This is an n8n community node for DeepRead — AI-native document processing with 97%+ accuracy using multi-model consensus (GPT + Gemini + dual OCR).
n8n is a fair-code licensed workflow automation platform.
Installation Operations Credentials Compatibility Usage Resources
Follow the installation guide in the n8n community nodes documentation.
Quick install in n8n:
- Go to Settings → Community Nodes
- Click Install
- Enter
n8n-nodes-deepread - Click Install
The DeepRead node supports four operations, all powered by the same DeepRead API:
Extract text from any PDF or image. Returns the raw extracted text plus a preview URL for the document.
Extract typed JSON fields from documents using a custom JSON Schema. The node outputs the full job response. Extracted fields live in the extraction.fields array ($json.extraction.fields), where each field is an object:
key— the field name from your schema (e.g.invoice_number)value— the extracted value (scalar, object, or array)needs_review—trueif the field needs human reviewreview_reason— explanation when flagged (present only whenneeds_reviewistrue)location.page— page number the value was found on
Use this for invoices, receipts, contracts, medical records, insurance claims — any document where you need specific fields.
Fill any PDF form (including scanned, non-editable forms) with your data. AI visually detects fields, semantically maps your JSON data, fills the form, and quality-checks the result. Returns the filled PDF as a binary attachment.
Returns:
filled_form_url— URL to the filled PDFfields_detected— total fields foundfields_filled— fields successfully filledfields_hil_flagged— fields needing review
Detect and redact 14 types of PII with irreversible black bars (HIPAA/GDPR ready):
- Names, SSNs, credit cards, emails, phones, addresses
- IPs, DOB, passport numbers, driver's licenses
- Bank accounts, IBANs, URLs, medical record numbers
Returns the redacted PDF as a binary attachment plus a detection report by PII type.
Supports 5 languages: English, Chinese, Spanish, Hindi, Arabic.
You need a DeepRead API key:
- Sign up at deepread.tech/dashboard (free, no credit card)
- Get your API key
- In n8n, create a new DeepRead API credential
- Paste your API key (starts with
sk_live_...) - Click Test to verify
Free tier: 2,000 pages/month Pro: $99/mo for 50,000 pages BYOK: Connect your own OpenAI/Google/OpenRouter key at deepread.tech/dashboard/byok for zero DeepRead LLM costs and unlimited pages
- Tested with n8n 1.0+
- Works in self-hosted and cloud n8n
- Compatible with all standard n8n agent integrations (use as a tool in AI Agent nodes)
[Gmail Trigger] → [DeepRead: Structured Extraction] → [Google Sheets]
Schema: vendor, total, due_date
[File Upload] → [DeepRead: PII Redact] → [OpenAI: Analyze]
[Webhook] → [DeepRead: Form Fill] → [Email: Send filled PDF]
Form fields: full_name, dob, ssn, address
The node handles all async polling automatically — submit a document, get the result back. No need to manage job IDs or polling logic.
- DeepRead website: https://www.deepread.tech
- Dashboard: https://www.deepread.tech/dashboard
- API documentation: https://www.deepread.tech/docs
- Demo repo (Python/Node/cURL examples): https://github.com/deepread-tech/deepread-demo
- n8n community nodes documentation: https://docs.n8n.io/integrations/#community-nodes
- Report issues: https://github.com/deepread-tech/n8n-nodes-deepread/issues
- Email support: support@deepread.tech
- Fix: PII errors now properly extracted from
{code, message}objects - Fix: Credential test now uses authenticated endpoint to validate API keys
- Fix: Lint errors (icon, alphabetical order, sleep import)
- Initial release with 4 operations: OCR Extract, Structured Extraction, Form Fill, PII Redact
- Async polling with exponential backoff
- Binary output for redacted/filled PDFs