# Microsoft-Decision-1: a model that answers with odds, not essays

URL: https://ai-pulse.aglaganova.com/blog/microsoft-decision-1-a-model-that-answers-with-odds-not-essays
Published: 2026-10-14
Author: Roman Aglaganov, Full-stack developer
Category: Models
Region: Global
Tags: agents, benchmarks

> Microsoft’s new small model does not write. It reads text, picks from fixed answers and gives a probability for each, quickly and cheaply. It is part of a new category of AI built for software to act on.

![Illustration: a stream of small squares reaching a node that splits three ways, the middle route red with the longest bar](https://ai-pulse.aglaganova.com/api/media/file/decision-1.png)

Not every AI job needs a paragraph. Is this email spam? Which team should handle this ticket? Should an agent go ahead, or ask a human first? Microsoft’s new model, Microsoft-Decision-1, released on 9 October, is built only for questions like these.

## How it is different

A chatbot answers by generating text, which then has to be read and interpreted. A decision model takes some text, called the state, plus one or more questions with fixed answers. It returns a calibrated probability for each answer, in a format software can act on straight away. Because the answer carries its own confidence, an app can decide to act, wait or send the case to a person.

Microsoft lists the uses as routing, classification, prioritisation, verification, workflow control, guardrails for agents, and grading other AI models’ work. It is clear about what it is not for: writing, conversation, translation or summaries.

## The numbers

**Size and price:** it is a small model, post-trained from Alibaba’s open Qwen3.5-9B, with a 33,000-token context. On OpenRouter it costs $0.042 per million input tokens, and output is free.

**Microsoft’s claims:** it had the highest accuracy in Microsoft’s 36-benchmark comparison of nearly 150,000 questions, and was the fastest measured: 2.5 times quicker than the runner-up, H2O-Lightning-4B, and 35 times quicker than OpenAI’s GPT-6 Sol. These are Microsoft’s own tests; independent results will follow.

**Where to get it:** Microsoft Foundry and OpenRouter. Its weights are updated continually while the interface stays the same.

## Why it matters

As AI agents take on more work, they make thousands of small decisions. Running each one through a frontier chatbot is slow and expensive, and the answer can be hard to check. Small, cheap models that output a number are easier to test, monitor and set thresholds for. One caution: a confident probability is still a guess, so decisions that affect people, like hiring or credit, should never rest on it alone.

## Sources

- [Microsoft: Introducing Microsoft-Decision-1, our model for fast decision-making](https://commandline.microsoft.com/microsoft-decision-1-model-foundry/)
- [OpenRouter: Microsoft-Decision-1](https://openrouter.ai/microsoft/microsoft-decision-1)