Unverified50% confidenceFactExact time
Decision-1 receives a state description and a fixed set of candidate answers, returns calibrated probability values for each option, and outputs structured JSON rather than free text.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe way Decision-1 is used is to give it a fixed set of candidate options, and it returns calibrated probability values for each option in a single inference pass.80% similarUnverifiedDecisions API is a System 1 type model that does not follow the Next Token Prediction approach, but instead directly predicts the probabilities of various possible outcomes.73% similarUnverifiedThe Decisions API directly returns typed results, including probability values, options, and scores71% similarUnverifiedDecision models focus on answering yes/no judgments, multiple-choice questions, and probability-scored rating-type problems.71% similarUnverifiedForcing output in JSON, enumerated values, or fixed labels can constrain the model to answer within a predefined decision space, improving output parseability and reliability.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/997993API
curl https://kongchang.com/api/v1/knowledge/claims/997993MCP
get_claim(id=997993)