GET

/v1/schemas/typesafe/decision/v1/systemone?kind=output

kind outputactivity decisionhash 25a8cf2b…extracted Nov 11, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.

upstream-spec

Source trace
3ca93b6e6b9aa8d7820531b78c66ed7a9798b11e6e163ad96b140fb3d75fbcf4
{
  "fetchedAt": 1794374486,
  "extractorVersion": "2",
  "verifiedAt": null
}

Response body

3 properties · 3 required · 7 $defs
propertytypedescriptionconstraints
model*stringName of the model that answered the questions. May differ from the alias supplied in the request.
answers*objectAnswers keyed by the question names supplied in the request. Each answer's type matches its question's type.
usage*UsageInput and output token counts for this evaluation.

Types

7 $defs

AnswerNoulAnswer | ChoiceAnswer | ScoreAnswer | …

An answer whose type matches the corresponding question.

BoxAnswerobject

A located box with normalized edge coordinates and confidence.

type*constIdentifies a box answer."box"
box*BoxCoordinatesThe box's edges as fractions of image height and width, from 0 to 1. Each coordinate is the expected value of its edge's predicted position.
confidence*numberConfidence for the given box, from 0 to 1, with 1 being more confident. Null when the model does not provide confidence.nullable

BoxCoordinatesobject

Normalized box edges. Vertical coordinates are measured from the top of the image; horizontal coordinates are measured from the left.

top*numberTop edge of the box, as a fraction of image height from the top (0-1).
bottom*numberBottom edge of the box, as a fraction of image height from the top (0-1).
left*numberLeft edge of the box, as a fraction of image width from the left (0-1).
right*numberRight edge of the box, as a fraction of image width from the left (0-1).

ChoiceAnswerobject

The selected choice, confidence, and probabilities for a choice question.

type*constIdentifies a selection from the requested choices."choice"
choice*stringThe name of the choice with the highest probability among the question's criteria.
confidence*numberConfidence in the selected choice, from 0 to 1. Higher values indicate greater certainty; use lower values to flag uncertain selections for review.
probabilities*objectProbability of each choice in criteria, keyed by choice name, from 0 to 1. Shows how likely the alternatives are; values sum to approximately 1.

NoulAnswerobject

The probability of a yes answer or a true statement.

type*constIdentifies a yes/no answer."noul"
noul*numberProbability of a yes answer or a true statement, from 0 to 1. Values near 1 favor yes or true, values near 0 favor no or false, and values near 0.5 indicate uncertainty.

ScoreAnswerobject

An expected score with its rubric, confidence, and score-level probabilities.

type*constIdentifies a rating against the requested score levels."score"
score*numberExpected score: the probability-weighted average of the rubric levels. May fall between integer levels.
confidence*numberConfidence in the score, from 0 to 1. Higher values indicate greater certainty; use lower values to flag uncertain ratings for review.
legend*objectThe requested criteria mapped to their score levels, so you can interpret the score.
probabilities*objectProbability of each score level, from 0 to 1, using the same keys as legend. Shows how likely the alternatives are; values sum to approximately 1.

Usageobject

Token usage for the request.

input_tokens*integerNumber of billable input tokens used to evaluate the request.
output_tokens*integerNumber of output tokens used to answer the questions. Output tokens are currently free of charge.

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"typesafe","endpointId":"v1/systemone","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}