OpenAI Developer Platform Adds Decisions API Testing Interface, Supporting Judgment, Choice, and Scoring

October 20 - According to TestingCatalog, the OpenAI developer platform has added a Decisions API testing interface, allowing users to test three modes: Predicate, Choice, and Score, which are respectively used to estimate the probability that a condition is true, make a choice from given options, and score according to rating criteria. OpenAI's official documentation shows that the API is currently in public beta, supports text and image input, and can be used for content classification, request routing, and task priority determination. Currently, only the gpt-6-luna model is supported, with a base input price of $0.10 per million tokens and no output token fees.