# Document Verification API > POST a document, get a structured JSON verdict in about a minute: clear, suspicious, or likely tampered, with plain-English findings. 130+ forensic checks across 100+ document types - no template setup, no sales call, no document storage. **Canonical URL:** https://tampercheck.ai/document-verification-api --- ## Why document verification belongs in the API layer Most document fraud tooling is built for enterprise procurement: demo calls, annual contracts, per-seat dashboards. Meanwhile the actual work - deciding whether a submitted PDF is genuine - happens inside **your** onboarding, lending, or claims pipeline, where what you need is an endpoint, not a portal. Building verification in-house doesn't scale either. One or two forensic checks are a weekend project; maintaining 130+ checks against fraudsters who update their tooling every few months is a permanent team. An API-first verification layer means fraud detection sits inline in your existing flow: documents are checked at upload, verdicts route the application, and suspicious files never reach downstream systems as trusted data. ## What TamperCheck detects ### Single REST endpoint POST the file to /api/v1/analyse with your API key. No SDKs required, no callback gymnastics for the simple path - a synchronous verdict in about a minute, with webhooks available for async workflows. ### Structured JSON verdicts Every response includes a verdict (clear / suspicious / likely tampered), a calibrated 0-100 risk score, and itemised findings tied to regions of the document - ready to route programmatically. ### 130+ forensic checks per call Font metrics, running-balance arithmetic, metadata fingerprints, text-layer vs raster comparison, ELA, AI-generation detection, and more - all running in parallel on every submission. ### 100+ document types Bank statements, payslips, passports, driver's licences, utility bills, academic credentials, invoices, trade licences - across most major issuing countries, with no per-template configuration. ### Zero document storage Documents are analysed in memory and discarded once the verdict is returned. Nothing is retained - which keeps GDPR and data-minimisation reviews short. ### BYOK for AI inference Bring your own OpenAI, Anthropic, Google, or Azure key and the LLM adjudication layer runs on your provider account at cost - or use managed inference with no keys to configure. ## Integrate document fraud detection in an afternoon TamperCheck is self-serve by design: create an account, generate an API key, and make your first call with the $5 trial credits. The verdict format is stable, documented, and built to be routed on - not read in a dashboard. - **One endpoint** - POST /api/v1/analyse with the file, get JSON back - **Verdict in about a minute** - fast enough to sit inline in onboarding - **Webhooks** for asynchronous and batch pipelines - **$0.50 per document** - usage-based, no subscriptions or minimums - **$5 trial credits** on signup - test with your own documents first - **Full API docs** at tampercheck.ai/docs, no sales call required ## Frequently asked questions ### What is a document verification API? A document verification API accepts a document (PDF, scan, or photo) over HTTP and returns a machine-readable judgment on whether it's genuine - covering tampering, forgery, and AI generation - so fraud checks can run inline in an automated workflow instead of a manual review queue. ### How fast is the API? A full 130+ check analysis returns in about a minute per document on average. Checks run in parallel, so complex documents don't take proportionally longer. ### What does the response look like? A JSON object with an overall verdict (clear, suspicious, or likely tampered), a 0-100 risk score calibrated per document type, and an array of findings, each with a plain-English description and the document region it applies to. ### Is there a free tier or trial? New accounts include $5 in trial credits - enough to analyse 10 documents at the standard $0.50 per document rate. No card is required to start, and there are no subscriptions or monthly minimums after that. ### Do you store the documents we send? No. Files are processed ephemerally: analysed in memory, verdict returned, bytes discarded. This zero-storage design is deliberate, so integrating the API doesn't add a new data-retention surface to your compliance review. ### Can we use our own AI provider keys? Yes. BYOK (bring your own key) is supported for OpenAI, Anthropic, Google, and Azure. The LLM adjudication layer routes through your account at provider cost; the upstream forensic checks run on TamperCheck's infrastructure either way. ## Related use cases - https://tampercheck.ai/use-cases/kyc-identity-verification - https://tampercheck.ai/use-cases/lending-credit - https://tampercheck.ai/use-cases/insurance-claims ## Compare with alternatives - https://tampercheck.ai/compare/inscribe-vs-tampercheck-ai - https://tampercheck.ai/compare/resistant-ai-vs-tampercheck-ai --- Try TamperCheck free: https://tampercheck.ai/dashboard · Docs: https://tampercheck.ai/docs · Pricing: https://tampercheck.ai/pricing