How to classify and route text with the Azure OpenAI Decisions API
Asking a language model to pick a category usually ends with code that parses its prose, hopes the label is spelled the way you expected and breaks the day the model adds a polite sentence before the answer. When I built Linkmortem , I solved that by asking Gemma 4 for a single JSON object with a fixed list of page kinds and validating it in code. Microsoft Foundry now offers a more direct route…
The Azure OpenAI Decisions API is a service that evaluates text, images, or both and returns typed answers that can be read directly by your code. It is designed for classifying content, routing requests, and prioritizing work. The API takes an input, which is the content to evaluate, and a list of questions, each with a type, name, and instructions. The type determines the shape of the answer.
There are three question types: predicate, probability, and choice. The predicate type checks whether a condition is true and returns a boolean value. The probability type returns a value between 0 and 1, indicating the likelihood of an option being correct. The choice type returns the option that fits best, along with its value and description. The choice type can have between 2 and 255 unique options.
The Decisions API supports three question types: predicate, probability, and choice. The predicate type checks whether a condition is true and returns a boolean value. The probability type returns a value between 0 and 1, indicating the likelihood of an option being correct. The choice type returns the option that fits best, along with its value and description. The choice type can have between 2 and 255 unique options.
The API supports up to 400 questions and up to 128 images per request, with a combined image size of 32MB. The input costs $0.10, cached input $0.01, and output $0.50. The Decisions API is generally available in Microsoft Foundry and uses the gpt-6-luna model, which joined the generally available lineup on September 22, 2026. To use the Decisions API, you need an Azure subscription, a Microsoft Foundry resource, a deployment of gpt-6-luna, and a region where the API has rolled out.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
