Nutrient document API comparisons
Published by NutrientUpdated

Extend alternatives

Verdict

Extend bundles Parse, Extract, Classify, Split, and Edit with human review, evaluation sets, and a hosted MCP server, bills $0.0125 per credit on pay-as-you-go after 10,000 free credits, and runs as SaaS, BYOC, or hybrid, and lists no on-prem option in its docs. People look for alternatives when they want on-prem or air-gapped deployment, per-page USD list prices, a hyperscaler contract, or a renewing free tier.

Choose Reducto for list prices per 1,000 pages and deployment up to air-gapped. Choose LlamaParse for 130-plus input formats and a Fast tier at about $1.25 per 1,000 pages. Choose Azure AI Document Intelligence when you are on Azure and want prebuilt invoice, receipt, ID, and contract models at $10 per 1,000 pages with containers for Read and Layout. Choose Nutrient Data Extraction for parse, extract, classify, and split in one credit pool, grounded extraction with match labels, and 5,000 credits renewing monthly. Nutrient was founded as PSPDFKit in 2011. 3,000-plus organizations, including 15 percent of the Global 500, rely on it, with over a billion document interactions a year. The same extraction engine runs hosted, self-hosted in the Python and Java SDKs with no external API calls for OCR and ICR, or on a Mac in Extract Studio.

At a glance

Extend, Reducto, LlamaParse (LlamaCloud), Azure AI Document Intelligence, Nutrient Data Extraction API; facts fetched 2026-10-15 to 2026-10-16
FactExtendReductoLlamaParse (LlamaCloud)Azure AI Document IntelligenceNutrient Data Extraction API
Product typehosted API[1]hosted API[2]hosted API[3]hosted API (Azure resource, REST + SDKs, Document Intelligence Studio); Read and Layout also ship as Docker containers[4]Hosted Data Extraction API, web Studio, and macOS Extract Studio[5]
Output formatsMarkdown, JSON, HTML tables[6]Markdown, JSON, HTML tables[7]Markdown, Plain text, JSON (per-page items), XLSX, HTML tables, Annotated PDF, Structured JSON to custom schema[3]JSON (analyzeResult), Markdown (outputContentFormat=markdown, tables rendered as HTML), searchable PDF (prebuilt-read only)[8]Spatial JSON, Markdown, Schema-shaped JSON with citations, Ranked labels with independent 0-1 scores, Split page ranges and ZIP files[9]
OCR for scansYes[10]Yes[11]Yes[12]Yes[13]Yes: structure, understand, and agentic; text has no OCR; 100+ languages[14]
HandwritingYes[10]Yes[15]Yes[16]Yes[8]Yes: printed-style in understand; cursive/freeform needs agentic[17]
TablesYes[10]Yes[15]Yes[3]Yes[8]Yes: spans and bounds; complex tables may need agentic mode[17]
Layout and bounding boxesYes[18]Yes[15]Yes[19]Yes[8]Yes: element and optional word bounds; word bounds exclude XLSX[17]
Per-field confidenceYes[20]Yes[21]Yes[22]Yes[8]Yes: 0-1 relative signal, not a probability[23]
Source citations and groundingYes[24]Yes[21]Yes[22]Yes[8]Yes: field boxes, match labels, confidence, and source boxes[23]
Schema extractionYes[25]Yes[26]Yes[27]Yes[28]Yes: closed JSON Schema subset; 128 KB, 2,000 nodes, depth 5[29]
ClassificationYes[30]Yes[31]Yes[32]Yes[33]Yes: zero-shot, 2+ labels; independent 0-1 scores; 1 credit/page[34]
Document splittingYes[35]Yes[36]Yes[37]Yes[33]Yes: boundary detection for PDF/images; 3 credits/page[38]
Free tier10,000 free credits, then pay-as-you-go (no contract, monthly minimum or sales call)[10]$150 in free usage (Standard plan)[39]Includes 10K credits (Free plan, $0/month)[3]Free (F0) instance: 0-500 pages free per month (pricing page); F0 analyzes only the first 2 pages per request, 4 MB max file, 1 TPS; no premium features or Query meter; Azure free account adds $200 credit for 30 days[40]5,000 credits/month; no card; all parse modes, including Auto[41]
Pricing modelCredits per page by operation and mode (Performance vs Light); plan sets the per-credit rate[42]USD per 1,000 pages, per endpoint; Growth/Enterprise custom with volume discounts[43]Credits per page by tier; 1,000 credits = $1.25 (i.e. $0.00125/credit). Parse v2 tiers: Fast 1, Cost-effective 3, Agentic 10, Agentic Plus 45 credits/page. Add-ons: layout extraction +3, enriched forms +10 per form page, spreadsheet 1/sheet, audio 3/min.[44]per 1,000 pages by model family (Read cheaper than Layout/prebuilt/custom), volume tier for Read over 1M pages, plus add-on, query-field, training-hour meters; batch meters; commitment tiers for connected and disconnected containers[40]Credits/page by endpoint and mode; Auto routes each page and bills that mode's rate; subscription plus capped overage[45]
List price examplesPay As You Go: $0.0125 per credit (10,000 free credits, all APIs, ZDR, no BAA, limited rate limits)
Scale: $500 / month (50,000 credits/month included, then $0.01 per credit; Slack support; HIPAA/BAA add-on)
Enterprise: Custom (BYOC and Hybrid, SSO/SAML, custom MSA/DPA/SLA, custom models, dedicated support)
Per-page (Performance, PAYG): Parse 2 credits ($0.025); Extract 3 ($0.0375); Split 2 ($0.025); Classify 1 ($0.0125); Edit filling 1 ($0.0125); Form detection 2 ($0.025) (Extract also triggers an automatic Parse: pricing FAQ example is a 10-page extract = 50 credits (~$0.63))
Per-page (Light, PAYG): Parse 0.5 ($0.00625); Extract 0.7 ($0.00875); Split 0.5; Classify 0.3 (Light is lower accuracy on poor scans, hard handwriting, large tables)
Operator extraction: 5 credits/page (agent-guided extraction, with rare overages)[42]		Standard (list), Parse r-1: $10 / 1,000 pages (r-1 parse; OCR data return / Parse citations +$2/1k; prompted blocks +$5/1k)
Standard (list), Extract: $20 / 1,000 pages (parsing included; dense extractions (>100 fields/page) may incur per-field surcharge)
Standard (list), Deep Extract: $40 / 1,000 pages (agentic extraction; not eligible for batch discount)
Standard (list), Split / Deep Split: $20 / $40 per 1,000 pages (parsing included)
Standard (list), Classify / Deep Classify: $7.50 / $15 per 1,000 pages (first 5 pages by default; Deep Classify is alpha pricing)
Standard (list), Edit: $60 / 1,000 pages ($15 for fully prefilled pages) (standalone, cannot be combined with other products)
Batch queue: -20% on Parse and Extract (async, 12-hour completion guarantee)
Growth / Enterprise: Custom (contact sales) (volume discounts, ZDR, BAA, EU/AU residency (Growth); VPC/on-prem, SSO/SAML, SLA (Enterprise))[39]		Free: $0/month (10K credits; 5 concurrent parse jobs; community support)
Starter: $50/month (40K credits; pay-as-you-go up to $500/mo (400K credits); basic email support)
Pro: $500/month (400K credits; pay-as-you-go up to $5,000/mo; 20 concurrent jobs; priority Slack Connect support; limited-time one-time bonus of 800K credits ($1,000) for business email domains)
Enterprise: Custom (Volume discount, 5x higher rate limits, SSO, SaaS or hybrid/VPC deployment, dedicated account manager, 100 concurrent jobs, custom BAAs)[3]		Read (S0): $1.50 per 1,000 pages (first 1M); $0.60 per 1,000 over 1M (OCR text, handwriting, searchable PDF)
Layout / all prebuilt models (S0): $10 per 1,000 pages (Layout, Invoice, Receipt, ID, W-2, tax, health insurance card, contract etc. (pricing page: 'All Prebuilt Models: Document, Layout, Receipt, Invoice, ID, W-2, 1098 Tax forms, Health insurance card, Contract'))
Custom extraction (S0): $30 per 1,000 pages (template/neural custom models; custom generative extraction also $30 per 1,000)
Custom classification (S0): $3 per 1,000 pages (classifier/splitter)
Add-on capabilities (S0): $6 per 1,000 pages (high resolution OCR, font, formulas)
Query Fields (S0): $10 per 1,000 pages (Retail API also lists a 2023 meter 'S0 Query Pages' at $200 per 1,000; the newer 'pages for query fields' meter (effective 2024-11-01) is $10.)
Custom model training (S0): $3 per hour of training (template training free; neural free for first 10 hours (FAQ))
Batch Read / Layout / prebuilt / custom / generative / classifier: Read $1.50 (first 1M) then $0.60; Layout $10; prebuilt $10; custom $30; generative $30; classifier $3; query $10; add-on $6 per 1,000 pages (batch meters)
Content Understanding (separate service) document content extraction: Minimal ~$0.01, Basic $1, Standard $5 per 1,000 pages (+ model token charges for field extraction) (Retail API East US, effective 2025-12/2026-01; Learn pricing explainer (https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/pricing-explainer) defers numbers to the pricing page. Sync preview meters effective 2026-08-01: Basic $1.50, Standard $7.50.)[46]		Per-page credits: parse 1-18; extract 7-24 (classify 1; split 3)
Auto mode: bills each page at the mode it selects (recommended starting mode; routes clean pages to structure and scans or complex forms to understand)
Free: $0/month (5,000 credits; PAYG after a $25 wallet load)
Starter: $59/month; $49/month annual (25,000 credits; $0.0028 per extra credit)
Pro: $500/month; $450/month annual (500,000 credits; $0.0012 per extra credit)[41]
DeploymentSaaS, VPC[1]SaaS, VPC, on-prem, air-gapped[2]SaaS (US and EU regions), VPC / hybrid cloud, single-tenant SaaS, BYOC (Azure, AWS, GCP), self-hosting[47]cloud (Azure regions; list at https://azure.microsoft.com/explore/global-infrastructure/products-by-region/table), Docker containers: v4.0 Read and Layout; v3.1 Read, Layout, ID, Receipt, Invoice; v3.0 incl. Custom, connected and disconnected containers (commitment tiers)[48]Hosted API: Nutrient-managed cloud, Self-hosted: Data Extraction SDK for Python and Java, no network required; OCR and ICR run on your infrastructure with zero external API calls, Local VLM: Ollama, LM Studio, or vLLM on your own hardware, or your own OpenAI or Anthropic key, Desktop: Extract Studio for Apple silicon Macs (macOS Tahoe 26.4+); the engine runs on the Mac and, with a local model, documents never leave it; Nutrient counts pages for credits, .NET data extraction SDK also offered[49]
SDKsPython, TypeScript, Java, Go, CLI[50]Python, Node.js, Go, REST API, CLI[51]Python (llama-cloud, PyPI 2.18.0 at fetch), TypeScript (@llamaindex/llama-cloud), Go, Java, CLI, REST API, n8n node[52].NET (C#), Java, JavaScript, Python, REST[53]REST API, Python SDK, Java SDK, .NET page referenced, curl, JavaScript, and raw HTTP samples[54]
MCP or agent toolsHosted MCP server (https://mcp.extend.ai/mcp, OAuth), extend CLI with 'extend-cli' skill, agents.md[55]MCP server (local: uvx mcp-server-reducto; hosted: https://mcp.reducto.ai/mcp), CLI, llms.txt and agent guide[56]Hosted LlamaParse Platform MCP at mcp.llamaindex.ai/mcp (Parse, Classify, Extract, Split, Index); docs-search MCP; agent skills/plugins for Claude Code and Codex[57]Not published[4]Hosted MCP, Data Extraction Studio, and agent skills[58]
Maximum file size or pagesNot published[10]100 MB direct upload; up to 5 GB via presigned URL; no page limits on Standard plan[59]{"Batches": "10,000 files per batch (Pro/Enterprise)", "Classify": "512 MB", "Extract": "100 MB, 500 pages per job", "Parse": "512 MB, no page cap", "Split": "512 MB (PDF/DOCX/PPTX)"}[60]S0: 500 MB, 2,000 pages per analysis; F0: 4 MB, first 2 pages. Image 50x50 to 10,000x10,000 px. Word/HTML billed in 3,000-character page blocks; Office string limit 8 million characters[61]Direct upload: 150 MB, URL input: 50 MB, URL timeout: 30 seconds, Processing: 5 minutes; HTTP 408 if exceeded, Page limit: not published, Test-key limits: lower, unpublished; Support-enabled[62]
ComplianceSOC 2 Type II (stated as controls aligned with SOC 2 Type II requirements; report via Trust Center), HIPAA with BAA (add-on on Scale, included on Enterprise, not on PAYG), GDPR (eu1 region, Frankfurt)[63]SOC 2 Type II (all tiers), HIPAA with signed BAA (Growth and Enterprise), Zero Data Retention (Growth and Enterprise)[64]SOC 2 Type II, GDPR, HIPAA (BAA for Enterprise)[47]Not published[65]SOC 2: Type 2, audited annually, BAA: no public statement, Transport: HTTPS/TLS only, No-retention plans: files discarded after processing, Retention plans: runs stored; may train/evaluate models, Payments: Paddle[66]
Public benchmarksRealDoc-Bench (1,500 layout samples; 1,359 Q&A prompts, 581 documents) Extend Parse 2.0: Q&A accuracy 95.7%, layout adjusted F1 0.847; Reducto layout F1 0.759, Reducto Agentic Q&A 91.1% (adjusted F1 / Q&A accuracy), vendor (Extend), 2026-05-26 (source)
LongArray-Extract (45 PDFs) 99.2% mean per-document accuracy; 45 of 45 completed (mean accuracy, failed runs scored zero), vendor (Extend), 2026-06-02 (source)
PoliTax Split (page shows '2026 (no day captured)'; date here is the fetch date) best harness F1 72.48% (Claude Opus 4.6); '+28.4 pts' largest F1 lift on homepage (split F1), vendor (Extend), 2026-10-15 (source)
Reducto-commissioned micro1 extraction benchmark, Extend MAX row 93.3% coverage, 86.4% precision, 92.7% recall, 92.8% leaf accuracy (see source), competitor-commissioned (Reducto), 2026-09-17 (source)[67]		Parse r-1 vs Reducto's previous agentic pipeline 20% reduction in error rate (error rate (preview)), vendor (Reducto), 2026-09-01 (source)
Extraction benchmark commissioned by Reducto, run by micro1 (225 documents) Reducto Deep Extract: 100% coverage, 99.6% precision, 99.6% recall, 99.3% leaf accuracy; Extend MAX: 93.3% coverage, 86.4% precision, 92.7% recall, 92.8% leaf accuracy (coverage / precision / recall / leaf accuracy), vendor-commissioned (Reducto; conducted by micro1), 2026-09-17 (source)
RD-TableBench (1,000 complex table images) Not published (hierarchical Needleman-Wunsch table similarity), vendor (Reducto), 2024-11-04 (source)
RealDoc-Bench, Reducto rows (run by Extend) layout adjusted F1 0.759; Document Q&A 91.1% (Reducto Agentic) (adjusted F1 / Q&A accuracy), competitor (Extend), 2026-05-26 (source)
Unstructured parsing benchmark, Reducto Agentic row (run by Unstructured) (page shows '2026 (no day shown)'; date here is the fetch date) adjusted CCT 0.812; table cell content accuracy 0.708; element alignment 0.595 (see source), competitor (Unstructured), 2026-10-15 (source)[68]		ParseBench public leaderboard (15 Oct 2026 snapshot) LlamaParse Agentic Plus 90.2 (#1), LlamaParse Agentic 87.0 (#2), LlamaParse Cost Effective 80.6 (#5) of 149 entries (overall 0 to 100), parsebench.ai (LlamaIndex), 2026-10-15 (source)
ParseBench (LlamaIndex, ~2,000 pages, 167K rules) LlamaParse Agentic 84.9% overall at ~1.2 cents/page; Cost Effective <0.4 cents/page; formatting 85.2% (Docling 1.0%) (overall of 5 dimensions), LlamaIndex (vendor-authored; self-benchmark), 2026-04-13 (source)
OmniParseBench LlamaParse headline 90.4 (text 88.2, tables 92.6, layout 90.4) (mean of text/tables/layout family pass rates), Datalab (competitor-authored), 2026-10-08 (source)
OmniExtractBench llamaextract agentic_plus accuracy 84.93, precision 86.57, recall 93.13, coverage 616/620 (accuracy), Datalab (competitor-authored), 2026-09-16 (source)[73]		[4]ParseBench public row 76.4; paired nightly: 82.8 (overall 0 to 100), LlamaIndex, 2026-10-15 (source)
ParseBench nightly 82.8; paired public row: 76.4 (overall 0 to 100), Nutrient, 2026-10-15 (source)
opendataloader-bench, Nutrient's own run understand 0.933; agentic 0.930; structure 0.892; text 0.889 (overall 0 to 1), Nutrient, 2026-10-16 (source)
opendataloader.org leaderboard Nutrient row (free CLI) 0.885; opendataloader hybrid 0.907 (overall 0 to 1), opendataloader.org, 2026-09-23 (source)[77]

How to read this list

Every vendor below is a direct substitute for Extend on at least one job: parsing to Markdown or JSON, schema extraction, classification, or splitting. Facts come from each vendor's own pricing and documentation pages on the fetched date, with sources listed below. Benchmark numbers are labeled with who ran them; none is independent of a vendor on this page.

Classification and splitting

Extend classifies with user-defined categories and confidence and splits multi-document files into typed sub-documents. Reducto has Classify, Split, and Deep Split. LlamaParse has Classify (1 or 2 credits per page) and Split in beta (4 credits per page). Azure's custom classifier needs at least five samples per class and does not split by default in API 2024-11-30 unless splitMode=auto. Nutrient classifies zero-shot from labels you send (1 credit per page) and splits merged PDFs with a boundary confidence per segment (3 credits per page).

Pricing at a glance

Extend: about 6.25 cents per Performance-mode extraction page on pay-as-you-go (our arithmetic), Scale $500 a month for 50,000 credits. Reducto: $20 per 1,000 pages Extract. LlamaParse: Extract 8, 25, or 60 credits per page including parsing, at $1.25 per 1,000 credits. Azure: Read $1.50, Layout and prebuilt $10, custom extraction $30 per 1,000 pages (East US). Nutrient: extract 7 to 24 credits per page, classify 1, split 3.

Deployment and compliance

Extend: SaaS in US and EU, BYOC, hybrid; controls aligned with SOC 2 Type II requirements; BAA as an add-on on Scale. Reducto: SaaS to air-gapped; SOC 2 Type II; BAA on Growth and Enterprise. LlamaParse: SaaS, Enterprise BYOC; SOC 2 Type II, GDPR, Enterprise BAA. Azure: Azure regions plus Docker containers for Read and Layout; certifications were not read from the pages fetched, so none is stated here. Nutrient: hosted, SOC 2 Type 2 audited; no BAA statement found on the public pages.

Published scores, with who ran them

Numbers here were run by the vendors named, several of them in the table above. Read them as directional and test on your own documents.

Nutrient's published benchmark results, as recorded on 16 October 2026: on LlamaIndex's ParseBench the public leaderboard row for Nutrient agentic is 76.4. Nutrient's own nightly run of 15 October 2026 scores 82.8 on the same test and is not on parsebench.ai yet; in that nightly run, understand mode scores 64.0. LlamaParse Agentic Plus leads the public leaderboard at 90.2. Nutrient is not on Datalab's OmniParseBench or OmniExtractBench public leaderboards. In Nutrient's own run on the opendataloader-bench corpus the API scores 0.933 in understand mode and 0.930 in agentic; on the public opendataloader.org leaderboard Nutrient's row (the free CLI) scores 0.885, behind opendataloader hybrid at 0.907.

Where Nutrient differs

The other products on this page are parsers or extraction APIs. Nutrient's Data Extraction API is the same kind of product, built by a company that has shipped document SDKs to enterprises since 2011. The facts below come from Nutrient's own public pages.

  • Founded as PSPDFKit in 2011, and the SDKs developers knew as PSPDFKit continue as Nutrient SDKs. Thousands of organizations in 80-plus countries, including Fortune 500s and governments, use them (about page).
  • 3,000-plus organizations and 15 percent of Global 500 companies rely on Nutrient, with over a billion document interactions a year (nutrient.io).
  • One engine, four deployments: hosted API in Nutrient's cloud; the Python and Java Data Extraction SDKs, self-hosted with no network required and no external API calls for OCR and ICR, with a local VLM through Ollama, LM Studio, or vLLM (Python SDK); Extract Studio on Apple silicon, where documents never leave the Mac when the model runs locally (Extract Studio); and the wider platform in the browser with WebAssembly, on your own servers with Document Engine, or air-gapped (nutrient.io).
  • Extraction is one credit pool with parse, classify, and split, and every extracted field carries a bounding box and a match label, so a reviewer can check the source instead of trusting the model. SOC 2 Type 2 audited.

What to test before switching

  • Run the same 20 documents through each API: five clean born-digital PDFs, five scans, five with tables that span pages, five with the fields your downstream system needs. Score reading order, table cells, and the fields you will actually consume.
  • Count the per-page cost at the mode or tier that passed your sample, not the cheapest tier on the pricing page. Every vendor here prices accuracy upward.
  • Check what the API returns when it is unsure: a confidence number, a bounding box, a not_found label, or nothing. That decides whether you can build a review queue.
  • Confirm retention and deployment in writing for the plan you will buy. Free and pay-as-you-go tiers often exclude BAAs, zero-retention, and private deployment.

Frequently asked questions

Which Extend alternative offers on-prem deployment?

Reducto lists on-prem and air-gapped on Enterprise. Azure ships Read and Layout as Docker containers. LlamaParse offers self-hosting on Enterprise. Nutrient runs the same engine three ways: the hosted API; self-hosted in the Python and Java Data Extraction SDKs, where OCR and ICR run on your infrastructure with no external API calls and the VLM stage can run locally through Ollama, LM Studio, or vLLM; and on a Mac in Extract Studio, where documents never leave the machine when the model runs locally.

Is Extend more accurate than the alternatives?

Extend's RealDoc-Bench, run by Extend, scores Extend Parse 2.0 at 95.7 percent Q&A accuracy and Reducto Agentic at 91.1 percent. Datalab's OmniParseBench, run by Datalab, scores Reducto 90.8, LlamaParse 90.4, Extend 83.3, and Azure 83.0. Nutrient is not on Datalab's public leaderboards.

What is the cheapest Extend alternative with a free tier that renews?

Nutrient's free plan renews 5,000 credits a month with no card. Azure's F0 tier allows 500 pages a month but analyzes only the first two pages per request. LlamaParse's Free plan lists 10,000 included credits on a $0-per-month plan, and its FAQ describes them as monthly for new users. Reducto's pricing page says standard rates apply after the first $150 of free usage.

Which alternatives have a hosted MCP server?

Reducto (mcp.reducto.ai), LlamaParse (mcp.llamaindex.ai), and Nutrient (mcp.nutrient.io). No official Document Intelligence MCP server was found for Azure.

Sources

  1. https://docs.extend.ai/security/deployment-options.md — fetched
  2. https://docs.reducto.ai/onprem/enterprise_deployment_options.md — fetched
  3. https://www.llamaindex.ai/pricing — fetched
  4. https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/overview — fetched
  5. https://www.nutrient.io/guides/dws-data-extraction/api-overview/ — fetched
  6. https://docs.extend.ai/parsing/configuration.md — fetched
  7. https://docs.reducto.ai/reference/faq.md — fetched
  8. https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/prebuilt/layout — fetched
  9. https://www.nutrient.io/guides/dws-data-extraction/parsing/ — fetched
  10. https://www.extend.ai/pricing — fetched
  11. https://reducto.ai/ — fetched
  12. https://developers.llamaindex.ai/llamaparse/parse/features/ocr-and-languages/index.md — fetched
  13. https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/prebuilt/read — fetched
  14. https://www.nutrient.io/guides/dws-data-extraction/parsing/processing-modes/ — fetched
  15. https://docs.reducto.ai/parse/overview.md — fetched
  16. https://developers.llamaindex.ai/llamaparse/parse/ — fetched
  17. https://www.nutrient.io/guides/dws-data-extraction/parsing/extract-document-elements/ — fetched
  18. https://docs.extend.ai/parsing/overview.md — fetched
  19. https://developers.llamaindex.ai/llamaparse/parse/features/layout-and-bounding-boxes/index.md — fetched
  20. https://docs.extend.ai/extraction/confidence-scores.md — fetched
  21. https://docs.reducto.ai/configs/extract/citations.md — fetched
  22. https://developers.llamaindex.ai/llamaparse/extract/guides/response-format/index.md — fetched
  23. https://www.nutrient.io/guides/dws-data-extraction/extract/citations-and-confidence/ — fetched
  24. https://docs.extend.ai/extraction/response-format.md — fetched
  25. https://docs.extend.ai/extraction/schema.md — fetched
  26. https://docs.reducto.ai/extract/overview.md — fetched
  27. https://developers.llamaindex.ai/llamaparse/extract/ — fetched
  28. https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/train/custom-model — fetched
  29. https://www.nutrient.io/guides/dws-data-extraction/extract/define-a-schema/ — fetched
  30. https://docs.extend.ai/classification/overview.md — fetched
  31. https://docs.reducto.ai/classify/overview.md — fetched
  32. https://developers.llamaindex.ai/llamaparse/classify/ — fetched
  33. https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/train/custom-classifier — fetched
  34. https://www.nutrient.io/guides/dws-data-extraction/classify/ — fetched
  35. https://docs.extend.ai/splitting/overview.md — fetched
  36. https://docs.reducto.ai/split.md — fetched
  37. https://developers.llamaindex.ai/llamaparse/split/ — fetched
  38. https://www.nutrient.io/api/data-extraction-api/split/ — fetched
  39. https://reducto.ai/pricing — fetched
  40. https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/ — fetched
  41. https://www.nutrient.io/api/pricing/data-extraction-api/ — fetched
  42. https://docs.extend.ai/general/how-credits-work.md — fetched
  43. https://docs.reducto.ai/reference/credit-usage.md — fetched
  44. https://developers.llamaindex.ai/llamaparse/general/pricing/ — fetched
  45. https://www.nutrient.io/guides/dws-data-extraction/pricing/ — fetched
  46. https://prices.azure.com/api/retail/prices?currencyCode=USD&$filter=contains(productName,'Document%20Intelligence')%20and%20armRegionName%20eq%20'eastus' — fetched
  47. https://developers.llamaindex.ai/llamaparse/general/enterprise-readiness/ — fetched
  48. https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/containers/install-run — fetched
  49. https://www.nutrient.io/sdk/python/pdf-data-extraction/ — fetched
  50. https://docs.extend.ai/sdks.md — fetched
  51. https://docs.reducto.ai/agent-guide.md — fetched
  52. https://developers.llamaindex.ai/llamaparse/parse/guides/tiers/index.md — fetched
  53. https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/sdk-overview-v4-0 — fetched
  54. https://www.nutrient.io/guides/dws-data-extraction/getting-started/ — fetched
  55. https://docs.extend.ai/mcp.md — fetched
  56. https://docs.reducto.ai/mcp-server.md — fetched
  57. https://developers.llamaindex.ai/for-agents/index.md — fetched
  58. https://www.nutrient.io/api/mcp-server-pdf-automation-llm/ — fetched
  59. https://docs.reducto.ai/upload/large-files.md — fetched
  60. https://developers.llamaindex.ai/llamaparse/general/limitations/ — fetched
  61. https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/service-limits — fetched
  62. https://www.nutrient.io/guides/dws-data-extraction/file-types/ — fetched
  63. https://docs.extend.ai/security/compliance.md — fetched
  64. https://docs.reducto.ai/enterprise/enterprise-readiness.md — fetched
  65. https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/document-intelligence/data-privacy-security — fetched
  66. https://www.nutrient.io/guides/dws-data-extraction/security/ — fetched
  67. https://www.extend.ai/benchmarks — fetched
  68. https://reducto.ai/compare/reducto-vs-extend — fetched
  69. https://reducto.ai/blog/parse-r-1-model — fetched
  70. https://reducto.ai/blog/rd-tablebench — fetched
  71. https://www.extend.ai/resources/realdocbench — fetched
  72. https://unstructured.io/benchmarks — fetched
  73. https://www.llamaindex.ai/blog/parsebench — fetched
  74. https://parsebench.ai/ — fetched
  75. https://www.datalab.to/blog/omni-parse-bench — fetched
  76. https://www.datalab.to/blog/omni-extract-bench — fetched
  77. https://www.nutrient.io/api/data-extraction-api/benchmarks/ — fetched
  78. https://opendataloader.org/docs/benchmark — fetched

Related