Unprofane
All comparisons

Unprofane vs hosted word-list APIs

Not whether a listed word appears, but whether the text can be shown, to which audience, and why.

A number of hosted services take a text and return a boolean or a list of matched words from a fixed list, often with a free tier and a flat price.

Toxic text caught at the same false-alarm rate
  1. Unprofane89.0%flagging 7.0% of clean text
  2. Perspective API58.4%at the same rate
  3. OpenAI moderation40.8%at the same rate
Disguised spellings caught
86.0%vsPerspective 51.7%, OpenAI 26.9%
Toxic usernames caught
76.5%vsPerspective 32.5%, OpenAI 9.0%

Hosted word-list APIs are not on the benchmark, so they have no bar and this page makes no claim about their accuracy. When you compare, ask for toxic text caught at a stated false-alarm rate, on text nobody tuned on.

The private test set, 9,029 texts labelled blind, read once on 2026-09-28, engine 2026-09-29. How it was measured

Try to fool it

The real engine, live. Type a disguised word and watch it read, named and judged; type an innocent one and watch it pass.

Every answer carries the same evidence through the API: the words, where they were, how they were disguised and a censored version.

Enter to check

Why Unprofane

  1. 01

    Usernames read as usernames

    Split into words and read backwards, so a reversed word is caught and a reserved name is told apart from a rude one.

    username

    kcuffuck

    reversedreview ยท strong

    Shown as ****

  2. 02

    One text, four audiences

    Kids, teen, standard and strict presets, with each category scored apart, so the same text can pass for adults and stop for children.

    Textkidsteenstandardstrict
    damn itblockallowallowblock
    holy shitblockblockreviewblock
  3. 03

    Measured in public

    False positives on innocent words are counted and published, per engine version.

    0.0%

    false positives on 1,447 innocent words and phrases, the Scunthorpe Test of 2026-10-12

    • Scunthorpeallow
    • Dickinsonallow
    • cockatooallow
    • Sussexallow
    • shiitakeallow
    • breast cancer screeningallow

Not just whether a word is on a list: whether the text can be shown, to whom, and why.

The first call

A test key is free, with a plan or without one. One request, in the language you use, and the answer carries the evidence.

curl -X POST https://api.unprofane.com/v1/check \
  -H "Authorization: Bearer up_test_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"xXsh1tXx","context":"username","policy":"teen"}'
Open the quickstart

Try it on your own text

Free test keys, 100 checks a day, no card. Live from $9 a month. Every answer shows its evidence.

Other comparisons