Calibrated spam classification, served from a single API.
POST text, get back a calibrated probability between 0 and 1. At 0.7, roughly 70% of inputs with that score are actually spam — pick a threshold once and trust it. Sub-10ms p99, no model to host, no queue to drain.
pip install siftfyfrom siftfy import Siftfy
client = Siftfy(api_key="sk_live_...")
result = client.predict("Win a free iPad — click here!")
print(result.spam_probability) # 0.97
print(result.likelihood) # "high"Or hit the API directly:
curl -X POST https://api.siftfy.io/v1/predict \
-H "Authorization: Bearer sk_live_..." \
-H "Content-Type: application/json" \
-d '{"text": "Win a free iPad — click here!"}'Get a key at siftfy.io. Free tier covers 10,000 requests/month — no card.
siftfy-python— official Python client.pip install siftfy.