score (the winning level index) plus expected_level, a probability-weighted continuous estimate across all levels, per-level probabilities, and a legend echoing your level descriptions back by index.
Use a Score when the answer is a position on a scale with defined levels — urgency, severity, sentiment intensity — rather than an unordered category.
Request
string
required
Always
"score".string
required
The question to evaluate, in natural language.
string[] | object
required
An ordered array of level descriptions, index
0 is the lowest level: ["low urgency, can wait", "medium urgency, handle soon", "high urgency, handle immediately"].Also accepts an object with numeric-string keys (e.g. {"1": "...", "3": "...", "5": "..."}) — keys are sorted and then discarded, and the response is always re-indexed 0..N-1 regardless of the keys you used.Response
score— a discrete integer index, the argmax level.expected_level—Σ(level × probability), the continuous, probability-weighted position across all levels. Use it when you want finer-grained thresholds than the discrete index provides.legendisn’t generated by the model — the API builds it from your owncriteria, indexed.confidence—top1 − top2, same formula as Choice, from0(two adjacent levels tied) to1(one level has ~all the probability mass). See Confidence for how to act on it.
Using the result
Related
- Noul — a yes/no decision with a probability
- Choice — pick one of several named options
- Decision Models — primitives overview, limits, and the full request contract
- GLiDE — what GLiDE is and when to use it

