LlamaParse website screenshot

LlamaParse

LlamaParse is an enterprise document parsing and AI pipeline platform from LlamaIndex that converts complex PDFs, Office files, and 130+ document formats into LLM-ready structured outputs. The platform offers six composable products under a single API key: Parse (agentic OCR), Extract (structured data extraction), Classify, Split, Sheets, and Index. Parse supports tier-based processing from fast and cost-effective modes to advanced agentic and agentic-plus tiers that preserve tables, figures, and layout for high-fidelity RAG and document AI workflows. Developers access the platform through Python and TypeScript SDKs or directly via the LlamaCloud REST API, with EU-region hosting available.

4 APIs 0 Features
Document ParsingOCRPDFLLMRAGAIDocument IntelligenceStructured Data Extraction

APIs

LlamaParse Parse API

The core document parsing API that converts PDFs and 130+ file formats into structured markdown, text, and layout-aware output for LLM and RAG pipelines. Supports tier selection...

LlamaParse Extract API

Structured data extraction API that pulls typed JSON output from unstructured documents using developer-defined schemas. Supports cost-effective and agentic tiers; composable wi...

LlamaParse Classify API

Document classification API that categorizes uploaded files by type or content. Available in fast (1 credit/page) and multimodal (2 credits/page) modes; useful for pre-filtering...

LlamaCloud Index API

Managed vector index API for ingesting parsed documents into searchable LlamaCloud indexes. Supports standard (1 credit/page), spreadsheet (2 credits/page), and multi-modal (2 c...

Pricing Plans

Llamaparse Plans Pricing

4 plans

PLANS

Rate Limits

Llamaparse Rate Limits

4 limits

RATE LIMITS

FinOps

Semantic Vocabularies

Llamaparse Context

47 classes · 21 properties

JSON-LD

Example Payloads

Resources

🔗
Website
Website
🔗
Documentation
Documentation
🔗
APIReference
APIReference
👥
GitHubOrganization
GitHubOrganization
👥
GitHubRepository
GitHubRepository
👥
GitHubRepository
GitHubRepository
🔗
LinkedIn
LinkedIn
🔗
X
X
📰
Blog
Blog
📄
ChangeLog
ChangeLog
💰
Pricing
Pricing
🟢
StatusPage
StatusPage
📦
PythonSDK
PythonSDK
📦
TypeScriptSDK
TypeScriptSDK
🔗
Plans
Plans
🔗
RateLimits
RateLimits
🔗
FinOps
FinOps
🔗
OpenAPI
OpenAPI
🔗
Vocabulary
Vocabulary
🔗
JSONLDContext
JSONLDContext

Sources

Raw ↑
aid: llamaparse
name: LlamaParse
description: 'LlamaParse is an enterprise document parsing and AI pipeline platform from LlamaIndex that converts complex
  PDFs, Office files, and 130+ document formats into LLM-ready structured outputs. The platform offers six composable products
  under a single API key: Parse (agentic OCR), Extract (structured data extraction), Classify, Split, Sheets, and Index. Parse
  supports tier-based processing from fast and cost-effective modes to advanced agentic and agentic-plus tiers that preserve
  tables, figures, and layout for high-fidelity RAG and document AI workflows. Developers access the platform through Python
  and TypeScript SDKs or directly via the LlamaCloud REST API, with EU-region hosting available.

  '
type: Index
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
tags:
- Document Parsing
- OCR
- PDF
- LLM
- RAG
- AI
- Document Intelligence
- Structured Data Extraction
url: https://raw.githubusercontent.com/api-evangelist/llamaparse/refs/heads/main/apis.yml
created: '2026-06-12'
modified: '2026-06-12'
specificationVersion: '0.19'
apis:
- aid: llamaparse-parse-api
  name: LlamaParse Parse API
  description: 'The core document parsing API that converts PDFs and 130+ file formats into structured markdown, text, and
    layout-aware output for LLM and RAG pipelines. Supports tier selection (fast, cost-effective, agentic, agentic-plus) with
    versioned, reproducible parsing behavior via the v2 endpoint.

    '
  humanURL: https://developers.llamaindex.ai/llamaparse/parse/
  baseURL: https://api.cloud.llamaindex.ai
  tags:
  - Document Parsing
  - OCR
  - PDF
  - Markdown
  properties:
  - type: Documentation
    url: https://developers.llamaindex.ai/llamaparse/parse/
  - type: APIReference
    url: https://developers.llamaindex.ai/llamaparse/parse/guides/api-reference/
  - type: GettingStarted
    url: https://developers.llamaindex.ai/llamaparse/parse/getting_started/
  - type: Tiers
    url: https://developers.llamaindex.ai/llamaparse/parse/guides/tiers/
  - type: OpenAPI
    url: openapi/llamaparse-llamacloud-openapi.yml
- aid: llamaparse-extract-api
  name: LlamaParse Extract API
  description: 'Structured data extraction API that pulls typed JSON output from unstructured documents using developer-defined
    schemas. Supports cost-effective and agentic tiers; composable with Parse to reduce per-page costs when re-extracting
    previously parsed documents.

    '
  humanURL: https://developers.llamaindex.ai/llamaparse/
  baseURL: https://api.cloud.llamaindex.ai
  tags:
  - Data Extraction
  - Structured Data
  - JSON
  - Documents
  properties:
  - type: Documentation
    url: https://developers.llamaindex.ai/llamaparse/
- aid: llamaparse-classify-api
  name: LlamaParse Classify API
  description: 'Document classification API that categorizes uploaded files by type or content. Available in fast (1 credit/page)
    and multimodal (2 credits/page) modes; useful for pre-filtering before invoking higher-cost parse or extract operations.

    '
  humanURL: https://developers.llamaindex.ai/llamaparse/
  baseURL: https://api.cloud.llamaindex.ai
  tags:
  - Classification
  - Documents
  - AI
  properties:
  - type: Documentation
    url: https://developers.llamaindex.ai/llamaparse/
- aid: llamaparse-index-api
  name: LlamaCloud Index API
  description: 'Managed vector index API for ingesting parsed documents into searchable LlamaCloud indexes. Supports standard
    (1 credit/page), spreadsheet (2 credits/page), and multi-modal (2 credits/page) indexing modes with real-time status monitoring.

    '
  humanURL: https://developers.llamaindex.ai/llamaparse/
  baseURL: https://api.cloud.llamaindex.ai
  tags:
  - Vector Index
  - RAG
  - Search
  properties:
  - type: Documentation
    url: https://developers.llamaindex.ai/llamaparse/
  - type: StatusMonitoring
    url: https://developers.llamaindex.ai/llamaparse/cloud-index/guides/index_status_monitoring/
common:
- type: Website
  url: https://www.llamaindex.ai/
- type: Documentation
  url: https://developers.llamaindex.ai/llamaparse/
- type: APIReference
  url: https://developers.llamaindex.ai/llamaparse/parse/guides/api-reference/
- type: GitHubOrganization
  url: https://github.com/run-llama
- type: GitHubRepository
  url: https://github.com/run-llama/llama-parse-py
- type: GitHubRepository
  url: https://github.com/run-llama/llama-cloud-ts
- type: LinkedIn
  url: https://www.linkedin.com/company/llamaindex
- type: X
  url: https://twitter.com/llama_index
- type: Blog
  url: https://www.llamaindex.ai/blog
- type: ChangeLog
  url: https://developers.llamaindex.ai/python/framework/changelog/
- type: Pricing
  url: https://www.llamaindex.ai/pricing
- type: StatusPage
  url: https://llamaindex.statuspage.io/
- type: PythonSDK
  url: https://pypi.org/project/llama-cloud/
- type: TypeScriptSDK
  url: https://www.npmjs.com/package/@llamaindex/llama-cloud
- type: Plans
  url: plans/llamaparse-plans-pricing.yml
- type: RateLimits
  url: rate-limits/llamaparse-rate-limits.yml
- type: FinOps
  url: finops/llamaparse-finops.yml
- type: OpenAPI
  url: openapi/llamaparse-llamacloud-openapi.yml
- type: Vocabulary
  url: vocabulary/llamaparse-vocabulary.yml
- type: JSONLDContext
  url: json-ld/llamaparse-context.jsonld
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com