Detection API

Send media over HTTPS and act on the JSON. Your backend submits an image, video, or document to the REST API with an API key and receives a probabilistic confidence score plus the evidence signals that fired. Your code compares the score to thresholds you set and branches — approve, step up, or route to review. There is no model to host; any language that can make an HTTP request can integrate today, with native SDKs coming.

A scored, explainable result rather than a bare label. The JSON response carries a probabilistic confidence score for manipulation, the specific signals that fired — the evidence behind the score — and per-frame detail for video so you can locate where in a clip manipulation appears. That structure serves machines and humans alike: your code thresholds on the score for automated decisions, while analysts and auditors read the signals to defend each outcome after the fact.

It should offer both speeds, because fraud workflows need both. ScamAI's synchronous endpoints return results at real-time latency for inline flows — an onboarding selfie check or a document step where a user is actively waiting. Batch endpoints handle volume work: re-screening a loan book, scoring a claims backlog, or moderating an upload queue where throughput matters more than a single request's speed. Both patterns return the same result structure, so one integration serves live decisions and pipeline jobs alike.