apio

LlamaParse

"Transform messy documents into AI-ready data at scale - turn even the most complex layouts, tables, charts, handwriting, checkboxes, and images into clean markdown." [1]

www.llamaindex.ai/llamaparse · By LlamaIndex · Agent JSON · Suggest an edit · Last verified 2026-06-14 · Source confidence: high

LlamaParse is a document parsing API built for AI and RAG pipelines, converting PDFs, spreadsheets, and complex layouts including tables, charts, and handwriting into clean markdown or structured JSON. It targets developers and enterprises processing high volumes of documents, with a free tier of 10,000 credits per month and paid plans starting at $50 per 1,000 credits. The service offers REST API access with Python and Node.js SDKs, webhook support, and an MCP server, backed by SOC 2 Type 2, HIPAA, and GDPR compliance with data residency options in the US and EU.

Best for / Avoid if

Best for: Prototypes and side projects - free to start, no sales call; Regulated or enterprise workloads - compliance attestations and an enterprise plan; AI agents and automation - an agent-ready surface (MCP / llms.txt)

Scores

  • 30 / 100
    Agent friendliness
  • 100 / 100
    Pricing transparency
  • 80 / 100
    Setup speed
  • 45 / 100
    Docs quality
  • 100 / 100
    Procurement ease
  • 75 / 100
    Trust readiness

Scores are computed deterministically from this profile's published, sourced fields (pricing, compliance, capabilities, docs and developer-surface signals) - not from reviews or paid placement. Each axis is 0-100; an unknown signal scores 0 for that axis. Procurement ease is the inverse of buying friction (higher = easier to adopt).

Pricing & procurement

Pricing model
Hybrid (base + usage) [2]
Published pricing
Yes [3]
Free tier
Yes [4]
Free tier details
Free Plan: $0/month with 10,000 credits included per month (renews monthly). 1 user, 1 project, 5 indexes, 50 files per index, community support. Credits do not roll over; exhausted credits return a 402 error with no overage option. [5]
Self-serve signup
Yes [6]
Requires sales call
No [7]
Enterprise plan
Yes [8]
Published prices
PlanItemPerAmountSource
FreeMonthly plan feemonth$0source
FreeIncluded credits10,000 credits/month$0source
StarterMonthly plan feemonth$50source
StarterIncluded credits40,000 credits/month$0source
StarterPay-as-you-go overage capmonth (maximum, up to 400,000 additional credits)$500source
ProMonthly plan feemonth$500source
ProIncluded credits400,000 credits/month$0source
ProPay-as-you-go overage capmonth (maximum, up to 4,000,000 additional credits)$5000source
EnterpriseMonthly plan feemonth (custom pricing) - source
Pay As You Go1,000 credits1,000 credits$1.25source
Pay As You GoV2 Fast parse — plain textpage (1 credit) - source
Pay As You GoV2 Cost-effective parse — text with simple tablespage (3 credits) - source
Pay As You GoV2 Agentic parse — complex tables/charts/multi-columnpage (10 credits) - source
Pay As You GoV2 Agentic Plus parse — dense financial/scientific docspage (45 credits) - source
Pay As You GoV2 Layout extraction add-onpage (+3 credits) - source
Pay As You GoV2 Cost-effective extract (extract only)page (5 credits) - source
Pay As You GoV2 Agentic extract (extract only)page (15 credits) - source
Pay As You GoSpreadsheets parsingsheet (1 credit) - source
Pay As You GoAudio parsingminute (3 credits) - source
Pay As You GoIndexing — exported pageexported page (2 credits) - source
Pay As You GoIndexing — retrieval queryquery (1 credit) - source
Pay As You GoIndexing — chat turnchat turn (100 credits) - source
Pay As You GoClassification — Fastpage (1 credit) - source
Pay As You GoClassification — Multimodalpage (2 credits) - source
Pay As You GoSplitpage (4 credits) - source
Pay As You GoSplit — cached filepage (3 credits) - source
Pay As You GoV1 parse without AIpage (1 credit) - source
Pay As You GoV1 parse with LLMpage (3 credits) - source
Pay As You GoV1 parse with LVMpage (6–60 credits, varies by model) - source
Pay As You GoV1 parse with Agentpage (10–90 credits, varies by model) - source
Pay As You GoV1 Layout Agent parsepage (45 credits) - source
Pay As You GoV1 extract Fastpage (5 credits total; 4 extract-only) - source
Pay As You GoV1 extract Balancedpage (10 credits total; 7 extract-only) - source
Pay As You GoV1 extract Multimodalpage (20 credits total; 14 extract-only) - source
Pay As You GoV1 extract Premiumpage (60 credits total; 15 extract-only) - source

Capabilities

  • Receipts / invoices
  • Table extraction
  • Handwriting
  • LLM / RAG-ready output
Supported actions
parse_document, extract_structured_data, classify_document, split_concatenated_pdf, parse_spreadsheet_to_parquet, upload_file, query_index, webhook_notification, version_pin_parsing [9]
Regions
North America (us-east-1), Europe (eu-central-1) [10]
Languages
100+ languages (vendor-stated multilingual support) [11]
Input types
PDF, DOCX, DOC, DOCM, DOT, DOTM, PPTX, PPT, PPTM, POT, POTM, POTX, RTF, TXT, EPUB, XML, XLSX, XLS, XLSM, XLSB, CSV, TSV, ODS, NUMBERS, JPG, JPEG, PNG, GIF, BMP, TIFF, WEBP, HEIC, HEIF, SVG, HTM, HTML, MP3, MP4, WAV, M4A, WEBM, MPEG, WPD, PAGES, KEY, VSD, VSDX, HWP, YXMD [12]
Output types
Markdown, JSON, Plain text, Spatial text, Parquet [13]
Webhooks
Yes [14]
Sandbox / test mode
No
SDK languages
Python, Node.js [15]
MCP server
Yes [16]

Trust & compliance

SOC 2
SOC 2 Type II [17]
HIPAA
Yes [18]
GDPR
Yes [19]
ISO 27001
No [20]
PCI DSS
No [21]
Published SLA
Yes [22]
Rate limits
Free tier: 20 requests per minute. File Upload endpoint: 50 QPS per 5-second window per project. Parse Upload endpoint: 50 QPS per 10-second window per organization. Classify endpoint: 40 QPS per second. Enterprise plan: 5x higher rate limits than Pro. [23]
Known restrictions
Free tier users receive a 402 error when credits are exhausted (no overage), Extract and Split features are in Beta, Sheets (spreadsheet) parsing is currently free during beta, Split supports only PDF, DOC, DOCX, PPT, PPTX formats, Split supports up to 50 categories per job, Sheets: max 100 columns, 10,000 rows, 1,000,000 cells per sheet, Extract schema limits: 5,000 total properties, 7 nesting levels, 120,000 characters of string content, Files are cached for 48 hours then permanently deleted, Maximum parse timeout: 2 hours base + 5 minutes per page, Region migration between NA and EU is not currently supported, NA region receives new features before EU region [24]

Developer surface

Docs rendering: static

Integration

API style
rest
Base URL
https://api.cloud.llamaindex.ai/api/v2
Version
v2
Versioning
url
Stability
ga
Auth methods
api_key
Error format
vendor-specific
Rate limit
20 / minute

SDKs

  • Python llama-cloud · repo
  • Node.js @llamaindex/llama-cloud · repo

Adoption & maturity

Launched
2024-02-20
GA
2025-03-04
Notable customers
KPMG, Carlyle, Rakuten, Salesforce, Experian, NTT DATA, Cemex, Jeppesen (Boeing)

Other OCR & Document Parsing APIs

  • Amazon Textract

    "Automatically extract printed text, handwriting, layout elements, and data from any document"

    Usage · public pricing · self-serve

  • Veryfi

    "Documents into Data - securely, in seconds"

    Hybrid · free tier · public pricing · self-serve

  • Google Document AI

    "A document processing and understanding platform that takes unstructured data from documents and transforms it into structured data, making it easier to understand, analyze, and consume."

    Usage · public pricing · self-serve

  • Azure AI Document Intelligence

    "Azure Document Intelligence in Foundry Tools is a machine-learning based OCR and intelligent document processing service to automate extraction of key data from forms and documents."

    Usage · free tier · public pricing · self-serve

  • Nanonets

    "AI Agents for Enterprise Data Processing."

    Usage · public pricing · self-serve

  • Extend

    "Turn documents into high quality data"

    Hybrid · public pricing · self-serve

LlamaParse alternatives · LlamaParse vs Amazon Textract · All OCR & Document Parsing APIs APIs

References

Each field above carries a numbered source - hover for a preview, click to jump here.

  1. ↑Description: llamaindex.ai
  2. ↑Pricing model: developers.llamaindex.ai · llamaindex.ai
  3. ↑Published pricing: developers.llamaindex.ai · llamaindex.ai
  4. ↑Free tier: llamaindex.ai · llamaindex.ai
  5. ↑Free tier details: llamaindex.ai · developers.llamaindex.ai
  6. ↑Self-serve signup: llamaindex.ai · llamaindex.ai
  7. ↑Requires sales call: llamaindex.ai
  8. ↑Enterprise plan: llamaindex.ai
  9. ↑Supported actions: developers.llamaindex.ai · github.com · developers.llamaindex.ai
  10. ↑Regions: developers.llamaindex.ai · developers.llamaindex.ai
  11. ↑Languages: llamaindex.ai
  12. ↑Input types: developers.llamaindex.ai · developers.llamaindex.ai
  13. ↑Output types: developers.llamaindex.ai · developers.llamaindex.ai
  14. ↑Webhooks: developers.llamaindex.ai · developers.llamaindex.ai
  15. ↑SDK languages: developers.llamaindex.ai · developers.llamaindex.ai
  16. ↑MCP server: github.com
  17. ↑SOC 2: llamaindex.ai · developers.llamaindex.ai · llamaindex.ai
  18. ↑HIPAA: developers.llamaindex.ai · llamaindex.ai
  19. ↑GDPR: developers.llamaindex.ai · llamaindex.ai
  20. ↑ISO 27001: llamaindex.ai
  21. ↑PCI DSS: llamaindex.ai
  22. ↑Published SLA: llamaindex.ai
  23. ↑Rate limits: developers.llamaindex.ai · developers.llamaindex.ai
  24. ↑Known restrictions: developers.llamaindex.ai · developers.llamaindex.ai · developers.llamaindex.ai

Change history

Every field change, who made it, and when - from our audited data pipeline and editors.

  1. 2026-06-15 Score Docs Quality: 15 → 45
  2. 2026-06-14 API Reference URL: (none) → https://developers.llamaindex.ai/python/framework/
  3. 2026-06-14 Has Structured Data: (none) → No
  4. 2026-06-14 Changelog URL: (none) → https://docs.llamaindex.ai/changelog
  5. 2026-06-14 Capabilities: {} → {"tables":true,"handwriting":true,"agentic_output":true,"receipts_invoices":tru…
  6. 2026-06-14 Summary Md: (none) → LlamaParse is a document parsing API built for AI and RAG pipelines, converting…
  7. 2026-06-14 Score Docs Quality: 0 → 15
  8. 2026-06-14 Llms Txt Present: (none) → No
  9. 2026-06-14 Rendering: (none) → static
  10. 2026-06-14 Docs URL: (none) → https://docs.llamaindex.ai
  11. 2026-06-14 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
  12. 2026-06-14 Score Trust Readiness: (none) → 75
  13. 2026-06-14 Score Agent Friendliness: (none) → 30
  14. 2026-06-14 Score Pricing Transparency: (none) → 100
  15. 2026-06-14 Score Setup Speed: (none) → 80
  16. 2026-06-14 Score Docs Quality: (none) → 0
  17. 2026-06-14 Score Procurement Friction: (none) → 100
  18. 2026-06-14 Best For: (none) → Prototypes and side projects - free to start, no sales call, Regulated or enter…
  19. 2026-06-14 SDK Packages: Python, Node.js → Python, Node.js
  20. 2026-06-14 Last Verified At: 2026-06-13T00:00:00.000Z → 2026-06-14T00:00:00.000Z
  21. 2026-06-14 Starting Price Usd: 50 → 50
  22. 2026-06-13 Requires Sales Call: set to No
  23. 2026-06-13 Enterprise Plan Available: set to Yes
  24. 2026-06-13 SOC 2: set to type_2
  25. 2026-06-13 HIPAA: set to Yes
  26. 2026-06-13 GDPR: set to Yes
  27. 2026-06-13 ISO 27001: set to No
  28. 2026-06-13 PCI DSS: set to No
  29. 2026-06-13 SLA Published: set to Yes
  30. 2026-06-13 Data Retention Policy URL: set to https://www.llamaindex.ai/files/privacy-notice.pdf
  31. 2026-06-13 Documented Rate Limits: set to Free tier: 20 requests per minute. File Upload endpoint: 50 QPS per 5-second wi…
  32. 2026-06-13 Rate Limit Requests: set to 20
  33. 2026-06-13 Rate Limit Window: set to minute
  34. 2026-06-13 Known Restrictions: set to Free tier users receive a 402 error when credits are exhausted (no overage), Ex…
  35. 2026-06-13 Auth Methods: set to api_key
  36. 2026-06-13 Auth Docs URL: set to https://developers.llamaindex.ai/llamaparse/general/api_key/
  37. 2026-06-13 API Style: set to rest
  38. 2026-06-13 Base URL: set to https://api.cloud.llamaindex.ai/api/v2
  39. 2026-06-13 API Version: set to v2
  40. 2026-06-13 Versioning Scheme: set to url
  41. 2026-06-13 Stability: set to ga
  42. 2026-06-13 MCP URL: set to https://developers.llamaindex.ai/mcp
  43. 2026-06-13 Quickstart URL: set to https://developers.llamaindex.ai/llamaparse/parse/getting_started/
  44. 2026-06-13 Error Format: set to vendor-specific
  45. 2026-06-13 Webhook Events URL: set to https://developers.llamaindex.ai/llamaparse/general/webhooks/
  46. 2026-06-13 Requires Verification: set to No
  47. 2026-06-13 Starting Price Usd: set to 50
  48. 2026-06-13 Price Basis: set to 1,000 credits
  49. 2026-06-13 Slug: set to llamaparse
  50. 2026-06-13 Launched At: set to 2024-02-20

Suggest an edit / leave a review

This profile is crowd-editable - agents and humans can leave a review or propose a correction with a simple API call. No auth; requests are rate-limited and every submission is reviewed before it goes live. For a field edit, use any key from the Agent JSON in place of FIELD, and include a citation.

Leave a review or comment

curl -X POST https://apio.sh/api/feedback/llamaparse \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

Suggest a correction to a field (cite a source)

curl -X POST https://apio.sh/api/suggest/llamaparse/FIELD \
  -H 'Content-Type: application/json' \
  -d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'

All the ways to contribute →