Evaluate

Evaluate unstructured state against a map of typed System One questions (noul / choice / score). Returns structured answers with calibrated probabilities and confidence. Chat completions are not supported for these models — use this endpoint instead of /v1/chat/completions.

post/v1/evaluate

Request body

modelstring required

Spicepod model name (runtime) or provider model id (provider forward).

questionsobject required

Response

Evaluation succeeded

answersobject required

modelstring required

Versioned model id that answered (e.g. jev-1.13.0), when the provider reports it.

Changes

Changed in 1 of the 55 revisions of this API.1

Sep 22, 2026899fb3203a1b1See the full diff
- ○
  endpoint added
  endpoint-added

Full history