Skip to content
Visork
Request pilot access

Making content safety radically more efficient.

An EU-hosted AI API for real-time CSAM detection — built so harmful uploads are caught before they reach your users.

Request pilot access See how detection works

Real-time AI detection

Including new and AI-generated content.

Drop-in REST API

Sub-200ms target. JSON in, JSON out.

EU-hosted, GDPR-first

Inference, storage, and audit logs — all in the EU.

Auditable by default

Every score logged, exportable for legal review.

POSTapi.visork.com / v1 / images / analyze
Request
curl -X POST https://api.visork.com/v1/images/analyze \
  -H "Authorization: Bearer $VISORK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image_url": "https://your-cdn/uploads/4f2a.jpg",
    "modules": ["csam"],
    "threshold": 0.85
  }'
Response · 184 ms
200 OK
{
  "id": "an_2k9d4e1m7q",
  "verdict": block,
  "modules": {
    "csam": {
      "score": 0.974,
      "flagged": true
    }
  },
  "audit_log_id": "log_8c1f02b9",
  "region": "eu-central-1"
}
Score 0.974Threshold 0.85
One credit per analysis · No standing minimum
Audit log retained for review

One REST endpoint, every backend stack.
Built so a junior engineer can ship the integration in an afternoon.

DETECT. DECIDE. DOCUMENT.

Built for platforms that take user safety seriously

Visork sits between an upload and your moderation queue. It scores every image, returns a verdict in milliseconds, and keeps a record of why — so your team only ever sees what genuinely needs human judgement.

Catches CSAM the moment it's uploaded

Detection trained to flag CSAM the moment it appears — including newly created and AI-generated content. The same architecture is what we'll extend to violence, deepfakes, and grooming detection.

Drop-in REST integration

One endpoint, JSON in, JSON out. Engineered for sub-200ms response so it fits inside your upload pipeline without slowing it down.

EU-hosted, audit-ready

Inference, storage, and audit logs stay in the EU. Every analysis is signed and retrievable for legal review.

What Visork is

Visork is an EU-hosted detection API that identifies illegal and harmful content in user uploads in real time, starting with CSAM in images. Your backend sends an image to one REST endpoint and receives a probabilistic score per module, a block / review / allow verdict against a threshold you set, and a signed audit log entry — your own systems make the final moderation decision. Detection is ML-first: a classifier trained to recognise CSAM, including newly created and AI-generated material. That complements hash-matching systems such as PhotoDNA, Project Arachnid, and Cloudflare's CSAM Scanning Tool, which only match files already present in known-content databases; the two approaches run side by side. Inference, storage, and audit logs all stay inside the EU, API media is analysed in memory and deleted by default after the verdict, and customer data is not used for training by default — only where a platform enables it, by agreement or in the service settings.

Everything between an upload and a verdict

Tunable thresholds.

Set the precision/recall trade-off per module. Audit-ready scores attached to every verdict.
csam0.974
violence0.412
nudity0.318

Threshold UI — additional modules in development

Speaks every backend.

REST in, REST out. Official SDKs (PHP, Node.js, Python, Java) are on the long-term roadmap.

Verdicts, not raw scores.

Block, route to review, or allow — your call, your thresholds.
block
route to review
allow

Audit logs by default.

Every decision recorded with score, threshold, and module — exportable for compliance.
log_8c1f02b9block0.974
log_8c1f02b8allow0.012
log_8c1f02b7block0.991
log_8c1f02b6review0.741

Webhook notifications.

Coming soon Push alerts for flagged content the moment it lands. Async-native moderation workflows without polling.
POST → /webhook/visork
event: analysis.flagged
Your service
200 acknowledged

Wherever users upload, the same primitives apply

One endpoint, one verdict format, one audit trail. These are the segments where user-generated imagery carries the most legal and regulatory risk under the DSA — and where the integration looks identical.

  • Social & communication

    Stop harmful imagery before it ever surfaces in a feed.

    Score every upload at the edge of your moderation pipeline. Block the obvious, route the unclear, let the rest through.

  • Hosting & cloud

    Screen every upload without leaving the EU.

    A drop-in API for object storage and upload pipelines. Inference, storage, and audit logs are EU-hosted.

  • Dating platforms

    Photo screening at sign-up, frictionless for the user.

    Hold profile photos at the gate. A sub-200ms response target keeps onboarding smooth, even at peak traffic.

  • Communities & forums

    Moderate at scale without growing the team.

    Quarantine harmful uploads automatically and surface only the borderline cases that genuinely need a human.

  • E-commerce & marketplaces

    Catch policy violations the moment listings go live.

    Run listing photos through one endpoint before they're indexed. Fewer takedowns after the fact, less exposure for your review team.

  • Content sharing

    Quarantine quietly, escalate on your own terms.

    Flag high-risk uploads for asynchronous review. Every verdict is recorded with its score and threshold, and exportable for your compliance process.

Request pilot access See how pricing works
100 credits included · EU-hosted · Onboarded selectively

Questions we get on scoping calls

If you can't find what you're looking for, get in touch.

Detection & technology

What does Visork detect right now?

The first production module is image-based CSAM (child sexual abuse material) detection. Detection of violence, deepfakes, and nudity in images, plus grooming detection in text, is on the roadmap and will roll out as separate modules.

How do you handle false positives?

Every analysis returns a probabilistic score, not a binary verdict. You set the threshold per module to fit your platform's risk profile, and the model is calibrated continuously against representative data. False positives are treated as a first-class quality metric — not an afterthought.

Compliance & getting started

Where is my data processed?

Inference, storage, and audit logs run inside the EU. Data residency is a design choice, not a paid add-on, and it differentiates Visork from US-based competitors.

Can I try it for free?

Yes. Every pilot opens with 100 free credits — one credit per analysis — so you can measure detection quality and integration effort before any commercial terms. Access is granted after a short scoping call rather than through self-serve signup: a CSAM detection endpoint isn't something we hand to an unverified account. Request pilot access to start one.