canonical: https://jentic.com/apis/facecheck.id/facecheck # Facecheck Id Facial Recognition Reverse Image Face Search API FaceCheck.ID is a reverse image face search API that lets applications upload a photo and find matching faces across publicly indexed sources on the open web. The service is built around four operations: upload a probe image, trigger a search, poll for the result, and delete the uploaded photo when finished. It is commonly used in OSINT investigations, scam detection, dating-site verification, and person-of-interest workflows where a face image is the only available identifier. ## For AI agents Search the open web for matching faces from a probe photo and retrieve ranked match URLs with confidence scores. Useful for identity verification, scam detection, and OSINT lookups. ## Scope Does not handle document verification, liveness checks, or KYC compliance - use for reverse face search across publicly indexed images only. ## Capabilities - Upload a probe face image and receive an upload identifier for downstream search - Run a reverse face search across the indexed open-web image corpus - Poll for a queued search result and retrieve ranked matches with confidence scores - Inspect upload metadata to confirm a photo was processed correctly before searching - Delete a previously uploaded photo to remove it from the queue ## Use cases ### Romance Scam Detection Investigate whether a profile photo from a dating or social platform appears on known scam, catfish, or stolen-image sites. The API uploads the probe image, runs a reverse search across the open-web index, and returns ranked URLs with confidence scores so a reviewer can decide whether the profile is genuine. Typical end-to-end latency is under a minute for a single probe. Example prompt: Upload the suspected scam profile photo to `/api/upload_pic`, call `/api/search` with the returned id_search, poll until status is complete, and return the top five match URLs with their score values. ### OSINT Person-of-Interest Lookup Investigators with a single face photo and no name can search the open web for sources that contain the same face, surfacing social media profiles, news articles, and forum posts. The four-call flow covers upload, search, info, and delete, allowing a clean session that does not retain the probe image after the lookup. Suited to low-volume manual investigations rather than mass enrichment. Example prompt: Upload the probe face image, run `/api/search`, collect the ranked URL list, and call `/api/delete_pic` to remove the uploaded photo when the search completes. ### AI Agent Identity Triage An AI agent fielding an investigative query receives a face image and needs to surface candidate sources for a human reviewer. Through Jentic, the agent calls the Jentic search index for 'reverse image face search', loads the FaceCheck operation schema, and executes the four-step upload-search-info-delete flow without holding the API key in its context. Useful when face search is one tool among many in a wider research workflow. Example prompt: Call jentic.search with query 'reverse image face search', load the upload_pic and search operations, execute them in sequence with the supplied photo, and return ranked matches above a 70 score threshold. ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | `/api/upload_pic` | Upload a probe face image | | POST | `/api/search` | Trigger a reverse face search and retrieve ranked matches | | POST | `/api/info` | Get upload metadata for a probe image | | POST | `/api/delete_pic` | Delete a previously uploaded probe image | ## Key resources - **Upload** — Submit a probe face image and receive an id_search identifier for downstream operations - **Search** — Trigger a reverse face search and retrieve ranked match URLs with confidence scores - **Info** — Inspect upload state and metadata for a queued probe image ## Why Jentic - **Setup:** Wiring the FaceCheck.ID API by hand means placing its token in the Authorization header, targeting the facecheck.id host, and sequencing the upload-then-search calls yourself. Through Jentic you install once, import the FaceCheck.ID API from the API Directory, store the token once, and your agent calls it. - **Permission scoping:** FaceCheck.ID carries the image reference in the request body rather than a resource id in the path, so you limit the agent to the operations it needs, such as uploading a picture and running a search. You choose those operations, so the delete-picture call is not included unless you add it. - **Credential handling:** Your FaceCheck.ID token is stored once, encrypted, by your own Jentic One instance and injected as the Authorization header at execution time. It never enters the agent's prompt, logs, or context. - **Discovery method:** Agents search Jentic by intent such as 'reverse image face search', and Jentic returns the FaceCheck operations with their input schemas so the agent calls upload_pic and search in order without browsing the facecheck.id docs. ## Related APIs - **Onfido** — Document and biometric identity verification rather than open-web face search - **Veriff** — Full identity verification platform with document and liveness checks - **FullContact** — Enrich a matched face URL with associated person and contact data ## FAQ ### What authentication does the FaceCheck.ID API use? FaceCheck.ID uses an API token passed in the Authorization header under the Bearer apiKey scheme. Through Jentic, the token is stored encrypted in the vault and never enters the agent's context - the agent receives a scoped execution permission instead of the raw key. ### Can I run a reverse face search with the FaceCheck.ID API? Yes. The flow is to POST a probe image to `/api/upload_pic`, call `/api/search` with the returned id_search to queue the lookup, and poll the same endpoint until the search completes and ranked URLs with score values are returned. ### What are the rate limits for the FaceCheck.ID API? The OpenAPI spec does not declare numeric rate limits. FaceCheck enforces credit-based pricing per search rather than per-second quotas, so plan limits scale with the credits attached to the API token. ### How do I run a face search with the FaceCheck.ID API through Jentic? Run pip install jentic, then call jentic.search with the query 'reverse image face search'. Load the upload_pic operation schema, execute it with the probe image, then load and execute the `/api/search` operation with the returned id_search to retrieve the ranked match list. ### How do I remove an uploaded photo from FaceCheck.ID? Call POST `/api/delete_pic` with the id_search returned by the upload step. This removes the probe image from the queue and is the recommended cleanup step at the end of an investigation session. ### Is the FaceCheck.ID API free? FaceCheck.ID operates on a paid credit model - searches consume credits attached to the API token. A limited free tier is available for testing the upload and search flow. Get started with Jentic One, the self-hosted execution layer. ### Can I limit what my agent is allowed to do with the FaceCheck.ID API? Yes. Because you run Jentic One yourself, your own rules decide which FaceCheck.ID operations the agent may call and which credentials it may use. FaceCheck.ID carries the probe image in the request body rather than a resource id in the path, so you can grant only the operations a task needs, such as upload_pic and search, while leaving out info or delete_pic. The token is injected at execution time and never enters the agent's context, so the agent can only run the operations you allow.