Contract Extraction API

4.8/5

(30+ reviews)

Contract data extraction API that turns agreements into JSON

Pull parties, dates, amounts, renewal terms and signatures out of any contract, scanned or native PDF, into structured JSON. You define the fields once, and every value comes back with a confidence score.

No credit card required

SOC 2 Type II & GDPR

Contract data extraction API turning a master services agreement into JSON with dates, parties and amounts

Trusted by finance and product teams at

Why contract data stays locked in PDFs

Every counterparty drafts its own way, so dates, amounts and renewal terms sit in different clauses on different pages. Someone reads each agreement end to end and keys the terms into a tracker.

Contract signed

Signed PDF lands in an inbox or shared drive.

Read end to end

Someone reads every page to find the key terms.

Friction

Key dates hide in clauses, annexes and amendments.

Manual keying

Parties, dates and amounts typed into a tracker.

Friction

One wrong date and a renewal slips through.

Legal review

Unclear terms sent back to legal for a second read.

Friction

Every question adds days to the cycle.

Tracker updated

Finally logged, one agreement at a time.

RESULT

[X] minutes to read and key each contract, and [X]% of renewal dates missed or entered wrong.

See how Mindee fixes it

Contract details

contract_type, contract_number, signature_date

Parties

parties[].name, parties[].role, parties[].address

Key dates

effective_date, end_date, notice_period_days

Financial terms

total_value, currency, payment_terms

Renewal & law

is_auto_renewal, renewal_term_months, governing_law

Signatures

signatories[].name, signatories[].title, is_signed_by_all_parties

response.json

{

"contract_type": { "value": "Master Services Agreement" }, "contract_number": { "value": "MSA-2026-0137" }, "signature_date": { "value": "2026-03-02" },

"parties": [ { "name": { "value": "Northwind Analytics Ltd" }, "role": { "value": "Provider" } }, { "name": { "value": "Harbor Retail Inc." }, "role": { "value": "Client" } } ],

"effective_date": { "value": "2026-04-01" }, "end_date": { "value": "2028-03-31" }, "notice_period_days": { "value": 90 },

"total_value": { "value": 186000.00 }, "currency": { "value": "USD" }, "payment_terms": { "value": "Net 30" },

"is_auto_renewal": { "value": true }, "renewal_term_months": { "value": 12 }, "governing_law": { "value": "State of New York" },

"signatories": [ { "name": { "value": "Dana Ortiz" }, "title": { "value": "COO" } } ], "is_signed_by_all_parties": { "value": true },

}

Ready to post, not just to read.

You choose the fields. Dates come back in ISO 8601, amounts as numbers, and every value carries a confidence score and its position on the page.

Built for real contracts, not clean templates

Forty-page scanned agreements, amendments stapled to the back, signatures in the margin. The model reads the whole document and finds each term wherever the drafter put it.

Sample contract sent to Mindee, which drafts a data schema with typed fields you can edit

Your fields, drafted from one sample

Upload a sample contract and an AI agent drafts the data schema. Rename, add or remove fields, then call the API with your own model.

Effective date, notice period and contract value found on page 1, clause 14 and an annex

Terms found anywhere in the document

Effective date on page 1, notice period in clause 14, price in an annex. The model reads the full contract and returns each term in one response.

Contract signature page returned as two lists: parties with roles and signatories with titles

Every party and signatory, as a list

Each party comes back with its name, role and address, and each signatory with name and title, however many sign the agreement.

Reviewer correction on one contract feeds continuous learning, so the next contract is right first time

Learns from your corrected contracts

Turn on continuous learning and the contracts you correct feed the model, so it adapts to the way your counterparties draft.

PDF / JPEG / PNG / WEBP / TIFF / HEIC, Long multi-page agreements, +50 languages / any currency, Scanned & signed copies, Amendments & annexes

Contract extraction accuracy you can check, term by term

Every value comes with a confidence score, so clear terms flow straight to your system and ambiguous ones go to a reviewer. Test it on your own contracts in the free trial.

97.2%

Field-level accuracy on key terms

Parties, dates, amounts

90.1%

Accuracy on renewal & notice terms

Auto-renewal, notice period

2.5s

Median time per page

Multi-page contract, async call

A confidence score on every field

Set your own threshold. Fields above it flow straight to your systems; anything below lands in a review queue, with the exact spot on the contract highlighted. Définissez votre propre seuil. Les champs au-dessus partent directement dans vos systèmes ; les autres rejoignent une file de vérification, avec leur emplacement exact mis en évidence sur votre contract. Define tu propio umbral. Los campos que lo superan pasan directamente a tus sistemas; los que quedan por debajo van a una cola de revisión, con la ubicación exacta resaltada en contract.

Auto-approve the contracts you can trust Aprueba automáticamente contracts de confianza Validez automatiquement les contracts fiables

Send only real exceptions to a human

Document AI features, better than OCR

Prepare, classify and extract. Mindee delivers high-accuracy extraction for every document format, so you can automate workflows with speed and high reliability.

Prototype in minutes, go live with the API

Start with a no-code workflow to prove the value on your own contracts, then move the same model into your product. Commencez par un workflow no-code pour prouver sa valeur sur vos propres contracts, puis intégrez le même modèle dans votre produit.

What teams build with contract data extraction

The same API powers very different products. Here is where it usually starts.

Rated 4.8/5 by developers and operations teams

4.8

on G2

4.9

on Capterra

quote

Mindee is a software that helps us to convert all of our physical business data like bills, invoices, warranty cards, calendar, recipts received to us into a digital documents that can be stored in our drive and can be uploaded in different type of Excel sheets so that all the updates can be maintained and a proper analytics of transactions can be kept by the financial team

on G2

quote

Excellent. In addition to their great product, the sales team has always been proactive on how they could help us leverage the maximum results from their product. It was like having an additional product manager on our side

on Capterra

quote

I like the easiness and how to use it. Also the price model is very fair. Good with space for improvement

on Capterra

FAQ about Mindee's Contract Data Extraction API

Can't find what you're looking for? Our team answers within one business day.

About contract OCR À propos de l’OCR pour les contract

Can AI extract data from contracts?

Yes. Mindee reads contracts (native PDFs or scans) and returns the key information as structured JSON: parties, effective and end dates, duration, renewal and notice periods, contract value, payment terms, governing law and signature dates. Instead of reading dozens of pages to find a termination date, your teams get data they can search, filter and sync with a CLM, CRM or ERP. You can then trigger renewal reminders, track commitments across a whole contract portfolio, or migrate legacy contracts into a new system.

Can I extract fields specific to my own contracts?

Yes. Contracts vary much more than standardized documents, so you can define the exact fields you need for your use case. For example: a lease’s rent and indexation clause, a supplier agreement’s liability cap, an SLA’s service levels, or an employment contract’s notice period. Mindee extracts these fields with the same structured output and confidence scores as standard fields, without template configuration, and it works whatever the contract’s layout, length or language.

Can AI contract extraction be trusted?

Trust comes from being able to verify. General-purpose AI tools can produce a convincing summary that misses a clause or invents a date, with no way to know which parts are reliable. Mindee gives every extracted value a confidence score and its location in the document, so a reviewer can check the source in one click. You can approve high-confidence fields automatically and send uncertain ones to a person for review. Your team keeps control where it matters, while saving the time spent on manual reading.

Does Mindee review contracts or give legal advice?

No. Mindee extracts and structures contract data, but it doesn’t assess risks, suggest redlines or give legal advice. It provides the reliable data layer that legal, procurement and finance teams, or the contract review tools they use, can build on. For example, Mindee can tell you that a contract renews automatically with a 90-day notice period, and your team or CLM decides what to do about it. Contracts often contain confidential terms: Mindee is SOC 2 Type II certified and GDPR compliant, and data is encrypted in transit and at rest.

About Mindee

Is my data secured and protected during the conversion process?

Yes, your data is highly secured and protected during the entire conversion process. As an enterprise-grade OCR solution, Mindee takes data privacy very seriously. Here are the key security measures in place:

  • Certified compliance: Mindee's infrastructure is SOC 2 Type II certified and fully GDPR compliant, ensuring strict industry standards for data protection.
  • Encryption: All documents and extracted data are fully encrypted both in transit (during the API call) and at rest.
  • Data localization: You have control over where your data is processed, with the option to host and process your data on either EU or US servers.
  • Strict privacy: Mindee respects data confidentiality. Your processed documents are not shared with third parties, and your private data is not used to train global AI models.

In short, your sensitive documents are processed in a secure, isolated environment and remain completely under your control.

Is Mindee's OCR API free to use?

We provide a 14 days free trial so you can fully test any of our OCR models — no credit card required. After this, we offer different pricing tiers depending of the volume of pages processed and the features you might need. See the pricing page for more information.

What file formats are supported for JSON conversion?

The supported document formats are:

  • PDF (application/pdf) – While technically a document format rather than an image, it is natively supported for all extraction models.
  • JPEG / JPG (image/jpeg)
  • PNG (image/png) – Must be non-animated.
  • WebP (image/webp)
  • TIFF / TIF (image/tiff) – Both single-page and multi-page TIFFs are supported and processed similarly to PDFs.
  • HEIC (image/heic) – Apple's High-Efficiency Image Container format.

‍

📌 Important technical limitations to keep in mind:

To ensure the OCR pipeline runs smoothly and successfully returns your JSON, make sure your files adhere to the following constraints:

  • Maximum file size: 100 MB per file.
  • Maximum page count: Up to 200 pages per document.
  • File state: The files cannot be encrypted, and PDFs must not be password-protected.

Ready to stop reading contracts line by line?

Build your contract model from a sample in minutes and send your first agreement to the API, with a team of document processing engineers behind it.

14-day free trial

No credit card required