OpenAI Developer Platform Adds New Decisions API Test Interface, Supporting Judgment, Selection and Scoring

The OpenAI Developer Platform has launched a new Decisions API test interface, allowing users to test three modes: Predicate, Choice, and Score. These modes are respectively used to estimate the probability that a condition is true, make selections from given options, and assign scores based on specified scoring criteria. According to official OpenAI documentation, this API is currently in public beta, supports text and image inputs, and can be applied to use cases including content categorization, request routing, and task priority assessment. It currently only supports the gpt-6-luna model, with a base input pricing of $0.10 per million tokens, and no charges for output tokens.

Source: PANewsRead original