# ScamAI

> ScamAI (Reality Inc.) is a deepfake detection and scam-prevention platform. Multimodal detection (video, images, audio, documents) via the unified Eva V1.6 API, on-device real-time detection with Halo, plus KYC/IDV and document-forgery detection. Tagline: "Know what's fake."

This file is a map of the site for LLMs and AI agents. For the full site content in one fetch, read https://scam.ai/llms-full.txt. Key facts:

- Agents can call ScamAI detection directly: REST API at `https://api.scam.ai` (auth: `x-api-key` header). MCP: the hosted server is `https://api.scam.ai/mcp`, same `x-api-key` header; the client config is on /mcp-skills in the dashboard.
- There is ONE detection endpoint: `POST /v1/detections`, multipart field `file`. It infers whether you sent an image, a video, an audio recording or a document — you never choose a technique — and answers in one envelope: `verdict` (`LIKELY_AUTHENTIC`, `SUSPICIOUS` — send it to a human — or `LIKELY_AI_MANIPULATED`), `confidence` (0–1, the only score: the probability the media was MANIPULATED, so an authentic result carries a low number — it is not certainty in the verdict), a plain-English `summary`, `classes` (per-label probabilities summing to 1), `model` (always Eva V1.6 — one model; the server picks the detector from the media) and `credits_used`. Branch on `verdict`; sort on `confidence`. Errors are returned as errors — a caller out of credits gets a 402, never a reassuring verdict; a rate-limited call gets a 429.
- Credit cost per run: image 1 credit per image; video up to 20 credits per clip (1 credit per sampled frame, one frame a second, capped at 20); audio 1 credit per minute, rounded up; document 2 credits per page, sold on a plan through sales rather than self-serve credits. A credit is $0.02.
- Upload limits enforced by the scam.ai website and dashboard: image 10 MB, video 25 MB, audio 25 MB, document 25 MB. The REST API's own per-format limits are at https://scam.ai/docs/constraints.
- Self-serve pricing is prepaid credits at one flat rate: buy credits first, then every run spends them. Enterprise plans (a monthly platform fee with a lower per-frame rate) and document detection are arranged through https://scam.ai/contact; details at https://scam.ai/pricing.
- ScamAI is SOC 2 Type II audited and GDPR compliant; submitted media is analyzed to produce a result and then discarded, not retained.
- Marketing and docs pages are open to AI crawlers. App surfaces (/admin, /login, /signup, /credits, /settings, /api/) are private — don't crawl them.
- Research: 13 published papers across 5 areas (deepfake detection, document forgery, age-estimation robustness) with 7 open datasets — named authors on arXiv, listed at https://scam.ai/research.
- On-site metrics: 98.2% deepfakes caught (see https://scam.ai/platform/eva).
- To reach a human: https://scam.ai/contact.

## Start here
- [Home](https://scam.ai/): Deepfake detection and scam prevention.
- [Pricing](https://scam.ai/pricing): Pay as you go at $0.02 a credit, one flat rate; enterprise plans and document detection through sales.
- [Why ScamAI](https://scam.ai/why-scamai): Detection you can act on, with evidence.
- [Technology](https://scam.ai/technology): The detection research behind ScamAI.
- [FAQ](https://scam.ai/faq): Direct answers on what ScamAI detects, accuracy, real-time use, data handling, and compliance.
- [Request a demo](https://scam.ai/contact)

## Platform
- [Platform overview](https://scam.ai/platform): Detection, analytics, and the API in one place.
- [Eva V1.6 Detection Model — our detection engine](https://scam.ai/platform/eva): The unified API behind every ScamAI result: video, images, and documents, scored together in real time.
- [Check if AI — spot AI-generated media in seconds](https://scam.ai/platform/check-if-ai): Upload an image and get an instant read on whether it's AI-generated.
- [Deepfake Playground](https://scam.ai/platform/deepfake-playground): Deepfake yourself in 30 seconds. Point your camera at your own face, pick someone to become, and watch the swap happen live — the same thing an attacker can do with consumer tools.
- [On-prem deepfake detection](https://scam.ai/platform/on-prem-deployment): Run ScamAI detection inside your own environment — VPC, private cloud, or fully on-premises — so regulated data never leaves your perimeter.
- [Risk Signals](https://scam.ai/platform/risk-signals): Turn detection results into a view of your threat surface — patterns rather than single incidents. Available on request.
- [Deepfake Detection](https://scam.ai/platform/deepfake-detection): Purpose-built deepfake signals — face swaps, full generations, and replays — scored across images, video, and live calls.
- [ID Document Forgery Detection](https://scam.ai/platform/id-document-forgery): Tampering and forgery signals for identity documents — passports, national IDs, driver's licenses, residence permits.
- [Loan & Insurance Document Forgery](https://scam.ai/platform/loan-insurance-forgery): Forgery signals for due-diligence documents — bank statements, pay stubs, proof of income and address, invoices, policy documents.
- [Age Estimation](https://scam.ai/platform/age-estimation): Age checks from a live selfie — an estimated age and the probability the person is over your threshold, no ID collected.
- [Device Signals — liveness & presentation attacks](https://scam.ai/platform/capture-signals): Detection for spoofed presentations — printed photos, screen replays, and masks — plus liveness failures, caught at the point of capture.
- [Manual-Edit Forensics — image forgery detection](https://scam.ai/platform/manual-edit-forensics): Pixel-level forensics for manually edited selfies and documents — splices, clones, and retouching.
- [Halo — on-device deepfake detection](https://scam.ai/halo): The world's first on-device deepfake detection for live calls.

## For developers and AI agents
- [MCP & Skills for LLMs](https://scam.ai/platform/mcp): Bring ScamAI detection to AI agents — an MCP server and agent skills that let LLMs verify media and documents mid-task.
- [Detection API](https://scam.ai/platform/api): One API for the places fraud happens: send video, images, or documents and get a scored result back. Native SDKs are on the way.
- [API documentation](https://scam.ai/docs): ScamAI detection API overview: one REST endpoint returns an authenticity verdict for image, video, and audio — base URL, auth, request shape, and limits.
- [API docs: Authentication](https://scam.ai/docs/authentication): Authenticate ScamAI API requests with the x-api-key header, and create, rotate or revoke keys yourself from the dashboard — no sales call, no shared keys.
- [API docs: Quickstart](https://scam.ai/docs/quickstart): Run your first ScamAI detection with a single curl command against the unified endpoint, then read the verdict, confidence and credits spent in the reply.
- [API docs: Create a detection](https://scam.ai/docs/create-detection): POST /v1/detections runs a detection on one image, video or audio file — or a video link — and returns the verdict, the confidence, and the credits it spent.
- [API docs: Retrieve a detection](https://scam.ai/docs/retrieve-detection): GET /v1/detections/{id} fetches a detection after the fact and returns exactly the body the create call returned, so a webhook or a retry needs no cache.
- [API docs: Errors](https://scam.ai/docs/errors): Every error the ScamAI detection API returns — 400, 401, 402, 403, 409, 413, 415, 422, 429 and 502 — what each one means, and the action that clears it.
- [API docs: Media types & credits](https://scam.ai/docs/credits): What each media type costs on the ScamAI detection API: an image is one credit, video bills per sampled frame and audio per minute, all from a prepaid balance.
- [API docs: Constraints & best practices](https://scam.ai/docs/constraints): Accepted formats, per-media size caps and threshold guidance for the ScamAI detection API — what to send, what is refused, and how to read a middling score.
- [API docs: Dashboard & support](https://scam.ai/docs/dashboard): Manage API keys, watch the credit balance and open any detection's record in the ScamAI dashboard at app.scam.ai — plus how to reach support with a run id.

## Research
- [Research](https://scam.ai/research): Published papers on deepfake detection, document forgery, and age-estimation robustness, with open datasets and named authors on arXiv.

## Solutions
- [Solutions overview](https://scam.ai/solutions)
- [KYC / IDV fraud detection](https://scam.ai/solutions/kyc-idv): Make sure the person enrolling is live, present, and real — not a replay, a render, or a synthetic identity. ScamAI works with your KYC vendor to strengthen it, not replace it.
- [Loan & credit fraud detection](https://scam.ai/solutions/loan-credit): Stop synthetic applicants and doctored income documents at origination, before the money moves.
- [Insurance claims fraud detection](https://scam.ai/solutions/insurance-claims): Verify claim photos, videos, and documents are genuine — not staged, edited, or AI-fabricated.
- [Meeting deepfake protection](https://scam.ai/solutions/meeting-security): Continuous verification of who is really on the call — powered by Halo.
- [Pig butchering scams](https://scam.ai/solutions/pig-butchering): Detect the fake faces and forged proof behind long-con romance and investment scams — before your users are drained.
- [Deepfake social engineering attacks](https://scam.ai/solutions/social-engineering): Catch the deepfaked faces attackers use to manipulate employees into transfers, access, and approvals.
- [HR / Hiring](https://scam.ai/solutions/hiring-fraud): Protect hiring end to end — make sure the person you interview is the person you hire, not a deepfake stand-in or a proxy.
- [Content moderation](https://scam.ai/solutions/content-moderation): Score uploads for AI generation and manipulation before synthetic content spreads.
- [Misinformation detection](https://scam.ai/solutions/misinformation): Detect the deepfakes and synthetic media behind misinformation before it spreads and erodes trust.
- [Deepfake brand protection](https://scam.ai/solutions/brand-protection): Catch the deepfakes, fake ads, and impersonations that hijack your brand and your executives' likenesses.
- [AI phishing & spam detection](https://scam.ai/solutions/phishing-spam): Screen the images, documents, and media inside phishing and spam campaigns for AI generation and manipulation.

## Industries
- [KYC/AML compliance](https://scam.ai/industries/kyc-aml-compliance): Meet KYC and AML obligations against AI-era fraud — deepfake selfies, forged IDs, and synthetic identities caught at onboarding and beyond.
- [On-device deepfake detection agent](https://scam.ai/industries/on-device-agent): Real-time detection that runs on the device — media and identity verified locally, with nothing leaving the endpoint. Shipping today in Halo; an embeddable agent for your own apps and devices is in development.
- [Deepfake detection for financial services](https://scam.ai/industries/financial-services): Stop synthetic identities at onboarding and deepfaked executives on video calls before the wire is released.
- [Deepfake detection for the public sector](https://scam.ai/industries/public-sector): Protect officials and citizens from impersonation campaigns.
- [E-commerce & marketplaces](https://scam.ai/industries/e-commerce-marketplaces): Keep fake sellers and cloned storefronts out.
- [Dating apps](https://scam.ai/industries/dating-apps): Keep fake profiles, AI-generated photos, and deepfaked video calls off your platform — before they turn into romance scams.
- [Telecom fraud detection](https://scam.ai/industries/telecom): Protect SIM changes, account access, and support channels from synthetic identities and social engineering.

## Compare
- [ScamAI vs Reality Defender](https://scam.ai/company/vs-reality-defender): Reality Defender is a strong, well-funded media-authenticity layer — it flags AI-generated audio, video, image, and text, and now watches live calls. But it stops at detection: no document-forgery or liveness for identity flows, and every check runs server-side. ScamAI adds the identity and document layer, and runs detection on the endpoint itself with Halo.
- [ScamAI vs Sensity](https://scam.ai/company/vs-sensity): Sensity has grown from deepfake monitoring into real-time detection — a KYC product and a Teams plugin for live calls, with strong forensic explainability. The gap now is where the detection runs: Sensity scores in the cloud, while ScamAI runs on the endpoint with Halo, so sensitive KYC media never leaves the perimeter.
- [ScamAI vs Hive](https://scam.ai/company/vs-hive): Hive is a content-moderation platform with a serious deepfake-detection line — credible enough to win a U.S. Department of Defense contract. But its core is moderation at scale; ScamAI is fraud-first, built to protect identity and stop scams, and runs on-device where Hive is a cloud API.
- [ScamAI vs Resemble AI](https://scam.ai/company/vs-resemble-ai): Resemble Detect is genuinely capable — one model across audio, video, and image, real-time on calls, with a strong explainability story. But Resemble also builds voice-cloning technology, so it sits on both sides of the problem. ScamAI is independent — detection is the whole business — and runs on-device with Halo.
- [ScamAI vs Incode](https://scam.ai/company/vs-incode): Incode is a Gartner-Leader identity-verification platform that now ships Deepsight, a dedicated deepfake engine. It's excellent at onboarding — but that's its center of gravity. ScamAI defends every call, claim, and login after onboarding, runs on-device for live meetings, and deploys on-prem/VPC.
- [ScamAI vs Sightengine](https://scam.ai/company/vs-sightengine): Sightengine is a content-moderation API with deepfake detection and a passive-liveness check bolted on. ScamAI is a fraud and identity platform — document-forgery, liveness, and deepfake detection in one result, running on-device with Halo where Sightengine runs server-side.
- [ScamAI vs AI or Not](https://scam.ai/company/vs-aiornot): AI or Not answers "is this AI-generated?" — a general classifier. ScamAI is a fraud and identity detection layer: document-forgery, liveness, and deepfake signals your KYC flow acts on, running on-device with Halo.

## Resources
- [Resources](https://scam.ai/resources): Research, documentation, the regulation tracker, and partner programs.
- [Deepfake regulation tracker](https://scam.ai/resources/regulation): Where deepfake and AI-fraud law stands, jurisdiction by jurisdiction.
- [Education](https://scam.ai/resources/education): Learn how AI-driven scams work — and how to defend against them.
- [Trust Center](https://scam.ai/resources/trust-center): Security, privacy, and compliance documentation.
- [Changelog](https://scam.ai/resources/changelog): What's new in ScamAI detection — models, APIs, and product.
- [Affiliate program](https://scam.ai/resources/affiliate): Earn by referring teams that need deepfake and fraud detection.
- [Partner program](https://scam.ai/resources/partners): Resell, integrate, or build on the ScamAI detection API.
- [Deepfake detection education program](https://scam.ai/resources/education-program): Training, certification, and curriculum for partners, students, and institutions who want to teach and deploy deepfake detection.
- [Our partners](https://scam.ai/resources/partnerships): Build with ScamAI — technology, channel, and integration partnerships that embed deepfake detection into more products, platforms, and go-to-market motions.

## Blog
- [Blog](https://scam.ai/resources/blog): Detection research and field notes from the team.

## News
- [Press](https://scam.ai/resources/press): Announcements and coverage.

## Community
- [Anti-Scam Community](https://scam.ai/community): Threat sharing, researcher Q&A, and early access.

## Company
- [About ScamAI](https://scam.ai/company/about): ScamAI exists because seeing is no longer believing. We build the tools that let people and organizations trust what they see.
- [Careers](https://scam.ai/company/careers): Don't apply if you just want a job — this isn't one. Everyone here shares the same goal and the same faith: beat the criminals using AI to deceive people. The bar is high and we are ruthlessly selective. But if this is your fight, we want to hear from you.
- [Team](https://scam.ai/company/team): The researchers and engineers building ScamAI — focused on detecting AI-generated deception at the moment it matters.
- [Company](https://scam.ai/company): About, team, careers, and brand.
- [Brand kit](https://scam.ai/brand)

## Legal
- [Privacy Policy](https://scam.ai/legal/privacy): How Reality Inc. (DBA Scam.ai) collects, uses, discloses, and protects personal data across its sites and services, and the rights available to individuals.
- [Terms of Service](https://scam.ai/legal/terms): The binding terms governing access to and use of the ScamAI website, dashboard, API, and apps, including accounts, acceptable use, termination, and liability.
- [Cookie Policy](https://scam.ai/legal/cookies): How and why ScamAI uses cookies and similar technologies on its sites, what each category does, and how to control or withdraw consent in your browser or ours.
- [Data Processing Addendum](https://scam.ai/legal/dpa): Processor terms for personal data ScamAI processes on behalf of customers under GDPR Article 28: instructions, security, subprocessors, transfers, audits.
- [Subprocessors](https://scam.ai/legal/subprocessors): Third parties ScamAI engages to help operate the Services — hosting, database, email, analytics, and abuse prevention — and how we announce changes to the list.
- [Master Services Agreement](https://scam.ai/legal/msa): The default commercial terms for paid ScamAI Services — fees, term, confidentiality, IP and data, and liability — unless a signed agreement provides otherwise.
- [Halo App End User License Agreement](https://scam.ai/legal/halo-eula): The license terms for the Halo on-device deepfake-detection app: what you may install and run, what stays on your device, updates, and limits of liability.