://www.anchorterminal.com/benchmark/index.md

## The shortlist

| # | Tool | Grade | Score | Best for | Price | Where |
| --- | --- | --- | --- | --- | --- | --- |
| 1 | [Google Cloud Document AI](https://www.anchorterminal.com/tools/google-cloud-document-ai.md) | BB | 73.9 | Agents already on Google Cloud that need OCR, form and table extraction or chunks for retrieval, with IAM, audit logs and EU processing. | $1.50 / 1k pages | local |
| 2 | [Amazon Textract](https://www.anchorterminal.com/tools/amazon-textract.md) | BB | 73.5 | Teams already on AWS with documents in S3 that need OCR, tables and form fields at volume with IAM and CloudTrail controls, and for US invoices, receipts, identity documents and mortgage packages. | $1.50 / 1k pages | hosted |
| 3 | [LandingAI Agentic Document Extraction](https://www.anchorterminal.com/tools/landingai-agentic-document-extraction.md) | B | 69 | Agents that need Markdown with block-level page coordinates and schema extraction with citations, in the US or EU. | $0.01 / credit | hosted |
| 4 | [Azure Document Intelligence](https://www.anchorterminal.com/tools/azure-document-intelligence.md) | B | 66 | Teams already on Azure that want OCR, layout to Markdown and prebuilt invoice, receipt, identity and tax models with Entra ID and regional processing. | $1.50 / 1k pages | local |
| 5 | [Extend API + MCP](https://www.anchorterminal.com/tools/extend.md) | B | 62.9 | Teams building production extraction with evaluation sets and versioned processors, and for agents that need to build or tune extractors as well as run them. | $25 / 1k pages | hosted |
| 6 | [Reducto API + MCP](https://www.anchorterminal.com/tools/reducto.md) | B | 62.9 | Messy PDFs, tables and spreadsheets where an agent needs parse, extract and split behind one small MCP. | $10 / 1k pages | hosted and local |
| 7 | [Mindee API](https://www.anchorterminal.com/tools/mindee.md) | C | 61.3 | Teams with a fixed set of document types (invoices, receipts, IDs) who want short retention and EU processing. | $44 / mo | hosted |
| 8 | [LlamaParse API + MCP](https://www.anchorterminal.com/tools/llamaparse.md) | C | 59.2 | RAG ingestion where cost per page matters and a tier can be picked per document, and for agents that want a small MCP surface. | $1.25 / 1k pages | hosted |
| 9 | [Mistral OCR API](https://www.anchorterminal.com/tools/mistral-ocr.md) | C | 58.8 | Turning PDFs and scans into Markdown for RAG or reading at a flat, low page price. | $4 / 1k pages | hosted |
| 10 | [OpenDocRouter](https://www.anchorterminal.com/tools/opendocrouter.md) | C | 56.6 | Agents that need page-level markdown from PDFs and images and want to choose or compare models on price and published benchmark scores with one key. | $48.82 / 1k pages | hosted |

## Picks by need

- Highest score overall: [Google Cloud Document AI](https://www.anchorterminal.com/tools/google-cloud-document-ai.md), BB, 73.9/100 on the benchmark. Also [Amazon Textract](https://www.anchorterminal.com/tools/amazon-textract.md), BB, 73.5/100.
- Reliability: [Amazon Textract](https://www.anchorterminal.com/tools/amazon-textract.md), 96/100 on reliability, against 90 for the overall leader.
- Schema & documentation: [Mistral OCR API](https://www.anchorterminal.com/tools/mistral-ocr.md), 89/100 on schema & documentation, against 81 for the overall leader.
- Agent ergonomics: [Reducto API + MCP](https://www.anchorterminal.com/tools/reducto.md), 84/100 on agent ergonomics, against 70 for the overall leader.
- Maintenance & community: [LandingAI Agentic Document Extraction](https://www.anchorterminal.com/tools/landingai-agentic-document-extraction.md), 85/100 on maintenance & community, against 80 for the overall leader.
- Lowest paid price per 1,000 pages: [OpenDocRouter](https://www.anchorterminal.com/tools/opendocrouter.md), $0.80 per 1,000 pages, the lowest of the 13 listings here with a paid price in this unit (free allowances aside). Also [LlamaParse API + MCP](https://www.anchorterminal.com/tools/llamaparse.md), $1.25 per 1,000 pages.
- A hosted MCP endpoint: [Extend API + MCP](https://www.anchorterminal.com/tools/extend.md), remote MCP server, nothing to install.
- Self-hosting under an open licence: [Unstructured API + MCP](https://www.anchorterminal.com/tools/unstructured.md), self-hosted, Apache-2 licence.

## How to choose

- Text accuracy on scans: Test text accuracy on your own scans, since clean born-digital PDFs hide the errors that matter when an agent reads a faded, skewed or handwritten page.
- Table structure and layout: Check that tables keep their rows, columns and merged cells, since a flattened table can look correct as text while the figures no longer line up for the agent.
- Page references for citations: Look for page references on each extracted field, so an agent can cite the source page and a person can check a figure against the original document.
- Price per page and file limits: Compare price per page at the volume you expect, and check the file types and sizes accepted, since long scanned PDFs can cost more or fail outright.

- How the benchmark tests this category: The same scans, invoices, tables and long PDFs through every API. We score text accuracy, table structure, field extraction, page references, processing time and price per page.

Each listing's verdict, strengths and weaknesses: https://www.anchorterminal.com/best/document-extraction/index.md