Amazon Rekognition
Amazon Rekognition is a cloud-based computer vision service that makes it easy to add image and video analysis to your applications, providing capabilities such as object and scene detection, facial analysis, face comparison, celebrity recognition, text detection, content moderation, custom labels, face liveness detection, and streaming video analysis using deep learning technology.
Reference-quality API operations across every facet — a rich contract, published governance, transparent operations, and machine-readable commercial terms.
API Evangelist profiles Amazon Rekognition the way a machine reads it — 167 machine-readable artifacts across 10 APIs, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.
Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — Amazon Rekognition scores 77.4/100 (exemplar), with a separate agent-readiness read of 81/100 (agent native). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.
Kin Score
This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.
Kin Score
How this is scored →scored 2026-07-27 · rubric v0.5
How we profile Amazon Rekognition
Each block below is one kind of artifact we hold for Amazon Rekognition. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.
APIs 10
Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.
Individual APIs this provider publishes, each with its own machine-readable definition.
Amazon Rekognition Celebrity Recognition API
Identify celebrities in images and videos.
Amazon Rekognition Content Moderation API
Detect inappropriate or explicit content.
Amazon Rekognition Custom Labels API
Train and use custom image classifiers.
Amazon Rekognition Face Collections API
Create and manage searchable face collections.
Amazon Rekognition Face Liveness API
Verify that a user is physically present during identity verification.
Amazon Rekognition Face Search API
Search for matching faces within collections.
Amazon Rekognition Facial Analysis API
Detect and analyze faces with detailed attributes.
Amazon Rekognition Image Analysis API
Detect labels, objects, scenes, and concepts in images.
Amazon Rekognition Stored Video Analysis API
Asynchronous analysis of videos stored in Amazon S3.
Amazon Rekognition Text Detection API
Detect and extract text from images and videos.
Scroll within the panel for all 10 ·
Postman Collections 1
A runnable collection turns the contract into something a developer can execute in seconds. We profile them because the fastest way to trust an API is to make a real call against it.
Ready-to-run Postman collections for exercising this provider's APIs.
Amazon Rekognition
POSTMANOpen Collections 1
Open, tool-agnostic collections carry the same runnable value as Postman without locking you to one client — the portable, forkable form of the same exercise.
Open, tool-agnostic API collections (OpenAPI-derived and Bruno).
Amazon Rekognition
OPEN COLLECTIONArazzo Workflows 11
Real integrations are rarely a single call. Arazzo describes the multi-step sequences — auth, then create, then confirm — so both a human and an agent can follow the choreography, not just the endpoints.
Multi-step API workflows described with the Arazzo specification.
Amazon Rekognition Celebrity Scene Context
Recognize celebrities in an image and then label the same image for scene context.
ARAZZOAmazon Rekognition Custom Labels and Moderate
Run a Custom Labels model on an image and then screen the same image for unsafe content.
ARAZZOAmazon Rekognition Detect then Compare Faces
Confirm a face exists in the source image, then compare it against every face in a target image.
ARAZZOAmazon Rekognition Enroll and Search a Face
Create a face collection, index a face into it, then search the collection by a query image.
ARAZZOAmazon Rekognition Face Liveness Session
Create a Face Liveness session, then poll for its results until a terminal status is reached.
ARAZZOAmazon Rekognition Label and Moderate an Image
Detect general labels in an image and then screen the same image for unsafe content.
ARAZZOAmazon Rekognition Quality Gated Enrollment
Detect a face and check its quality, then index it into a collection only when a face is present.
ARAZZOAmazon Rekognition Reuse or Create Collection then Enroll
List collections, branch to create the collection only if missing, then index a face into it.
ARAZZOAmazon Rekognition Text and Moderation Screen
Extract text from an image and then screen the same image for unsafe content.
ARAZZOAmazon Rekognition Verify a Face Against a Collection
Detect a face in an image to confirm a single subject, then search a collection to verify identity.
ARAZZOAmazon Rekognition Video Label Detection Job
Start an asynchronous video label detection job, poll until it succeeds, then read the results.
ARAZZOScroll within the panel for all 11 ·
MCP Servers 1
Model Context Protocol servers expose these APIs directly to AI agents. We profile them because agent-native access is the fastest-growing way this provider's capabilities actually get used.
Model Context Protocol servers that expose these APIs to AI agents.
amazon-rekognition-mcp.yml
MCP SERVERGraphQL 1
Where a provider ships GraphQL, the schema is the contract. We profile it alongside the REST surface so the whole interface is legible in one place.
GraphQL schemas published by this provider.
Amazon Rekognition GraphQL Schema
This directory contains a conceptual GraphQL schema for the Amazon Rekognition API. The schema is derived from the Amazon Rekognition REST API and its public documentation at ht...
GRAPHQLPricing Plans 1
Pricing is part of the interface. Machine-readable plans tell you what a tier costs and includes before you commit — one of the six things the Kin Score reads for commercial clarity.
Published pricing tiers and plan structures.
Rate Limits 1
Rate limits are the difference between a demo that works and a production integration that doesn't fall over. Publishing them is an operational-transparency signal — and a hard requirement for any agent that plans its own throughput.
Documented rate limits and quota policies.
Amazon Rekognition Rate Limits
RATE LIMITSFinOps 1
Cost, billing, and metering signals let a buyer model the financial operations of an API before it's live. We profile them for the same reason we profile pricing: the money is part of the contract.
Cost, billing, and metering signals for API financial operations.
Features 14
The notable capabilities this provider advertises, captured as structured features so they can be searched and compared instead of read one landing page at a time.
Notable capabilities this provider offers.
Object and Scene Detection
Detect thousands of objects, scenes, and concepts in images and videos with high confidence scores using deep learning.
Facial Analysis
Detect and analyze faces with attributes including age range, emotions, gender, and facial landmarks.
Face Comparison
Compare faces across images to determine if they are the same person with a similarity score.
Face Collections
Create searchable face collections to index and search millions of faces in near real-time.
Celebrity Recognition
Identify thousands of celebrities in images and videos across categories like sports, entertainment, and politics.
Text Detection
Detect and extract printed and handwritten text from images and videos in multiple languages.
Content Moderation
Detect explicit, inappropriate, or violent content in images and videos for automated content moderation.
Custom Labels
Build and train custom image classifiers using your own labeled images for domain-specific object detection.
Protective Equipment Detection
Detect personal protective equipment such as face covers, hand covers, and head covers on persons in images.
Face Liveness Detection
Verify that a user is physically present during identity verification to prevent spoofing attacks.
People Pathing
Track and follow identified people across frames in stored video footage.
Video Segmentation
Identify technical cues and segments such as black frames, end credits, and color bars in video content.
Streaming Video Analysis
Analyze live streaming video in real-time using Amazon Kinesis Video Streams integration.
Image Properties Analysis
Evaluate image quality attributes including sharpness, brightness, contrast, and dominant colors.
Scroll within the panel for all 14 ·
Semantic Vocabularies 1
JSON-LD contexts give the data shared meaning across APIs. We profile them because semantics are what let a machine reconcile 'customer' here with 'customer' somewhere else.
JSON-LD contexts and semantic vocabularies used across these APIs.
Amazon Rekognition Context
JSON-LDSpectral Rules 2
Governance rulesets we run against this provider's specs — the automated checks behind parts of the score. Profiling them makes the quality bar explicit and re-runnable, not a matter of opinion.
Amazon Rekognition API Rules
SPECTRALAmazon Rekognition API Rules
SPECTRALJSON Schema 36
Standalone JSON Schema definitions describe the data models behind the API. We profile them so the shapes are validatable on their own — useful long after a single request is forgotten.
Standalone JSON Schema definitions for this provider's data models.
BoundingBox
JSON SCHEMACompareFacesRequest
JSON SCHEMACompareFacesResponse
JSON SCHEMACreateCollectionRequest
JSON SCHEMACreateCollectionResponse
JSON SCHEMACreateFaceLivenessSessionRequest
JSON SCHEMACreateFaceLivenessSessionResponse
JSON SCHEMADetectCustomLabelsRequest
JSON SCHEMADetectCustomLabelsResponse
JSON SCHEMADetectFacesRequest
JSON SCHEMADetectFacesResponse
JSON SCHEMADetectLabelsRequest
JSON SCHEMADetectLabelsResponse
JSON SCHEMADetectModerationLabelsRequest
JSON SCHEMADetectModerationLabelsResponse
JSON SCHEMADetectTextResponse
JSON SCHEMADetectLabelsResponse
JSON SCHEMAFaceDetail
JSON SCHEMAGetFaceLivenessSessionResultsRequest
JSON SCHEMAGetFaceLivenessSessionResultsResponse
JSON SCHEMAGetLabelDetectionResponse
JSON SCHEMAGetVideoJobResultRequest
JSON SCHEMAImageOnlyRequest
JSON SCHEMAImage
JSON SCHEMAIndexFacesRequest
JSON SCHEMAIndexFacesResponse
JSON SCHEMALabel
JSON SCHEMAListCollectionsResponse
JSON SCHEMANotificationChannel
JSON SCHEMARecognizeCelebritiesResponse
JSON SCHEMAS3Object
JSON SCHEMASearchFacesByImageRequest
JSON SCHEMASearchFacesByImageResponse
JSON SCHEMAStartLabelDetectionRequest
JSON SCHEMAStartVideoJobResponse
JSON SCHEMAVideo
JSON SCHEMAScroll within the panel for all 36 ·
JSON Structure 36
JSON Structure captures the data shapes in a form built for tooling — a complement to JSON Schema that keeps the model machine-legible.
JSON Structure definitions describing this provider's data shapes.
Amazon Rekognition Bounding Box Structure
JSON STRUCTUREAmazon Rekognition Compare Faces Request Structure
JSON STRUCTUREAmazon Rekognition Compare Faces Response Structure
JSON STRUCTUREAmazon Rekognition Create Collection Request Structure
JSON STRUCTUREAmazon Rekognition Create Collection Response Structure
JSON STRUCTUREAmazon Rekognition Detect Faces Request Structure
JSON STRUCTUREAmazon Rekognition Detect Faces Response Structure
JSON STRUCTUREAmazon Rekognition Detect Labels Request Structure
JSON STRUCTUREAmazon Rekognition Detect Labels Response Structure
JSON STRUCTUREAmazon Rekognition Detect Text Response Structure
JSON STRUCTUREAmazon Rekognition Detectlabelsresponse Structure
JSON STRUCTUREAmazon Rekognition Face Detail Structure
JSON STRUCTUREAmazon Rekognition Image Only Request Structure
JSON STRUCTUREAmazon Rekognition Image Structure
JSON STRUCTUREAmazon Rekognition Index Faces Request Structure
JSON STRUCTUREAmazon Rekognition Index Faces Response Structure
JSON STRUCTUREAmazon Rekognition Label Structure
JSON STRUCTUREAmazon Rekognition List Collections Response Structure
JSON STRUCTUREAmazon Rekognition Notification Channel Structure
JSON STRUCTUREAmazon Rekognition S3 Object Structure
JSON STRUCTUREAmazon Rekognition Start Video Job Response Structure
JSON STRUCTUREAmazon Rekognition Video Structure
JSON STRUCTUREScroll within the panel for all 36 ·
Examples 36
Real request and response payloads are what turn a spec from abstract into obvious — and they're one of the twelve things an agent needs to call an API correctly on the first try.
Example request and response payloads for these APIs.
Scroll within the panel for all 36 ·
Security Posture 4
Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access 1
An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.
Recommended x-agentic-access execution contracts for AI agents.
Use Cases 9
What developers actually build with this provider — captured so the catalogue answers 'what is this for', not just 'what does this expose'.
What developers build with this provider.
Identity Verification
Verify user identities by comparing selfies to ID documents or previously stored face images for onboarding and authentication.
Content Moderation
Automatically moderate user-generated content on platforms to detect and filter explicit or inappropriate imagery.
Searchable Media Libraries
Build searchable image and video archives by automatically tagging media with detected labels, faces, and text.
Workplace Safety Compliance
Monitor camera feeds to detect whether workers are wearing required personal protective equipment in industrial settings.
Fraud Prevention
Prevent identity fraud during digital onboarding by using face liveness detection to confirm real users.
Smart Retail Analytics
Analyze in-store camera feeds to track customer behavior, measure foot traffic, and optimize product placement.
Public Safety and Security
Search video archives for persons of interest by comparing faces against a known collection.
Media and Entertainment
Automatically tag celebrities in photos and videos for media companies to improve content discoverability.
Custom Object Detection
Train custom classifiers to detect proprietary products, logos, brand assets, or industry-specific objects.
Scroll within the panel for all 9 ·
Resources
Every other property we hold for Amazon Rekognition — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.
Get Started 4
Portal, sign-up, and the first successful call
Documentation 37
Reference material describing how the API behaves
Scroll within the panel for all 37 ·
Agent Surfaces 4
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 56
Pagination, idempotency, versioning, errors, and events
Scroll within the panel for all 56 ·
Build 40
SDKs, sample code, and the tooling you integrate with
Scroll within the panel for all 40 ·
Access & Security 7
Authentication, authorization, and security posture
Scroll within the panel for all 7 ·
Learn 1
Tutorials, courses, talks, and written guidance
Operate 6
Status, limits, changes, and where to get help
Commercial 3
Pricing, plans, and the legal terms of use
Company 1
The organization behind the API
Other 2
Properties that don't map to a standard resource type
← All providers · Data indexed from github.com/api-evangelist/amazon-rekognition · machine-readable index on apis.io