Tohtoh HomeTohtoh
  • Docs
  • Pricing
  • Careers
Get started
Tohtoh - Document Intelligence Platform
SOC2 Compliant
Checking Status...

Product

PlatformPricingDocsChangelogStatus

Company

CareersPrivacy PolicyTerms of Service

Integrations

+67 more

Turn documents into structured data

Tohtoh understands complex docs — handling layout, tables, charts, handwriting, and images — powered by Longlichi, our purpose-built vision-language model.

Get started freeRead the docs
LonglichiLonglichi
STRUCTURED OUTPUT
{
  "vendor": "Acme Corp",
  "invoice_no": "INV-2847",
  "date": "2026-02-18",
  "items": [
    {
      "desc": "Service fee",
      "qty": 1,
      "amount": 2500.00
    },
    {
      "desc": "Platform license",
      "qty": 3,
      "amount": 1200.00
    }
  ],
  "subtotal": 6100.00,
  "tax": 549.00,
  "total": 6649.00,
  "due_date": "2026-03-18"
}

Purpose-built for document intelligence

Layout Intelligence

Longlichi reads documents the way humans do — understanding headers, columns, nested tables, and footnotes as a single coherent structure.

SEAL

Multimodal Intelligence

Charts, stamps, handwritten notes, embedded images — Tohtoh extracts meaning from every element on the page, not just the words.

{name: stramount: numdate: isoitems: []tax?: num}{"Acme Co"4,250.002025-01-15[3 items]637.50}

Schema Control

Define the exact JSON shape you need. Map fields, set validation rules, and get clean, predictable output every time.

{ sku: 01 }{ sku: 02 }{ sku: 03 }1M+ pages

Elastic Scaling

Process a single receipt or a million-page backlog. Async queues and parallel workers keep throughput high without sacrificing accuracy.

ARJADE{lang: "auto"data: [...]}

Native Multilingual Processing

Arabic invoices, Japanese contracts, German tax forms — Longlichi handles multilingual documents natively, no translation step required.

SOC2HIPAA

Enterprise-Grade Security

SOC 2 and HIPAA compliant with on-premise deployment options. Your documents never leave your infrastructure.

Built for every document workflow

01

Invoices & receipts

Extract line items, totals, vendor details, and payment terms from any format.

02

Legal documents

Identify key clauses, parties, dates, obligations, and renewal terms.

03

ID & KYC documents

Extract identity details from passports, licenses, and verification forms.

04

Medical records

Extract patient info, diagnoses, prescriptions, and lab results from clinical documents.

05

Bank statements

Process transaction histories, account summaries, and financial records for analysis.

06

Handwritten docs

Recognize and digitize handwritten notes, forms, and annotations with high accuracy.

Powered by

Longlichi logo

Longlichi

A vision-language model purpose-built for document intelligence by Hashtee Lab. Unlike general-purpose models, Longlichi is trained specifically to understand document layouts, read handwriting, parse complex tables, and extract structured data from real-world documents.

Get started free

Longlichi is a registered trademark of Hashtee Lab.

90+Supported formats
100+Languages
Sub-3sPer page processing
100+Integrations

Connect to your entire stack

Longlichi processes documents and sends structured data to 100+ integrations.

OpenAI
Slack
PostgreSQL
AnthropicAnthropic
Gmail
Notion
GitHub
Stripe
GeminiGemini
Discord
MongoDB
Salesforce
OpenAI
Slack
PostgreSQL
AnthropicAnthropic
Gmail
Notion
GitHub
Stripe
GeminiGemini
Discord
MongoDB
Salesforce
Longlichi
HubSpot
Mistral
Telegram
Supabase
Jira
Google Drive
Perplexity
WhatsApp
Pinecone
Firecrawl
Teams
HuggingFace
HubSpot
Mistral
Telegram
Supabase
Jira
Google Drive
Perplexity
WhatsApp
Pinecone
Firecrawl
Teams
HuggingFace
Browse all integrations

Simple, transparent pricing

Start free, scale as you grow. Usage-based billing so you only pay for what you use.

Free

$0/mo

For individuals getting started with document extraction.

  • $20 usage limit
  • 5 GB file storage
  • 5 min execution limit
  • Limited log retention
  • CLI / SDK access
Popular

Pro

$20/mo

For professionals running production workloads.

  • 150 sync runs / min
  • 1,000 async runs / min
  • 50 GB file storage
  • 50 min execution limit
  • Unlimited log retention
  • Unlimited invites

Team

$40/mo per seat

For teams that need shared resources and higher limits.

  • 300 sync runs / min
  • 2,500 async runs / min
  • 500 GB pooled storage
  • 50 min execution limit
  • Unlimited log retention
  • Dedicated Slack channel

Enterprise

Custom

For organizations with advanced security and scale needs.

  • Custom rate limits
  • Custom file storage
  • SSO / SAML
  • SOC 2 compliant
  • On-premise deployment
  • Dedicated support
View full pricing details