Text in. Label out.

Classify text with your own labels. Free. No account or API key.

Using sifty

Send text and labels. Get the most likely label back.

HTTP API

curl https://sifty.dev/spam,not+spam/Win+a+free+iPhone

Add ?verbose=1 for probabilities. Use POST for a batch:

curl https://sifty.dev/ -H 'Content-Type: application/json' \
  -d '{"input":["Win a free iPhone","Lunch at noon?"],"labels":["spam","not spam"]}'

Python

Install typesafe-sdk to ask typed questions.

from typesafe_sdk import Noul, TypeSafeClient

client = TypeSafeClient(
    api_key="free",
    base_url="https://sifty.dev",
    timeout=120,
)
response = client.system_one(
    state="I was charged twice.",
    questions={"billing": Noul(instructions="Is this about billing?")},
)
print(response.nouls["billing"].noul)

Limits

1,000 units per IP per day, reset at 00:00 UTC. A batch counts each text; a System One call counts each question. There is also a shared daily cap of 20,000 units.

Use 2–26 labels, up to 32 texts per batch. The X-RateLimit-Remaining header tracks your allowance. A 429 response includes Retry-After.

How it works

Qwen3-8B scores your labels using next-token probabilities, averaged across label orderings. It does not generate a text response. A cold GPU may take up to a minute to wake.

Requests pass through Cloudflare and RunPod, whose logs may record them. Please don’t send sensitive data.