Nutrient document API comparisons
Published by NutrientUpdated

Reducto alternatives

Verdict

Reducto lists Parse r-1 at $10 and Extract at $20 per 1,000 pages, offers deployment up to air-gapped, and scores 90.8 on Datalab's OmniParseBench and 93.47 on OmniExtractBench. People look for alternatives when they want a renewing free tier, a different price shape, an open source path, or a platform with workflows around the API.

Choose LlamaParse for 130-plus input formats and a Fast tier at about $1.25 per 1,000 pages. Choose Extend for a workflow platform with human review and evaluation sets. Choose Unstructured for ingestion pipelines with connectors and a flat $0.015 per page. Choose Docling for free, local, MIT-licensed parsing. Choose Nutrient Data Extraction for one credit pool across parse, extract, classify, and split, grounded extraction with match labels, and 5,000 credits that renew every month with no card. 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

Reducto, LlamaParse (LlamaCloud), Extend, Unstructured, Docling (IBM Research / LF AI & Data), Nutrient Data Extraction API; facts fetched 2026-10-15 to 2026-10-16
FactReductoLlamaParse (LlamaCloud)ExtendUnstructuredDocling (IBM Research / LF AI & Data)Nutrient Data Extraction API
Product typehosted API[1]hosted API[2]hosted API[3]both[4]open source library[5]Hosted Data Extraction API, web Studio, and macOS Extract Studio[6]
Output formatsMarkdown, JSON, HTML tables[7]Markdown, Plain text, JSON (per-page items), XLSX, HTML tables, Annotated PDF, Structured JSON to custom schema[2]Markdown, JSON, HTML tables[8]Markdown, JSON elements, HTML tables, chunks, embeddings[9]Markdown, HTML, JSON (lossless DoclingDocument), DocTags, DocLang XML, plain text, WebVTT, chunks JSONL, LaTeX[10]Spatial JSON, Markdown, Schema-shaped JSON with citations, Ranked labels with independent 0-1 scores, Split page ranges and ZIP files[11]
OCR for scansYes[12]Yes[13]Yes[14]Yes[15]Yes[5]Yes: structure, understand, and agentic; text has no OCR; 100+ languages[16]
HandwritingYes[17]Yes[18]Yes[14]Yes[15]Not published[5]Yes: printed-style in understand; cursive/freeform needs agentic[19]
TablesYes[17]Yes[2]Yes[14]Yes[20]Yes[21]Yes: spans and bounds; complex tables may need agentic mode[19]
Layout and bounding boxesYes[17]Yes[22]Yes[23]Yes[9]Yes[24]Yes: element and optional word bounds; word bounds exclude XLSX[19]
Per-field confidenceYes[25]Yes[26]Yes[27]Not published[28]No[29]Yes: 0-1 relative signal, not a probability[30]
Source citations and groundingYes[25]Yes[26]Yes[31]Not published[28]Yes[24]Yes: field boxes, match labels, confidence, and source boxes[30]
Schema extractionYes[32]Yes[33]Yes[34]Yes[35]Not published[5]Yes: closed JSON Schema subset; 128 KB, 2,000 nodes, depth 5[36]
ClassificationYes[37]Yes[38]Yes[39]Not published[28]Not published[5]Yes: zero-shot, 2+ labels; independent 0-1 scores; 1 credit/page[40]
Document splittingYes[41]Yes[42]Yes[43]Not published[28]Not published[5]Yes: boundary detection for PDF/images; 3 credits/page[44]
Free tier$150 in free usage (Standard plan)[45]Includes 10K credits (Free plan, $0/month)[2]10,000 free credits, then pay-as-you-go (no contract, monthly minimum or sales call)[14]10,000 free pages (once per account, no card required)[20]Free and open source (MIT)[5]5,000 credits/month; no card; all parse modes, including Auto[46]
Pricing modelUSD per 1,000 pages, per endpoint; Growth/Enterprise custom with volume discounts[47]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.[48]Credits per page by operation and mode (Performance vs Light); plan sets the per-credit rate[49]Per page: $0.015 per page after the first 10,000; Business plan custom[20]free OSS; you pay only for your own compute[5]Credits/page by endpoint and mode; Auto routes each page and bills that mode's rate; subscription plus capped overage[50]
List price examplesStandard (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))[45]		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)[2]		Pay 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)[49]		Free: $0 (10,000 free pages, no card required, all features)
Pay-As-You-Go: $0.015 per page (after first 10,000 pages; all features; SaaS)
Business: Custom (contact sales) (multi-user, dedicated instance / VPC / multi-tenant SaaS, bare metal, compliance)
Open source library: Free (Apache-2.0) (self-hosted, no SLA; reduced table/doc accuracy vs hosted per Unstructured's own docs)[20]		[5]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)[46]
DeploymentSaaS, VPC, on-prem, air-gapped[1]SaaS (US and EU regions), VPC / hybrid cloud, single-tenant SaaS, BYOC (Azure, AWS, GCP), self-hosting[51]SaaS, VPC[3]SaaS, VPC, on-prem, open source[20]open source, local, on-prem / air-gapped, self-hosted API server (docling-serve), MCP server[5]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[52]
SDKsPython, Node.js, Go, REST API, CLI[53]Python (llama-cloud, PyPI 2.18.0 at fetch), TypeScript (@llamaindex/llama-cloud), Go, Java, CLI, REST API, n8n node[54]Python, TypeScript, Java, Go, CLI[55]Python, TypeScript, Python (open source library)[56]Python (pip install docling; PyPI 2.139.0 at fetch, Python >=3.10), CLI, REST via docling-serve[57]REST API, Python SDK, Java SDK, .NET page referenced, curl, JavaScript, and raw HTTP samples[58]
MCP or agent toolsMCP server (local: uvx mcp-server-reducto; hosted: https://mcp.reducto.ai/mcp), CLI, llms.txt and agent guide[59]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[60]Hosted MCP server (https://mcp.extend.ai/mcp, OAuth), extend CLI with 'extend-cli' skill, agents.md[61]Transform MCP server (https://mcp.transform.unstructured.io), UNS-MCP server, agent skills, llms.txt and agent guide[62]docling-mcp server (uvx docling-mcp-server); agent skills page in docs[63]Hosted MCP, Data Extraction Studio, and agent skills[64]
Maximum file size or pages100 MB direct upload; up to 5 GB via presigned URL; no page limits on Standard plan[65]{"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)"}[66]Not published[14]50 MB per document on Transform Upload/Parse/Extract; no page limit stated[67]Not published[68]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[69]
ComplianceSOC 2 Type II (all tiers), HIPAA with signed BAA (Growth and Enterprise), Zero Data Retention (Growth and Enterprise)[70]SOC 2 Type II, GDPR, HIPAA (BAA for Enterprise)[51]SOC 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)[71]SOC 2 Type 2, HIPAA, GDPR, ISO 27001[20]Not published[5]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[72]
Public benchmarksParse 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)[73]		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)[78]		RealDoc-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)[82]		Unstructured document parsing benchmark (1,000+ enterprise pages; vs Reducto, LlamaParse, Docling, Snowflake, Databricks, NVIDIA) (page shows '2026 (no day shown)'; date here is the fetch date) Unstructured: Adjusted CCT 0.880 (#1), tokens added 0.051, element alignment 0.574 (#4), table cell content accuracy 0.820, table cell spatial accuracy 0.813; Reducto Agentic: 0.812 / 0.124 / 0.595 / 0.708 / 0.706 (Adjusted CCT, tokens added, element alignment, table cell content/spatial accuracy), vendor (Unstructured), 2026-10-15 (source)
RD-TableBench, Unstructured included (High Res mode) Not published (table similarity), competitor (Reducto), 2024-11-04 (source)[77]		Granite-Docling-258M model card, FinTabNet 150dpi TEDS structure 0.97, TEDS with content 0.96 (smoldocling-256m-preview 0.82 / 0.76) (TEDS), IBM (model card; this is the Granite-Docling VLM, not the default Docling PDF pipeline), 2025-09-17 (source)
Granite-Docling layout (same card) mAP 0.27, F1 0.86, precision 0.92, recall 0.88 (layout), IBM, 2025-09-17 (source)
Granite-Docling full-page OCR (same card) edit distance 0.45 (lower better), F1 0.84 (OCR), IBM, 2025-09-17 (source)
olmOCR-bench (Datalab run) docling (GPU) 50.3 overall, 64.0 digital-only, 2.1 pg/s (olmocr-bench macro average), Datalab (competitor-authored), 2026-07-20 (source)
ParseBench Docling semantic formatting 1.0% (formatting dimension), LlamaIndex (competitor-authored), 2026-04-13 (source)[83]		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)[85]

How to read this list

Every vendor below is a direct substitute for Reducto 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.

Pricing at a glance

Reducto: $10 per 1,000 pages Parse r-1, $20 Extract, $150 free usage (the same page also says 15,000 credits). LlamaParse: $1.25 per 1,000 credits, 1 to 45 credits per page, 10,000 free credits. Extend: $0.0125 per credit pay-as-you-go, about 5 credits for a Performance-mode extraction page, 10,000 free credits. Unstructured: $0.015 per page after 10,000 free pages. Docling: free, your compute. Nutrient: 1 to 18 credits per parse page, 7 to 24 per extract page, 5,000 free credits a month.

Grounding and confidence

Reducto, Extend, LlamaParse, and Nutrient return per-field confidence and citations with bounding boxes; Nutrient adds a match label (id_match, fuzzy_match, not_found) per field. No per-field confidence was found in Unstructured's Transform Extract docs. Docling returns document-level conversion grades and item provenance, not field confidence.

Deployment

Reducto: SaaS to air-gapped. Extend: SaaS, BYOC, hybrid; no on-prem listed. LlamaParse: SaaS, BYOC and self-hosting on Enterprise. Unstructured: SaaS, in-VPC, bare metal, open source. Docling: local or self-hosted. Nutrient: 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.

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

What is the best free alternative to Reducto?

Docling is free and open source under MIT and runs locally. For a hosted free tier that renews, Nutrient's 5,000 credits a month and LlamaParse's 10,000 credits are the two in this list; Unstructured's and Extend's free pages or credits are one-time.

Which Reducto alternative supports on-prem deployment?

Docling runs locally, including air-gapped, per its README. Unstructured offers bare metal and in-VPC on Business. LlamaParse offers self-hosting on Enterprise. Extend's docs list BYOC and hybrid, and no on-prem option. 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.

Which alternative is most accurate?

On Datalab's OmniParseBench (Datalab-run) Reducto scores 90.8 and LlamaParse 90.4, with Extend at 83.3. LlamaIndex's ParseBench ranks LlamaParse first. Extend's RealDoc-Bench ranks Extend first. Each vendor leads its own benchmark; Nutrient is not yet on Datalab's public leaderboards; it publishes its ParseBench results (76.4 public, 82.8 nightly) and its opendataloader-bench run (0.933).

Why switch from Reducto at all?

The reasons people cite are price shape (per-page USD versus credits with a renewing free tier), a need for a platform with review workflows, or a preference for open source. Reducto's own strengths are its deployment range and its leaderboard positions.

Sources

  1. https://docs.reducto.ai/onprem/enterprise_deployment_options.md — fetched
  2. https://www.llamaindex.ai/pricing — fetched
  3. https://docs.extend.ai/security/deployment-options.md — fetched
  4. https://docs.unstructured.io/open-source/introduction/overview.md — fetched
  5. https://raw.githubusercontent.com/docling-project/docling/main/README.md — fetched
  6. https://www.nutrient.io/guides/dws-data-extraction/api-overview/ — fetched
  7. https://docs.reducto.ai/reference/faq.md — fetched
  8. https://docs.extend.ai/parsing/configuration.md — fetched
  9. https://docs.unstructured.io/transform/parse.md — fetched
  10. https://docling-project.github.io/docling/usage/supported_formats/ — fetched
  11. https://www.nutrient.io/guides/dws-data-extraction/parsing/ — fetched
  12. https://reducto.ai/ — fetched
  13. https://developers.llamaindex.ai/llamaparse/parse/features/ocr-and-languages/index.md — fetched
  14. https://www.extend.ai/pricing — fetched
  15. https://unstructured.io/ — fetched
  16. https://www.nutrient.io/guides/dws-data-extraction/parsing/processing-modes/ — fetched
  17. https://docs.reducto.ai/parse/overview.md — fetched
  18. https://developers.llamaindex.ai/llamaparse/parse/ — fetched
  19. https://www.nutrient.io/guides/dws-data-extraction/parsing/extract-document-elements/ — fetched
  20. https://unstructured.io/pricing — fetched
  21. https://arxiv.org/abs/2408.09869 — fetched
  22. https://developers.llamaindex.ai/llamaparse/parse/features/layout-and-bounding-boxes/index.md — fetched
  23. https://docs.extend.ai/parsing/overview.md — fetched
  24. https://docling-project.github.io/docling/concepts/docling_document/ — fetched
  25. https://docs.reducto.ai/configs/extract/citations.md — fetched
  26. https://developers.llamaindex.ai/llamaparse/extract/guides/response-format/index.md — fetched
  27. https://docs.extend.ai/extraction/confidence-scores.md — fetched
  28. https://docs.unstructured.io/ — fetched
  29. https://docling-project.github.io/docling/concepts/confidence_scores/ — fetched
  30. https://www.nutrient.io/guides/dws-data-extraction/extract/citations-and-confidence/ — fetched
  31. https://docs.extend.ai/extraction/response-format.md — fetched
  32. https://docs.reducto.ai/extract/overview.md — fetched
  33. https://developers.llamaindex.ai/llamaparse/extract/ — fetched
  34. https://docs.extend.ai/extraction/schema.md — fetched
  35. https://docs.unstructured.io/transform/extract.md — fetched
  36. https://www.nutrient.io/guides/dws-data-extraction/extract/define-a-schema/ — fetched
  37. https://docs.reducto.ai/classify/overview.md — fetched
  38. https://developers.llamaindex.ai/llamaparse/classify/ — fetched
  39. https://docs.extend.ai/classification/overview.md — fetched
  40. https://www.nutrient.io/guides/dws-data-extraction/classify/ — fetched
  41. https://docs.reducto.ai/split.md — fetched
  42. https://developers.llamaindex.ai/llamaparse/split/ — fetched
  43. https://docs.extend.ai/splitting/overview.md — fetched
  44. https://www.nutrient.io/api/data-extraction-api/split/ — fetched
  45. https://reducto.ai/pricing — fetched
  46. https://www.nutrient.io/api/pricing/data-extraction-api/ — fetched
  47. https://docs.reducto.ai/reference/credit-usage.md — fetched
  48. https://developers.llamaindex.ai/llamaparse/general/pricing/ — fetched
  49. https://docs.extend.ai/general/how-credits-work.md — fetched
  50. https://www.nutrient.io/guides/dws-data-extraction/pricing/ — fetched
  51. https://developers.llamaindex.ai/llamaparse/general/enterprise-readiness/ — fetched
  52. https://www.nutrient.io/sdk/python/pdf-data-extraction/ — fetched
  53. https://docs.reducto.ai/agent-guide.md — fetched
  54. https://developers.llamaindex.ai/llamaparse/parse/guides/tiers/index.md — fetched
  55. https://docs.extend.ai/sdks.md — fetched
  56. https://docs.unstructured.io/llms.txt — fetched
  57. https://pypi.org/pypi/docling/json — fetched
  58. https://www.nutrient.io/guides/dws-data-extraction/getting-started/ — fetched
  59. https://docs.reducto.ai/mcp-server.md — fetched
  60. https://developers.llamaindex.ai/for-agents/index.md — fetched
  61. https://docs.extend.ai/mcp.md — fetched
  62. https://docs.unstructured.io/transform/get-started/overview.md — fetched
  63. https://docling-project.github.io/docling/usage/mcp/ — fetched
  64. https://www.nutrient.io/api/mcp-server-pdf-automation-llm/ — fetched
  65. https://docs.reducto.ai/upload/large-files.md — fetched
  66. https://developers.llamaindex.ai/llamaparse/general/limitations/ — fetched
  67. https://docs.unstructured.io/transform/limits.md — fetched
  68. https://docling-project.github.io/docling/usage/ — fetched
  69. https://www.nutrient.io/guides/dws-data-extraction/file-types/ — fetched
  70. https://docs.reducto.ai/enterprise/enterprise-readiness.md — fetched
  71. https://docs.extend.ai/security/compliance.md — fetched
  72. https://www.nutrient.io/guides/dws-data-extraction/security/ — fetched
  73. https://reducto.ai/compare/reducto-vs-extend — fetched
  74. https://reducto.ai/blog/parse-r-1-model — fetched
  75. https://reducto.ai/blog/rd-tablebench — fetched
  76. https://www.extend.ai/resources/realdocbench — fetched
  77. https://unstructured.io/benchmarks — fetched
  78. https://www.llamaindex.ai/blog/parsebench — fetched
  79. https://parsebench.ai/ — fetched
  80. https://www.datalab.to/blog/omni-parse-bench — fetched
  81. https://www.datalab.to/blog/omni-extract-bench — fetched
  82. https://www.extend.ai/benchmarks — fetched
  83. https://huggingface.co/ibm-granite/granite-docling-258M — fetched
  84. https://github.com/datalab-to/marker — fetched
  85. https://www.nutrient.io/api/data-extraction-api/benchmarks/ — fetched
  86. https://opendataloader.org/docs/benchmark — fetched

Related