Use case · content moderation

Check content against your own policy

Ask a yes/no question about a comment, post or message and get a probability back. You set the threshold: block, queue for review or let it through.

Get API keyRead the quickstart

Sign in with Google or an email link. Free allowance by invitation; add credit from EUR 1.

Moving from Perspective? Moderation API beta: Perspective-shaped endpoint and free migration tool →

Example request

One call, five lines

Set DECISIONMODELS_API_KEY to a key from your dashboard. The request below uses the EU tier; send S1-Region: global for the Peer-to-Peer tier.

Request · POST /v1/systemone
curl https://api.decisionmodels.io/v1/systemone \
  -H "Authorization: Bearer $DECISIONMODELS_API_KEY" \
  -H "Content-Type: application/json" \
  -H "S1-Region: eu" \
  -d '{"model":"s1-fast","state":"You are a complete idiot and nobody wants you here.","questions":{"violates":{"type":"noul","instructions":"Does this comment break a rule against personal insults?"}}}'

Example response

A typed answer with probabilities

Illustrative, not a measured model output. Always read the probability before your application acts on it.

Response · illustrative
{"id":"dec_example","model":"s1-fast","answers":{"violates":{"type":"noul","noul":0.94}},"usage":{"input_tokens":187,"output_tokens":0,"decisions":1},"tier":"eu"}

Notes

Before you build on it

Cost example

Illustrative cost for 1,000 decisions

List-price illustration for accounts created on or after 12 November 2026: 1,000 text decisions, one question per request and 1,000 billed input tokens each, cost 0.028 EUR on s1-fast (Peer-to-Peer) or 0.030 EUR (EU); s1-pro costs 0.085 EUR or 0.090 EUR. Output tokens are free; applicable taxes are excluded. Input tokens include the state, instructions and answer options. Actual costs depend on the input and tier. Full pricing.

FAQ

Frequently asked question

Which model should I use for content moderation?

s1-fast accepts one typed question per request; s1-pro accepts up to three typed text questions. Put your policy in the question and set thresholds using representative review data; the API has no built-in moderation policy.