Image API

The AI image detection API.

Detect AI-generated and manipulated images at scale. One REST call returns a verdict, Authentic, Likely Synthetic, or Inconclusive, with a confidence-scored TrustScore, in milliseconds.

High accuracy · 60s file purge · Keys hashed at rest

cURL
JavaScript
Python
Java
Go
# detect an AI-generated image curl -X POST \ https://app.deepfakedetector.ai/api/v1/detect/image \ -H "Authorization: Bearer sk_live_..." \ -H "Content-Type: application/json" \ -d '{ "image_url": "https://example.com/photo.jpg" }' # or upload a file via multipart curl -X POST \ https://app.deepfakedetector.ai/api/v1/detect/image \ -H "Authorization: Bearer sk_live_..." \ -F "file=@photo.jpg"
const res = await fetch( 'https://app.deepfakedetector.ai/api/v1/detect/image', { method: 'POST', headers: { 'Authorization': 'Bearer sk_live_...', 'Content-Type': 'application/json' }, body: JSON.stringify({ image_url: 'https://example.com/photo.jpg' }) } ); console.log(await res.json());
import requests res = requests.post( "https://app.deepfakedetector.ai/api/v1/detect/image", headers={ "Authorization": "Bearer sk_live_...", "Content-Type": "application/json", }, json={"image_url": "https://example.com/photo.jpg"}, ) print(res.json())
var url = URI.create( "https://app.deepfakedetector.ai/api/v1/detect/image"); var req = HttpRequest.newBuilder().uri(url) .header("Authorization", "Bearer sk_live_...") .header("Content-Type", "application/json") .POST(HttpRequest.BodyPublishers.ofString( "{\"image_url\": \"https://example.com/photo.jpg\"}")) .build(); var res = HttpClient.newHttpClient() .send(req, HttpResponse.BodyHandlers.ofString());
body := strings.NewReader( `{"image_url": "https://example.com/photo.jpg"}`) req, _ := http.NewRequest("POST", "https://app.deepfakedetector.ai/api/v1/detect/image", body) req.Header.Set("Authorization", "Bearer sk_live_...") req.Header.Set("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req)
What it detects

One endpoint for AI-generated and manipulated images.

A single POST to /v1/detect/image covers fully AI-generated images and manipulated photos alike. It is the single-modality companion to our full deepfake detection API, and powers the same engine behind our consumer AI image detector.

Every major generator

Flags fully AI-generated images from across MidJourney, DALL-E, Stable Diffusion, Flux, Firefly, Imagen, and Ideogram. The API detects synthetic origin without attributing an image to any specific generator.

Manipulated and face-swapped

Catches edited, composited, and face-swapped photos as well as synthetic faces, not just images that are AI from scratch.

A clear verdict

Each call returns one of three verdicts, Authentic, Likely Synthetic, or Inconclusive, alongside a TrustScore from 0 to 100 you can threshold on.

Request schema

Send a URL or a file. Get a verdict.

Pass a public or signed image_url, or upload via multipart. We fetch, scan, score, and purge, all within 60 seconds of the verdict unless you opt into retention. Supported formats are JPG, PNG, and WEBP.

ParameterTypeDescription
image_urlstringHTTPS URL to the image. Either image_url OR multipart upload required.required*
filemultipartUpload the image directly as multipart form data. JPG, PNG, or WEBP.required*
webhook_urlstringWebhook for async jobs. We POST the verdict here when analysis is done.
strict_modebooleanLower confidence threshold. Increases recall, may reduce precision. Default false.
retainbooleanKeep the image for audit instead of purging. Default false (60s purge).
Request
# POST /api/v1/detect/image curl -X POST \ https://app.deepfakedetector.ai/api/v1/detect/image \ -H "Authorization: Bearer sk_live_..." \ -H "Content-Type: application/json" \ -d '{ "image_url": "https://example.com/photo.jpg", "strict_mode": false, "webhook_url": "https://your-app.com/webhook" }'
Response
{ "job_id": "job_8mTk2x", "verdict": "likely_synthetic", "trust_score": 12, "confidence": 0.94, "media_type": "image", "processing_ms": 734 }

Verdicts map to Authentic / Likely Synthetic / Inconclusive. Files are deleted within 60 seconds of analysis unless retain is set.

Use cases

Built for moderation and trust & safety at scale.

Drop image detection into your pipeline with batch processing, webhooks for async jobs, and high throughput at low latency.

UGC & marketplaces

Flag AI-generated listings, product shots, and profile photos before they reach buyers.

Dating apps

Catch catfish and synthetic profile photos at signup and on every new upload.

Newsrooms & fact-checkers

Verify imagery before publication and triage suspect photos at speed.

Ad & brand safety

Screen creative and submitted assets so synthetic imagery never runs under your brand.

Process images one at a time or in batch, register a webhook_url for async results, and scale throughput as your moderation queue grows. Want the science behind the verdict? Read how AI image detectors work.

SDKs

Official clients in eight languages.

Same call to detect an AI-generated image, same response shape. Auth, retries, exponential backoff, file streaming, and webhook signature verification handled for you.

JavaScript / TypeScript
Python
Go
Ruby
PHP
Java
.NET
Rust
Pricing

API access is included from the Starter plan.

Start free with 50 detections per month, no card required. API access begins on Starter at $49/mo, Business is $199/mo, and Enterprise is $599/mo. See full limits on our pricing page.

$0

Free. 50 detections/month in the web app, no card required.

$49

Starter. Adds API access for programmatic image detection.

$199

Business. Higher volume, higher rate limits, batch workflows.

$599

Enterprise. Highest throughput with priority support.

FAQ

AI image detection API questions.

Everything teams ask before they integrate. Comparing tools? See the best AI image detectors.

What is an AI image detection API?

A REST API that analyzes an image and returns whether it is AI-generated or authentic, with a confidence-scored verdict.

Which image generators can it detect?

Images from all major generators including MidJourney, DALL-E, Stable Diffusion, Flux, Firefly, Imagen, and Ideogram.

How do I call the API?

POST an image_url or upload a file to /v1/detect/image with your API key; you get back a JSON verdict (Authentic / Likely Synthetic / Inconclusive) and a TrustScore.

What image formats and sizes are supported?

JPG, PNG, and WEBP; size limits depend on your plan.

How fast is it?

Most images return in well under a second; use webhooks for large batches.

Can I use it for content moderation?

Yes, teams use it to flag AI-generated and manipulated images in user uploads, listings, and profiles as part of a moderation pipeline.

Is it free, and are images stored?

A free account includes 50 detections/month; API access starts on the Starter plan. Images are deleted from primary storage within 60 seconds of analysis unless you opt into retention.

Detect AI images
at scale.

One REST endpoint, confidence-scored verdicts, webhooks, and SDKs, built for moderation and trust & safety teams.