Didit Age Estimation API

Overview

Estimates a person's age from a facial image and runs a passive liveness check in the same call to block spoofs. The age is model-predicted from the face, not verified against a document: use it for age gates and low-friction checks, not as legal proof of age.

Key constraints:

• Allowed file extensions: tiff, jpg, jpeg, png, webp (no PDF)
• Maximum file size: 5 MB (images are compressed to about 0.3 MB before processing)
• One clear, front-facing, well-lit face. The largest detected face drives age_estimation
• Accuracy: mean absolute error (MAE) 3.5 years overall; 1.5 years for under-18 (see the table below)

Pricing: $0.10 (per successful call; standalone calls have no free tier). These are the list prices until 1 November 2026, when Didit pricing changes and the 500 free checks a month become $10 of free credit a month. Check didit.me/pricing for current prices.

Decision: any warning declines. status is Approved only when warnings is empty. There is no In Review on this endpoint. method is always PASSIVE.

Not on this endpoint: blocklist and duplicate-face screening, MULTIPLE_FACES_DETECTED, the ID verification fallback for borderline ages and per-country age limits. Those are workflow features (see Adaptive Age Estimation).

Saving (save_api_request, default true): the call is saved as an API session (Business Console, status.updated webhook, and GET /v3/session/{request_id}/decision/, where the result appears in liveness_checks[] with features: ["AGE_ESTIMATION"]), the face crop and reference image are stored, and the face is added to your application's face search index (used by Face Search and duplicate detection). With false nothing is stored and request_id cannot be looked up.