- Product
- Document extraction
- Intake
- Upload · E-mail · API
- Output
- JSON · Excel · CSV
- Plans
- $0 · $9.90 · $100 · Custom
Built for huge volumes and 1,000-page documents.
High-volume pipelines and whole documents read in one pass, billed in credits, with a free plan to start.
Free plan, no card required. Enterprise by contract. Try it on one file
Figure 1 Six kinds of paperwork, read for you: receipts, supplier invoices, a 40-page contract, a case file of phone photos, résumés and bank statements. Select a pin to start the film at that use.. The film has sound. Every document, company and person in it is fictional.
Credits included every month. Top up only when you need more.
Billing Annual billing is 20% off the monthly price. Credits still renew every month. How credits work
| Start here | |||
| Free | Starter | Pro | Enterprise | |
|---|---|---|---|---|
$0/mo No card required | $9.90/mo per month · cancel anytime | $100/mo per month · cancel anytime | Custom By contract · your own model key | |
Kick the tires on your own documents | Freelancers and small teams automating a real workflow | Teams running pipelines and very long documents | High volume and very long documents, on your own model key: run it yourself or have us set it up | |
| Start free | Get Starter | Get Pro | Talk to sales | |
| Credits | ||||
| Credits per monthRenew every month, do not roll over | 10 | 125 | 1,500 | Noneyour own model key |
| Price of an extra creditTop-up packs of $10, $25, $50 or $100 | $0.10 | $0.08 | $0.067 | Not applicable |
| Bonus on top-ups | None | +25% | +50% | Not applicable |
| Limits | ||||
| Max pages per documentRead whole, in one pass | 10 | 100 | 1,000 | No limit |
| Parallel documents | 1 | 3 | 10 | No limit |
| Extraction & integration | ||||
| Extraction templates | 3 | 25 | Unlimited | Unlimited |
| Validation rules | Included | Included | Included | Included |
| REST API + webhooks | Included | Included | Included | Included |
| Upload, e-mail or API intake | Included | Included | Included | Included |
| JSON, Excel and CSV output | Included | Included | Included | Included |
| Team & support | ||||
| Support | Docs | An engineer, in a shared chat | ||
| Templates configured for you by our engineer | Not included | Not included | Not included | Included |
| Proof of concept on your documents | Not included | Not included | Not included | Included |
| Security & procurement | ||||
| Automatic deletion | 7 days | 7 days | 7 days | Configurable |
| Your data never trains AI | Included | Included | Included | Included |
| DPA | On request | On request | On request | Included |
| Bring your own LLM key (BYOK) | Not included | Not included | Not included | Included |
| Invoicing | Not included | Not included | Not included | Included |
| Included in every plan |
| |||
What a month of credits covers
How many documents of each kind a plan's monthly credits cover. Top-ups are not counted.
| Item | Free, 10 credits | Starter, 125 credits | Pro, 1,500 credits | Enterprise, own model key |
|---|---|---|---|---|
| Invoice, 1 page1 credit each | 10 documents | 125 documents | 1,500 documents | Not applicable |
| Sparse contract, 50 pages1.1 credits each | Over the page limit | 113 documents | 1,363 documents | Not applicable |
| Dense table, 1 page3.9 credits each | 2 documents | 32 documents | 384 documents | Not applicable |
| Dense table, 10 pages21.2 credits each | Not covered | 5 documents | 70 documents | Not applicable |
Not covered means one such document costs more than the plan's credits for the month.
Measured on synthetic documents. Real documents vary: the same dense document varied by up to 50% between two runs.
Top-ups
One-off packs of extra credits, used after your plan credits.
| Item | Free, no bonus | Starter, +25% bonus | Pro, +50% bonus | Enterprise, own model key |
|---|---|---|---|---|
| $10 pack | 100 credits | 125 credits | 150 credits | Not applicable |
| $25 pack | 250 credits | 312 credits | 375 credits | Not applicable |
| $50 pack | 500 credits | 625 credits | 750 credits | Not applicable |
| $100 pack | 1,000 credits | 1,250 credits | 1,500 credits | Not applicable |
Price of an extra credit: Free $0.10, Starter $0.08, Pro $0.067.
Any document type. One pipeline.
By use case
- 4.1
Invoice processing
Invoice processing, see use caseVendor, tax ID, line items, taxes and due date from invoices and bills.
Fields vendor tax_id line_items total
- 4.2
Contract extraction
Contract extraction, see use caseParties, dates, amounts and the clauses you name, read at intake.
Fields parties effective_date term contract_value
- 4.3
Receipts & expenses
Receipts & expenses, see use caseMerchant, tax ID, total, taxes and expense category from receipts and proofs of payment.
Fields merchant tax_id total taxes
- 4.4
Bank statements
Bank statements, see use caseAccount, period, opening and closing balances and one row per transaction from bank statements.
Fields account_holder account_number period_end closing_balance
By industry
Your documents are different? Book a demo.
All solutions05
Integrate in an afternoon.
A REST API, real-time webhooks and custom extraction templates. Full documentation, no SDK required.
Extraction templates and validation rules
Define your fields once; Parser validates every document against your rules.
A webhook the moment it's ready
Data lands in your ERP or internal system, no polling.
Sent when extraction completed · failed
Sample request and result, abridged. Upload returns 202 Accepted with a documentId and an extractedDocumentId; the result arrives on your webhook or from GET /extracted-documents/{id}, where id is the extractedDocumentId. Field names come from your extraction template.
$ curl -X POST \ https://api.parserai.co/documents/upload \ -H "Authorization: Bearer $PARSER_API_KEY" \ -F "file=@invoice.pdf" \ -F "entity_group_id=$TEMPLATE_ID"# 202 Accepted# {"documentId": "…", "extractedDocumentId": "…"}{ "extraction_status": "success", "extracted_data": [ { "vendor": "Acme Supplies Inc.", "tax_id": "12-3456789", "total": 1859.76 } ]}The questions we get about pricing, limits and data.
Pricing and limits
A credit is the unit Parser bills in. One credit is about what a typical one-page invoice costs, and every extraction costs at least 1. Beyond that, an extraction is charged on the work the model actually did for it: a heavier document uses more credits and a light one uses the minimum. A 50-page text-heavy contract can cost about as little as an invoice, and a dense table costs more. Building a template with AI also uses credits (minimum 1). Free includes 10 credits a month, Starter 125 and Pro 1,500. The console shows your balance and the cost of each document.
New documents wait until you top up or the month renews. Plan credits renew every month and do not roll over, and top-up credits are used after the plan credits. A top-up is a one-off pack of $10, $25, $50 or $100; Starter adds a +25% bonus and Pro +50%. Nothing else is billed: the only charges are your subscription and the top-ups you choose to buy. Enterprise runs on your own model key, so it has no credits to run out.
No. A failed extraction is not charged. Reprocessing a document is charged again, because it is a new run.
Parser reads the whole document at once instead of cutting it into small pieces. Fields that depend on distant pages, like a total on page 900 that must match a line item on page 12, are extracted and validated together. The limit is pages per document: 10 on Free, 100 on Starter, 1,000 on Pro and no limit on Enterprise.
No. Free includes 10 credits a month: sign up, send documents, and upgrade or top up only if you outgrow them.
When 1,000 pages per document or 10 parallel documents are not enough, when you want to run on your own model key (BYOK) instead of credits, or when you want an engineer for your team, with your templates set up for you. Enterprise is priced by contract.
Product and data
Validation rules check every field against what you expect, before it enters your system.
The upload takes PDF, TXT, JSON, DOCX, CSV and XLSX files. The fields come from your extraction template, not from a fixed list of document types. Typical documents are listed by use case and by industry under Solutions.
The core endpoint integrates in an afternoon. Most customers are in production in under a week, with templates configured by us in parallel.
Encryption in transit and at rest. Documents are deleted automatically after 7 days, and extracted data is kept until you delete it. Your documents and extracted data are never used to train AI models. GDPR/LGPD compliance; DPA available on request.
The prototype is easy; production is hard. Documents that scan badly, broken tables, cross-validation, monitoring and model upgrades without regressions each need an owner. The “Build or buy?” page, linked in the footer, lists the work between a prototype and production.
- Free 10
- Starter 100
- Pro 1,000
- Enterprise No limit
See it on your own documents.
In the demo we process your documents live — no slides, no fluff.
30 minutes · no commitment
08 Order
Self-serve
Free, Starter ($9.90/month) and Pro ($100/month) start when you sign up. No card required for Free. Try it on one file
Enterprise
By contract · your own model key · an engineer for your team · setup done for you if you want it · POC on your documents.