RLCD Decision API

Structured classification in a single forward pass. Give it a piece of text and a field schema (enums / booleans); one request judges every field at once and returns each value with a calibrated confidence score. No API key needed here — just try it.

checking… limits: 16 fields / 64 choices / 8000 chars model on Hugging Face rate limit: 12 req/min

Input

Schema

Ctrl/+Enter to submit · leave schema empty for the server default

Result

No result yet — enter text on the left and hit Classify.

Call it directly

This endpoint is request/response-identical to the upstream API — it just doesn't need an Authorization header. Point your base URL here and it works.


  
FieldMeaning
contextRequired. The text to classify, ≤8000 characters.
schemaOptional. Omit it to use the server default: fraud_risk / block_account / language / sentiment.
schema.<field>.type"enum" or "boolean"
schema.<field>.choicesEnum only. 1–64 options, each ≤80 characters.
schema.<field>.descriptionThe judging criteria, ≤500 characters — writing this well is what determines accuracy.

One hard-won tip: in the description, spell out when each option applies, and give an explicit positive fallback rule ("code with no side effects is always true"). Ask an open-ended question like "is this safe?" and the model skews systematically toward the negative answer — and it will be confidently wrong, so the confidence score won't save you.