spam classification · v1

Stop spam
at the API.

Updated August 22, 2026

SiftFy is a spam detection API. Send text, get a calibrated probability back, and set your own threshold.
No queues. No models to host. No surprises.

10,000 requests/month free · no credit card · two-line install

curlOne endpoint. Two lines of code.
curl -sX POST https://api.siftfy.io/v1/predict \
  -H "X-API-Key: $SIFTFY_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "FREE iPhone! click http://bit.ly/x to claim NOW"}'

# {
#   "spam_probability": 0.65,
#   "likelihood": "medium",
#   "max_confidence": 0.84
# }
87.4%
F1 on 1,741 comments
<10ms
p99 latency, CPU only
1
endpoint to learn
18MB
model · BERT-tiny + signals

How it works

01

Create a key

Sign in with your email — we send a one-time link. Generate an API key from the dashboard.

02

Send a request

POST any text to /v1/predict. The response is a calibrated spam score between 0 and 1.

03

Threshold & ship

Use max_confidence when setting policy. The model alone cannot reach the 0.85 block band.

Built for an inbox that doesn't wait.

Calibrated probabilities

Not a thumbs-up classifier. A calibrated model score plus bounded content evidence lets you pick the review threshold that matches your false-positive tolerance.

Single round trip

No queues, no async webhooks, no streaming. One HTTPS request, single-digit milliseconds, response inline.

Per-key everything

Every key has its own usage counter, last-used timestamp, and revocation. Issue keys to specific apps; revoke any one of them in a click.

Deterministic by design

Model version is pinned per release. Same input, same probability — no silent drift on your spam filter when we retrain.

In production in our own products

Foliomulti-domain webmail · classifies every inbound messageintegration breakdown →
EchoThreadprivacy-first comments · classifies every new commentintegration breakdown →

Both are operated by VectraSEO LLC, the company that operates Siftfy. They are shown here as working integrations we run ourselves, not as third-party endorsements.

Frequently asked questions

How accurate is the model?
On a 1,741-comment UCI YouTube Spam Collection benchmark at a 0.50 review threshold, the model measured 87.4% F1, 96.3% precision, and 80.0% recall. That run is model-only and does not establish accuracy on unseen customer traffic; validate the returned scores against your own submissions before enforcing a policy.
What language(s) does it support?
The active model is trained primarily on English. Non-English inputs still classify, but accuracy degrades. If you need a specific language we can swap the underlying model — email us.
How fast is /v1/predict?
Single-digit milliseconds for SMS-length text on CPU. Most calls round-trip in under 10ms p99 from the same region. There are no async queues, no webhooks — one HTTP request, one response.
Do you store the text I send?
No. We log request metadata (timestamp, status, duration, tenant id) but the request body is not persisted. If you need contractual confirmation in writing, get in touch.
What happens if I exceed my quota?
On the free tier you get 10,000 requests/month and 60/minute. Cross either and the API returns 429 with a Retry-After hint. Pro lifts the cap to 1M/month included plus $0.0001/req metered.
Can I self-host?
We run a managed service. For very large volumes or air-gapped requirements we can talk about a dedicated deployment — email hi@siftfy.io.

Drop it in where you already are.

Eight integrations, each with a real runnable example. Pick the one that matches your stack — or read the /v1/predict reference and roll your own in 15 lines.

Also useful: Python, Next.js, fake signups, AI-generated spam, comment moderation, and the comment spam examples.

Two lines from now,
you're filtering spam.

10,000 free requests every month. Pro is $9 + $0.0001 per request after that. Compare the pricing models before you pick a vendor.

Get an API key →