Checkobot

AI-generated image detection API

One REST call per image. Send a file, a URL or base64 and get back a verdict (AI or No AI detected), which detector fired, both detector scores and the face box.

Show Checko an image

Drop or paste an image here

JPEG, PNG, WebP, AVIF, GIF, BMP or TIFF · up to 20 MB

No image handy? Try one of ours.

Most we made with AI; one is a phone photo. Checko wasn’t told which.

On free checks, images are checked in memory and never stored.

What it detects

The API detects AI-generated and AI-manipulated images, with a dedicated face-forensics model for deepfakes. Each response includes per-model explanations: which detector fired and the face box.

Where teams use it

  • Trust and safety: flag AI-generated or swapped profile photos and uploads for review.
  • Marketplaces and listings: catch AI-made product, property and review photos.
  • Dating and social platforms: check profile photos at sign-up or on report.
  • Newsrooms and fact-checking tools: add a second opinion to a verification workflow.

The request

  • POST /v1/check with a multipart file, a JSON image_url, or JSON image_b64.
  • Authorization: Bearer with a cb_live_ API key.
  • Original bytes are scored as sent; nothing is resized or re-encoded on the way.
  • POST /v1/check/batch takes up to 8 images per call (API Growth and above). GET /v1/usage returns checks used this period.

The response

  • id: the check ID, which also links to its result page.
  • is_ai: the verdict (true means AI, false means No AI detected).
  • fired: which detectors crossed their threshold (full_image_specialist for the whole-image analysis, face_specialist for the face analysis).
  • reason: a one-line, human-readable explanation.
  • scores and face_box: both detector scores and the location of the face that was checked.
  • model and bands_version: the exact model and thresholds used, so every decision can be audited later.

Plans

  • API Starter: $49 a month for 5,000 checks.
  • API Growth: $149 a month for 20,000 checks, plus the batch endpoint.
  • API Scale: $499 a month for 100,000 checks.
  • No extra charges: once the month's checks are used up, calls get quota_exceeded until the 1st (UTC). Upgrade any time. Enterprise plans are priced to your volume.

Data handling

Images are processed in memory and not stored, unless you turn on Store images for a key or send store=true with a request; then the image is kept, encrypted, for your plan's 30-day history. Each check keeps a SHA-256 hash of the file, the verdict and the scores, so results can be audited later.

Limits

  • Images under 256 pixels on the short side, or JPEGs below quality 50, are refused with image_too_small or image_too_compressed. Refused images aren't billed.
  • Maximum 20 MB per image. JPEG, PNG, WebP, AVIF, GIF, BMP and TIFF are accepted; HEIC isn't yet.
  • Not for audio or liveness. ID and document checks are coming soon.

Questions

Is there a free tier for the API?

API keys come with the API plans. You can try the same detectors on the website first, 3 checks a day, no sign-up.

Can I choose different thresholds?

Not yet. Profile choice is planned for API Growth and custom thresholds for Enterprise.

Do you train on the images we send?

No. By default images are processed in memory and not stored, so there is nothing to train on. If you turn storage on (a key's Store images switch, or store=true), images are kept for your 30-day history and then deleted. We keep the hash, verdict and scores.

How fast is it?

Model compute is around 80–150 ms per image. Total time depends mostly on the size of the image you upload and the network between you and us.

Should we block users automatically on an AI verdict?

We recommend against it. Treat the verdict as a risk signal: route flagged images to review or ask for another photo, rather than banning silently.