Skip to main content
Didit 融资 750 万美元，打造身份与欺诈基础设施
Didit
无人商店验证

在门口验证购物者。打开购物篮。阻止受限 SKU。

首次访问 $0.33，每次回访 $0.10, 门口人脸识别，按类别强制执行年龄限制，无需人工。每月免费 500 次验证。

免费开始阅读文档
投资方
Y CombinatorRobinhood Ventures
GBTC Finance
Bondex
Crnogorski Telekom
UCSF Neuroscape
Shiply
Adelantos

全球2,000多家组织信赖。

一张电影般的深色抽象无人商店入口插图, 四个浮动的半透明玻璃面板以 3D 透视效果呈现在纯黑色背景上，由一条发光的 Didit 蓝色线条串联，并由四个发光的扫描支架框住。每个面板都带有一个微小的浅白色抽象图案，代表无人零售入口（门拱、带支架的人脸椭圆形、年龄门日历、购物篮）。

无人零售的合规义务

无需店员。无需员工。每次入店依然合规。

无人便利店、自助售货亭、智能冰箱、无人加油站, 它们都与有人值守商店承担相同的合规义务：真实身份、真实年龄、真实 审计追踪。Didit 将其整合为一个工作流程：首次访问 $0.33，每次 回访 $0.10，中位判决时间低于 2 秒，支持 220 多个国家/地区的 14,000 多种证件。

工作原理

从注册到验证用户，仅需四步。

  1. 步骤 01

    创建工作流程

    选择您需要的检查项, 身份、活体、人脸匹配、制裁名单、地址、年龄、电话、电子邮件、自定义问题。在仪表盘中将它们拖入流程，或将相同的流程发布到我们的 API。根据条件分支，运行 A/B 测试，无需代码。

  2. 步骤 02

    集成

    通过我们的 Web、iOS、Android、React Native 或 Flutter SDK 进行原生嵌入。重定向到托管页面。或者直接通过电子邮件、短信、WhatsApp 等任何方式向您的用户发送链接。选择适合您技术栈的方式。

  3. 步骤 03

    用户完成流程

    Didit 负责托管摄像头、灯光提示、移动设备切换和辅助功能。在用户进行流程时，我们实时评估 200 多个欺诈信号，并根据权威数据源验证每个字段。两秒内即可获得结果。

  4. 步骤 04

    您接收结果

    实时签名 Webhook 可确保用户获批、拒绝或发送审核时，您的数据库即时同步。按需轮询 API。或者打开控制台检查每个会话、每个信号，并按您的方式管理案例。

专为无人零售打造 · 基础设施级定价

六个基本功能。$0.33 首次访问，每次回访 $0.10。

无人零售合规并非单一检查，而是一套组合拳。首次访问进行 KYC，每次回访识别人脸，按区域按 SKU 强制执行年龄限制，并对每次尝试进行签名。
阅读文档获取 API 密钥
01 · 入场流程

扫描、验证、解锁。

首次访问捆绑包, 身份验证、被动活体检测、1:1 人脸比对，以及根据验证后的出生日期计算的年龄。通过 iBeta Level 1 反欺诈认证，支持 220 多个国家/地区的 14,000 多种证件。
用户验证模块
02 · 年龄门禁

按类别、按区域设置年龄门槛。

欧盟地区酒类 18 岁/美国地区 21 岁，烟草按州规定，电子烟 18 岁/21 岁，部分欧盟国家功能饮料 16 岁，锋利工具 18 岁，处方药需药房交接。在服务器端强制执行，绝不在自助服务机上执行。
年龄验证解决方案
03 · 回访购物者

刷脸进门。无需手机。

生物识别认证，每次进入 $0.10, 购物者将脸部对准门禁摄像头，门随即解锁。平均耗时 1.4 秒。您的所有门店均可使用同一身份。
生物识别认证
04 · 签名尝试日志

每次进入均签名并记录。

时间戳、门店 ID、购物者 PID（假名标识符）、年龄判定、X-Signature-V2 HMAC SHA-256, 每次尝试一条记录，可导出至您的防损仪表板或州监管门户。默认保留 5 年。
Webhooks 文档
05 · 分类 × 区域 · 时间

无需重新部署门店操作系统即可实现本地规则。

在禁酒县禁止销售酒类，限制夜间销售，对电子烟 SKU 要求州许可证，将处方药路由至合作药房后端。在无代码工作流构建器中按门店编辑。
工作流编排器
06 · 生态系统

接入门店操作系统、POS、支付堆栈。

Webhooks 接入您的门店操作系统，POS 在扫描时阻止受限 SKU，智能售货机仅在年龄验证后才打开货道，防损仪表板接收所有签名尝试。
1:1 人脸比对模块
集成

首次访问一次会话。每次回访生物识别。

开启入场会话。读取签名判决。解锁门禁。在每次后续访问中识别人脸。
POST /v3/session/首次访问
$ curl -X POST https://verification.didit.me/v3/session/ \
  -H "x-api-key: $DIDIT_API_KEY" \
  -d '{
    "workflow_id": "wf_store_entry_kyc",
    "vendor_data": "shopper-42",
    "metadata": { "store_id": "store_sf_12" }
  }'
201已创建返回托管会话 URL。
保持门锁闭，直到 webhook 返回 status: Approved。文档 →
POST /v3/session/返回
$ curl -X POST https://verification.didit.me/v3/session/ \
  -H "x-api-key: $DIDIT_API_KEY" \
  -d '{
    "workflow_id": "wf_store_entry_biometric",
    "vendor_data": "shopper-42",
    // base64 first-visit selfie, ≤ 1MB (omit for liveness-only)
    "portrait_image": "/9j/4AAQSkZJRgABAQE..."
  }'
201已创建生物识别认证 $0.10 · 门在约 1.4 秒内打开。
相同的 Sessions API。仅限生物识别认证工作流。文档 →
代理就绪集成

一键部署无人商店入口。

粘贴到 Claude Code、Cursor、Codex、Devin、Aider 或 Replit Agent 中。填写您的技术栈。Agent 将构建两个工作流，连接门禁控制器 webhook，并在结账时执行 SKU 规则。
didit-integration-prompt.md
You are integrating Didit into an autonomous-retail surface — an unstaffed convenience store, an age-gated vending machine, a smart fridge, an autonomous fuel station, or a self-checkout that handles restricted SKUs. The recipe verifies identity + age at entry and authenticates returning shoppers via face only.

Three pillars:

  1. First visit — verify the shopper's identity and age with one POST /v3/session/ ($0.33 bundle).
  2. Returning visit — Biometric Authentication at $0.10 per entry. Shopper holds their face to the door camera; door unlocks.
  3. Per-SKU enforcement — block restricted categories (alcohol, tobacco, vapes, energy drinks, RX) at scan or checkout based on the verified age and the store's local rules.

Cost:
  - First visit KYC bundle: $0.33 per shopper (Sessions API)
  - Returning visit Biometric Auth: $0.10 per entry
  - First 500 verifications free every month, forever

PRE-REQUISITES
  - Production API key from https://business.didit.me (sandbox key in 60s, no card).
  - Webhook endpoint with HMAC SHA-256 verification using the X-Signature-V2 header and your webhook secret.
  - Two workflows in the Workflow Builder:
      wf_store_entry_kyc      — ID Verification + Passive Liveness + Face Match 1:1 + age rules (first visit)
      wf_store_entry_biometric — Biometric Auth-only (returning visit)
  - A store-id + local-rule lookup so age thresholds vary per region (EU 18 vs US 21 for alcohol; state-by-state tobacco; dry counties; etc.).

STEP 1 — First visit: verify the shopper

  POST https://verification.didit.me/v3/session/
  Headers:
    x-api-key: <your api key>
    Content-Type: application/json
  Body:
    {
      "workflow_id": "<wf_store_entry_kyc>",
      "vendor_data": "<your shopper id, max 256 chars>",
      "callback": "https://<your-app>/store/entry/callback",
      "metadata": {
        "purpose": "autonomous_store_entry",
        "store_id": "<your store id>",
        "region": "<US-CA | EU-ES | etc.>"
      }
    }

  Response: 201 Created with the hosted session URL. Encode that URL in the QR sticker on the door (or push it to the shopper's phone via SMS / WhatsApp). Sub-2-second median verdict on completion.

STEP 2 — Read the signed webhook on entry-flow completion

  Didit POSTs to your callback. Session statuses are Title Case With Spaces:

  Body (excerpted):
    {
      "session_id": "<uuid>",
      "vendor_data": "<your shopper id>",
      "status": "Approved",
      "id_verification": {
        "status": "Approved",
        "date_of_birth": "1991-04-22",
        "country": "US"
      },
      "liveness": { "status": "Approved" },
      "face": { "status": "Approved", "similarity_score": 0.94 }
    }

  Status enum (exact case): Approved | Declined | In Review | Resubmitted | Expired | Not Finished | Kyc Expired | Abandoned.

  Verify the X-Signature-V2 header BEFORE reading the body — HMAC SHA-256 of the raw bytes with your webhook secret.

  Compute the age from date_of_birth, look up the region's age thresholds (per category), and store the (shopper_id, age_band, region, kyc_status) tuple in your data layer.

STEP 3 — Open the door

  When status is Approved, signal your store-OS / door-controller to unlock. Median wall-clock from QR scan to door open is around 1.4 seconds on entry-level Android, sub-2 seconds end to end.

  Failure modes to handle:
    Declined / In Review / Resubmitted — show a friendly UI on the kiosk and offer staff hand-off.
    Expired / Abandoned — shopper walked away; do nothing, the session expires.

STEP 4 — Returning visit: Biometric Authentication

  POST https://verification.didit.me/v3/session/
  Body:
    {
      "workflow_id": "<wf_store_entry_biometric>",
      "vendor_data": "<your shopper id>",
      "metadata": {
        "purpose": "autonomous_store_entry_return",
        "store_id": "<your store id>"
      }
    }

  The shopper just holds their face to the door camera. Cost is $0.10 per entry. Same webhook flow.

STEP 5 — Read the decision on demand

  GET https://verification.didit.me/v3/session/{sessionId}/decision/
  Headers:
    x-api-key: <your api key>

  Returns the full decision JSON. Use this from the POS / self-checkout when the shopper picks up a restricted SKU — confirm age + region match the SKU's rules before letting the basket close.

STEP 6 — Per-SKU enforcement at checkout

  Inside your POS / store-OS, every restricted SKU carries a category tag (alcohol, tobacco, vape, energy-drink, sharp-tool, RX). Look up the shopper's verified age band + the store's region rules. Examples:

    Alcohol            US-21 / EU-18, blocked in dry counties, time-of-day windows
    Tobacco / vapes    US-21 (state by state) / EU-18, store-licence flag required
    Energy drinks      EU-16 in some regions, no restriction elsewhere
    Sharp tools        ≥ 18 in most regions
    Prescription       Pharmacy hand-off only (DEA Schedule II–V)

  Tune the policy in the no-code Workflow Builder — no redeploy of your store-OS.

WEBHOOK EVENT NAMES
  - Sessions: status changes flow through the standard session webhook.
  - Verify X-Signature-V2 on every payload.

CONSTRAINTS
  - Session statuses use Title Case With Spaces (Approved, In Review). Don't transform them.
  - Don't store the raw document image in your store-OS — Didit holds it, the store-OS holds the shopper PID + age band only.
  - Compute the age band server-side, not in the kiosk — kiosks can be tampered with.
  - Log every entry attempt (Approved + Declined) signed with X-Signature-V2 for the loss-prevention dashboard. Default retention 5 years.

Read the docs:
  - https://docs.didit.me/sessions-api/create-session
  - https://docs.didit.me/sessions-api/retrieve-session
  - https://docs.didit.me/integration/webhooks
  - https://docs.didit.me/console/workflows

Start free at https://business.didit.me — sandbox key in 60 seconds, 500 verifications free every month, no credit card.
需要更多上下文？请参阅完整的模块文档。docs.didit.me →
合规性设计

一键开启新国家/地区业务。 我们为您解决难题。

我们负责设立当地子公司、获取许可证、进行渗透测试、获得认证，并与所有新法规保持一致。要在新国家/地区发布验证服务，只需轻点开关。已覆盖220多个国家/地区，每个季度进行审计和渗透测试, 是唯一一个被欧盟成员国政府正式认定比线下验证更安全的身份提供商。
阅读安全与合规性档案
欧盟金融沙盒
Tesoro · SEPBLAC · BdE
ISO/IEC 27001
信息安全 · 2026
SOC 2 · Type I
AICPA · 2026
iBeta Level 1 PAD
NIST / NIAP · 2026
GDPR
EU 2016/679
DORA
EU 2022/2554
MiCA
EU 2023/1114
AMLD6 · eIDAS 2.0
原生符合欧盟标准

数据证明

数据证明
  • $0.00
    首次访问 KYC 套餐。之后每次回访通过生物识别认证 $0.10。
  • ~1.4s
    从门口人脸识别到门解锁的平均实际时间。
  • 0+
    支持 220 多个国家/地区的证件类型, 适用于任何商店的所有客流量。
  • 0
    每个账户每月免费验证。
三个层级，一份价目表

免费开始。按使用量付费。可扩展至企业级。

每月 500 次免费验证，永久有效。生产环境按量付费。企业版提供定制合约、数据驻留和 SLA (Service Level Agreements)。
免费

免费

每月 $0。无需信用卡。

  • 免费 KYC 套件（身份验证 + 被动活体检测 + 人脸匹配 + 设备与 IP 分析）, 每月 500 次，永久有效
  • 黑名单用户
  • 重复检测
  • 每次会话 200+ 欺诈信号
  • Didit 网络中可重复使用的 KYC
  • 案件管理平台
  • 工作流构建器
  • 公开文档、沙盒、SDK、MCP（模型上下文协议）服务器
  • 社区支持
免费开始
最受欢迎
按用量付费

按用量计费

按实际用量付费。25+模块。公开的模块定价，无每月最低费用。

  • 完整KYC $0.33（身份+生物识别+IP/设备）
  • 10,000+ AML数据集, 制裁、PEP、负面媒体
  • 1,000+ 政府数据源用于数据库验证
  • 交易监控 $0.02/笔交易
  • 实时KYB $2.00/家企业
  • 钱包筛选 $0.15/次检查
  • 白标验证流程, 您的品牌，我们的基础设施
查看完整价格列表免费开始
企业版

企业版

定制MSA和SLA。适用于大批量和受监管项目。

  • 年度合同
  • 定制MSA、DPA和SLA
  • 专属Slack和WhatsApp频道
  • 按需人工审核员
  • 经销商和白标条款
  • 独家功能和合作伙伴集成
  • 指定CSM、安全审查、合规支持
联系我们

免费开始 → 仅在检查运行时付费 → 解锁企业版以获取定制合约、SLA 或数据驻留。

FAQ

常见问题

What is Didit?

Didit is infrastructure for identity and fraud, the platform we wished existed when we were building products ourselves: open, flexible, and developer-friendly, so it works as a real part of your stack instead of a black box you integrate around.

One API covers verifying people (KYC, know your customer), verifying businesses (KYB, know your business), screening crypto wallets (KYT, know your transaction), and monitoring transactions in real time, on a stack built to be:

  • Fast, sub-2-second p99 on every session
  • Reliable, in production with 1,500+ companies across 220+ countries
  • Secure, SOC 2 Type 1, ISO 27001, GDPR-native, and formally attested by Spain's financial regulator as safer than verifying someone in person

The footprint underneath: 14,000+ document types in 48+ languages, 1,000+ data sources, and 200+ fraud signals on every session. The Didit infrastructure dynamically learns from every session and gets better every day.

What's autonomous-store entry verification, in plain English?

It's the identity + age check that lets an unstaffed store open its door to a real, eligible shopper, and refuse everyone else, without a human clerk in the loop.

The pattern shows up wherever retail goes staffless:

  • Grab-and-go convenience stores (think Amazon-Go-style, Aldi Shop&Go, REWE Pick&Go, Polish Żabka Nano)
  • Smart fridges in offices, gyms, hospitals, airports
  • Vending pods for tobacco, alcohol, vapes, energy drinks, pharmacy SKUs
  • Autonomous fuel stations with self-pump alcohol-sales counters
  • Ghost kitchens with self-pickup lockers
  • Self-checkout that handles restricted categories

The shopper scans a QR or holds their face to the door camera. Didit verifies who they are and how old they are. The door opens. The basket starts. The POS blocks anything they're not allowed to buy.

Why can't the store just use a card check or a phone number?

Because neither proves a real human with a real age.

  • A card proves a payment instrument, not the cardholder's identity. Stolen cards, gift cards, family cards all pass.
  • A phone number proves a SIM, not a face. SIM farms and shared phones break it instantly.
  • An age self-declaration is the worst, it's the legal-fiction version of asking the shopper to swear they're 21.

Underage purchase of alcohol, tobacco, and vapes is regulated in every developed market, the US (state by state, with strict liability), the EU (Tobacco Products Directive + national alcohol laws), the UK (Licensing Act 2003), Canada, Australia, Japan, Singapore. Penalties run from per-store fines to licence revocation. A real ID + face check is the only durable defence.

How fast is the verification for my end user?

The full flow normally takes under 30 seconds end-to-end, pick up the ID, snap the document, snap the selfie, done. That is the fastest in the market. Legacy KYC providers usually take more than 90 seconds for the same flow.

On the back end, Didit returns the result in under two seconds at p99, measured from the moment the user finishes the selfie to the moment your webhook fires. Mobile capture is tuned for slow phones and slow networks: progressive image compression, lazy software development kit load, and a one-tap hand-off from desktop to phone via QR code if the user starts on web.

Per-region age rules are a nightmare. How do you handle them?

By keeping the rules server-side, not in the kiosk. The verified date of birth comes back from /v3/session/; the rule table lives in your Workflow Builder.

Typical thresholds in scope:

  • Alcohol, EU 18, US 21 (federal floor), some EU states 16 for beer/wine, dry counties block entirely
  • Tobacco, US 21 federal (Tobacco 21 Act), state-by-state vape rules, EU 18
  • Energy drinks, EU 16 in several states (e.g. Lithuania, Latvia), unrestricted elsewhere
  • Sharp tools / knives, UK 18 (Offensive Weapons Act 2019), most US states 18
  • Prescriptions, pharmacy hand-off only, never sold from an unstaffed pod (DEA Schedule II–V controls)

Edit the rules per store, per SKU, per time-of-day in the no-code Workflow Builder. No redeploy of the store-OS. The POS reads the latest policy at scan time.

What happens if a user fails, abandons, or expires?

Every session lands on one of seven clear statuses, so your code always knows what to do:

  • Approved, every check passed. Move the user forward.
  • Declined, one or more checks failed. You can allow the user to resubmit the specific failed step (for example, re-take the selfie) without re-running the whole flow.
  • In Review, flagged for compliance review. Open the case in the console, see every signal, decide approve or decline.
  • In Progress, user is mid-flow.
  • Not Started, link sent, user has not opened it yet. Send a reminder if it sits too long.
  • Abandoned, user opened the link but did not finish in time. Re-engage or expire.
  • Expired, the session link aged out. Create a new session.

A signed webhook fires on every status change, so your database always stays in sync. Abandoned and declined sessions are free.

Where does my customer data live and how is it protected?

Production data is processed and stored in the European Union by default, on Amazon Web Services. Enterprise contracts can request alternative regions for jurisdictions whose regulators require it.

Encryption everywhere. AES-256 at rest across every database, object store, and backup. Transport Layer Security 1.3 in transit on every API call, webhook, and Business Console session. Biometric data is encrypted under a separate Customer Master Key.

Retention is yours to control. Default retention is indefinite (unlimited) unless you configure shorter, between 30 days and 10 years per application, and you can delete any individual session at any time from the dashboard or the API.

Certifications: SOC 2 Type 1 (Type 2 audit in progress), ISO/IEC 27001:2022, iBeta Level 1 PAD, and a public attestation from Spain''s Tesoro / SEPBLAC / CNMV that Didit''s remote identity verification is safer than verifying someone in person. Full report at /security-compliance.

Is Didit compliant for my industry?

Didit ships compliant by default for the regulators that matter to identity infrastructure:

  • GDPR + UK GDPR, controller / processor split, full Data Processing Agreement published, lead supervisory authority named (Spain''s AEPD).
  • AMLD6 + EU AML Single Rulebook, 1,300+ sanctions, politically exposed person, and adverse-media lists screened in real time.
  • eIDAS 2.0, EU Digital Identity Wallet aligned; reusable-identity ready.
  • MiCA (Markets in Crypto-Assets), ready for crypto on-ramps, exchanges, and custodians.
  • DORA, Digital Operational Resilience Act, EU financial-services operational resilience.
  • BIPA, CUBI, Washington HB 1493, CCPA / CPRA, US biometric privacy (Illinois, Texas, Washington) and California consumer privacy.
  • UK Online Safety Act, age-gating and child-safety obligations.
  • FATF Travel Rule, originator and beneficiary data on crypto transfers, IVMS-101 interoperable.

Detailed memo, every certificate, every regulator letter: /security-compliance.

How fast can I integrate and start verifying users?
  • 60 seconds to a sandbox account at business.didit.me, no credit card.
  • 5 minutes to a working verification through Claude Code, Cursor, or any coding agent via our Model Context Protocol (MCP) server.
  • A weekend to a production-ready integration with signed-webhook verification, retries, and a remediation flow when a user is declined.

Three integration paths, pick whichever fits your stack:

  • Embed natively with our Web, iOS, Android, React Native, or Flutter SDK.
  • Redirect the user to the hosted verification page, zero SDK.
  • Send a link by email, SMS, WhatsApp, or any channel, zero front-end work.

Same dashboard, same billing, same pay-per-success price for all three. Step-by-step guide at docs.didit.me/integration/integration-prompt.

What does the loss-prevention audit pack look like?

Every entry attempt, Approved, Declined, In Review, produces a signed log line:

  • session_id, Didit's verifiable identifier for the attempt
  • shopper_pid, your pseudonymous shopper id
  • store_id, which store / pod / fridge
  • timestamp, entry time in UTC
  • age_decision, verdict + threshold matched (e.g. Approved · 21+)
  • signature, X-Signature-V2 HMAC SHA-256 of the payload

Pipe to your loss-prevention dashboard, your state-regulator portal (for tobacco / alcohol audits), and your SIEM (Security Information and Event Management). Default retention is 5 years post-relationship, extendable per local audit rules. Ready for ABC (Alcoholic Beverage Control) board inspections in the US and equivalent national bodies in the EU.

What hardware do I need for the store?

Two things at the door, one at the till:

  • At the door, a QR sticker (for first-visit) and a camera (for biometric return). Any IP camera with a clear face shot works; many operators use the off-the-shelf cameras that ship with autonomous-store hardware from Standard Cognition, AiFi, Trigo, Grabango.
  • In the shopper's hand, their own phone for the QR scan + hosted session
  • At the POS / till, your normal self-checkout terminal calling the Didit decision endpoint to confirm age + region against each restricted SKU

No Didit-branded hardware. No proprietary kiosk. The recipe runs on the cameras and terminals you already have.

How do I plug this into my store-OS?

Four wires:

  • The door QR encodes the hosted session URL Didit returns from POST /v3/session/
  • Your callback endpoint receives the signed webhook (X-Signature-V2, HMAC SHA-256). On status: Approved, send the unlock command to your door-controller
  • Your POS calls GET /v3/session/'{'sessionId'}'/decision/ when the shopper scans a restricted SKU, confirms age + region
  • Your loss-prevention dashboard subscribes to the same webhook stream for the audit log

The Didit MCP (Model Context Protocol) server is included free, paste the integration prompt above into Claude Code, Cursor, Codex, Replit Agent, Devin, or Aider and the agent scaffolds the whole thing against the live /v3/ API.

Related

相关模块 + 工作流

身份与欺诈基础设施。

一个 API 即可实现 KYC、KYB、交易监控和钱包筛选。5 分钟即可集成。

免费开始联系我们
让 AI 总结此页面