Face++

Face++ is a computer vision platform that gives developers APIs and SDKs for face analysis and other image tasks. It best suits teams adding identity checks or several vision capabilities to an application. Its broad toolkit is appealing, though free API throughput is shared and the Landmark SDK trial lasts only one day.

Overview

Face++ brings face analysis together with tools for body and skeleton recognition, gestures, OCR, image beautification, and photo album clustering. That range can be useful when one application needs several kinds of image processing. Teams looking for a single, narrowly focused or self-hosted model may find a better fit elsewhere.

Its use cases include identity verification, eKYC and passport matching, ride-hailing driver checks, biometric retail payments, and skin analysis. Liveness detection is designed to distinguish a live face from a photo, video, or mask, adding a check against spoofing in face-based workflows.

Key features

Face analysis and liveness

Face capabilities include detection, one-to-one comparison, one-to-many search, facial landmarks, and attributes. Together, these can support workflows that verify a claimed identity or search a collection for a matching face. Liveness adds a separate check for spoofing attempts, making it relevant to identity flows that use face recognition.

On-device landmarking

The Face Landmark SDK can perform face detection, tracking, and landmarking locally on Android and iOS devices. Local processing may suit mobile applications that need those tasks on-device. The SDK trial allows one day of authorized online licensing, with up to five authorizations per day, so it offers a short evaluation window.

Integration and privacy

Face++ provides technical support for integration, API issues, and troubleshooting. Its privacy policy describes the handling of personal information under MEGVII’s policy, including collection, use, retention, disclosure, protection, and global transfers. The policy was last updated on September 30, 2020.

Pricing

Face++ uses a freemium model. The Free plan costs nothing and includes free API access with one API key. Free-key QPS limits vary by API group: facial recognition APIs share a total limit of 3 QPS, while Dense Facial Landmarks API is limited separately to 1 QPS. Those caps can constrain evaluation or low-volume deployments that need predictable request capacity.

The Daily/Monthly Plan uses prepay for future usage by QPS capacity, measured in queries or requests per second, with custom pricing. It suits teams that need to reserve request capacity. Pay As You Go uses top-ups and usage-based billing, also with custom pricing, for teams that prefer charges tied to consumption. SDK licensing has custom pricing by license period or license number, with options for the Face Landmark SDK and Face Compare SDK. The free API access is the lowest-cost way to begin, but it does not remove the shared request-rate limits; the SDK trial is short and capped by daily authorizations.

Platforms

The platform lists Android, API, iOS, macOS, web, and Windows. The Face Landmark SDK supports Android, iOS, Windows, and Mac, with local face detection, tracking, and landmarking on mobile devices.

Who it's for

Face++ fits developers and product teams building face-based identity checks or applications that combine facial analysis with other vision tasks. It is especially relevant when API access, mobile landmarking, and functions such as OCR or gesture recognition belong in the same product. Teams with strict throughput needs should weigh the free QPS limits against the custom-priced capacity plans.

Pros and cons

• Pros: Face detection, comparison, search, landmarks, attributes, and liveness cover several parts of a face-based identity workflow.
• Pros: The wider set of vision functions, including OCR, body and skeleton recognition, and gestures, can serve products with needs beyond faces.
• Pros: Local Landmark SDK processing supports mobile detection, tracking, and landmarking on Android and iOS.
• Cons: The free API key has shared QPS limits, including 3 total for facial recognition APIs and a separate limit of 1 for Dense Facial Landmarks.
• Cons: The SDK trial provides only one day of authorized online licensing and allows up to five authorizations per day.
• Cons: Capacity, usage, and SDK license plans have custom pricing, making costs harder to assess before contacting Face++.

Alternatives

Compare AI image recognition software if you want to consider more tools in this category.

• MediaPipe is a free option for teams seeking on-device machine learning solutions and a framework across mobile, desktop, web, and self-hosted platforms.
• Sighthound AI may fit buyers seeking a paid option with a free plan, a 24-hour hosted tier for one user and up to two minutes, and a Pro plan priced at $2,500 a year.
• Google Cloud Vision API is another freemium API option, with pay-as-you-go image billing and a free allowance for the first 1,000 units.
• CompreFace suits teams looking for a free, open-source, Docker-based option with CPU and GPU support.
• InsightFace may suit research or non-commercial projects seeking open-source tools; commercial model use requires a separate license.
• LandingLens is a freemium alternative with a free monthly plan that includes 1,000 credits, three users, and one active project.
• Roboflow offers a free tier with 10 credits a month and a Core plan at $39 a month.
• Yandex Vision OCR is a paid option for teams focused on OCR, with printed text recognition charged per image or PDF page.

Verdict

Choose Face++ if your product needs several vision functions alongside face recognition, or if local mobile landmarking is part of the plan. Its range and combination of APIs with SDKs are the main reasons to choose it. Look elsewhere if you need a longer SDK evaluation or free API capacity beyond the shared QPS limits.