Objective benchmarks and architectural comparisons between OpenAI Decisions API powered by Luna and existing LLM paradigms.
Use Decisions API when your model needs to select strictly one discrete label or action at edge speed (~142ms). Use Structured Outputs when you must generate multi-field JSON payloads with nested objects, arrays, or prose fields.
Use Decisions API for fast, deterministic branching (which tool/action to take next) before invoking tools. Use Function Calling when the model must both choose a function AND construct complex arguments in a single step.
Use Decisions API whenever you find yourself prompting a chat model to "respond with ONLY label A, B, or C". It is ~13x faster, ~90% cheaper, and guarantees zero conversational preamble or markdown pollution.