Parse Any File
to Any Format
▌
The fastest, most accurate document parser for developers. Parse, chunk, or summarize any document for AI, LLMs, and vector databases.
✓ 100 free credits included • No credit card required
var(--color-success)">"color: var(--color-secondary)var(--color-success)">">var(--color-secondary)">import { PeterParser } var(--color-success)">"color: var(--color-secondary)var(--color-success)">">var(--color-secondary)">from &var(--color-text-tertiary)">#039;@peterparser/sdk';var(--color-success)">"color: var(--color-secondary)var(--color-success)">">var(--color-secondary)">const parser = var(--color-success)">"color: var(--color-secondary)">new PeterParser(&var(--color-text-tertiary)">#039;YOUR_API_KEY');var(--color-success)">"color: var(--color-secondary)var(--color-success)">">var(--color-secondary)">const result = var(--color-success)">"color: var(--color-secondary)">await parser.parse(&var(--color-text-tertiary)">#039;./invoice.pdf');console.log(result.json);Why PeterParser?
Built for developers who need reliable, fast, and accurate document parsing at scale.
Most Versatile
Parse virtually any file format to any output. PDF, images, Office docs, scans—convert to JSON, XML, Markdown, or your custom schema.
┌─────────┐ ┌─────────┐ │ .pdf │ ──▶ │ .json │ │ .docx │ ──▶ │ .xml │ │ .png │ ──▶ │ .md │ └─────────┘ └─────────┘
Fastest Parser
State-of-the-art cloud infrastructure in US and Germany. Auto-scaling, enterprise-grade performance with <500ms average response.
╔═══════════════════════════╗ ║ Response: 247ms ✓ ║ ║ ████████████████░░ 94% ║ ╚═══════════════════════════╝
Up to 99%+ Accuracy
AI Vision OCR excels on challenging documents. Modern AI understands context, layout, and handles scans, handwriting, and complex tables.
┌──────────────────────────┐ │ Clean docs: █████ 99%+ │ │ Scans/HW: ████░ 85%+ │ └──────────────────────────┘
Developer First
npm, pip, CLI, REST API. Copy two lines of code and start parsing. Comprehensive docs, type-safe SDKs, and playground.
$ npm i @peterparser/sdk $ peterparser parse doc.pdf ✓ Parsed in 312ms
Sync, Async, or Batch
One endpoint auto-classifies and routes. Process single files synchronously, async with webhooks, or batch thousands at once.
POST /v1/parse ├── mode: "sync" → 200 OK ├── mode: "async" → webhook └── mode: "batch" → queue
Custom Output Schema
Provide your XML or JSON schema—we match it exactly. Migrate from any parser without changing your integration.
{
"your_schema": true,
"compatible": "100%"
}Enterprise Ready
GDPR, CCPA, HIPAA-compliant architecture. Data processed in-region and never stored. German Datenschutz ready.
┌─────────────────────────┐ │ ✓ GDPR ✓ HIPAA-ready│ │ ✓ CCPA ✓ In-region │ └─────────────────────────┘
Transparent Pricing
Simple credit-based pricing. 100 free credits to start, then pay-as-you-go or save with monthly plans. No hidden fees.
┌─────────────────────────┐ │ 100 free credits │ │ Simple. Predictable. │ └─────────────────────────┘
Works Everywhere
Native SDKs, CLI tools, and integrations for every platform and workflow.
════════════════════════════════════════════════════════════
╔═══╗ ╔═══╗ ╔═══╗ All platforms. One API.
║ ◉ ║ ║ ◉ ║ ║ ◉ ║ Parse anywhere.
╚═══╝ ╚═══╝ ╚═══╝
════════════════════════════════════════════════════════════
Simple, Transparent Pricing
Pay only for what you parse. Starting at $0.05 per page or per 3,000 tokens. No subscriptions, no hidden fees.
Basic Extraction
Per page or per 3,000 tokens
- Plain Text / Markdown$0.05
- Website / HTML$0.05
Standard Documents
Per page
- Receipt$0.07
- Invoice$0.08
- Purchase Order$0.08
- Utility Bill$0.08
- Resume / CV$0.10
Identity Documents
Per document
- ID Card$0.10
- Driver License$0.10
- Passport$0.10
Financial Documents
Per document
- W-2 / W-9$0.10
- Pay Stub$0.10
- Bank Statement$0.15
- Tax Form$0.15
Complex Documents
Per page
- Bill of Lading$0.15
- Medical Record$0.30
- Legal Contract$0.30
Add-ons
Enhance any parsing job with optional features.
PII Masking
Auto-detect and redact personal identifiable information (SSN, addresses, phone numbers, etc.)
Extended TTL
Keep parsed results available beyond the default 24h retention window
Summarization
AI-generated summary of the parsed document content alongside structured output
Need help choosing? Check our FAQ or contact sales
Frequently Asked Questions
Everything you need to know about PeterParser.
We support 50+ file formats including PDF, PNG, JPG, TIFF, WEBP, DOC, DOCX, XLS, XLSX, PPT, PPTX, HTML, and more. If your format isn't listed, contact us—we likely support it or can add it.
Still have questions?
╔══════════════════════════════════════════════════════════╗
║ ║
║ $ peterparser parse document.pdf --output json ║
║ ✓ Parsed 42 pages in 1.2s ║
║ ║
╚══════════════════════════════════════════════════════════╝
Ready to start parsing?
Get 100 free credits and parse your first document in under 5 minutes. No credit card required.
Quick start:
npm install @peterparser/sdkpip install peterparser