# Microsoft-Decision-1 Just Landed: First systemone Call, Free Output Tokens, and the Qwen-to-MAI Rebase Catch > Source: > Published: 2026-10-12 13:43:30+00:00 **Attributed compile + one small offline smoke test** **Primary sources (Microsoft, 2026-10-09):** [Microsoft-Decision-1: Our model for fast decision-making](https://commandline.microsoft.com/microsoft-decision-1-model-foundry/) by **Achint Srivastava** (Command Line / Microsoft), [Deploy and use Microsoft-Decision-1 in Microsoft Foundry](https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/use-foundry-models-microsoft-decision) (Microsoft Learn), and the OpenRouter model page for [microsoft/microsoft-decision-1](https://openrouter.ai/microsoft/microsoft-decision-1) **Secondary:** [Microsoft launches a decision model built on Alibaba’s Qwen](https://thenextweb.com/news/microsoft-decision-1-qwen-decision-model) by The Next Web (2026-10-12) Accuracy, latency multiples, flip rates, and internal Xbox/Copilot anecdotes are **Microsoft's**. I have no Foundry or OpenRouter key on this box, so **I did not call Microsoft-Decision-1**. What I ran is an offline request/response linter against hand-built mocks, described below as exactly that. Microsoft shipped **Microsoft-Decision-1** into Foundry and OpenRouter on 2026-10-09, three days after Liquid open-weighted d1. Satya Nadella's launch post on X cleared a million impressions within hours. Same category shift: stop asking a chat model for JSON and ask a **decision model** for typed probabilities. The access difference matters. Liquid gave you weights. Microsoft gave you a hosted `systemone` endpoint, **$0.042 per million input tokens with output free**, and a **Qwen3.5-9B** base with an explicit plan to rebase onto MAI and OpenAI later. Same API shape either way. That rebase note is the catch. From Microsoft Learn and the OpenRouter page, a request is not a chat completion. You send a `state` (string or JSON) plus named `questions`. Each question is one of three types: | type | you give | you get back | |---|---|---| | `noul` | a yes/no condition | `P(yes)` in`[0, 1]` | | `choice` | named options with descriptions | selected option + per-option probabilities | | `score` | an ordered rubric (2+ levels) | probability-weighted level index | There is no free-form text and no written rationale. That is the point. Your code thresholds the probability, routes the ticket, or blocks the tool call. Learn's endpoint path on Foundry is: ``` /providers/microsoft/v1/systemone ``` The request's `model` field is **your deployment name**, not the string `Microsoft-Decision-1`. On OpenRouter the model id is `microsoft/microsoft-decision-1`, and OpenRouter documents that chat-completions SDKs will not work — you need the Decisions / System One surface. From Srivastava's post, labeled as vendor numbers: I did not reproduce any of that. Treat it as a launch claim sheet, then measure on your own labeled tickets. A single call can ask three questions over the same state. Pattern from Learn + OpenRouter: ``` python import json, os, urllib.request body = { "model": os.environ["DEPLOYMENT_NAME"], # your Foundry deployment name "state": "Help! My payouts have been failing for 3 days.", "questions": { "is_urgent": { "type": "noul", "instructions": "Does this message convey urgency?", "criteria": { "true": "Explicitly time-sensitive", "false": "No urgency expressed", }, }, "team": { "type": "choice", "instructions": "Which team should handle this?", "criteria": { "billing": "Payments, invoicing, refunds", "technical": "Bugs, outages, integrations", "sales": "Pricing, upgrades, new accounts", "cannot_tell": "Not enough information, or not a support request", }, }, "frustration": { "type": "score", "instructions": "How frustrated is the customer?", "criteria": ["Calm", "Frustrated", "Very angry"], }, }, } req = urllib.request.Request( os.environ["AZURE_ENDPOINT"].rstrip("/") + "/providers/microsoft/v1/systemone", data=json.dumps(body).encode(), headers={ "Content-Type": "application/json", "api-key": os.environ["AZURE_API_KEY"], }, method="POST", ) # with urllib.request.urlopen(req) as resp: print(resp.read().decode()) ``` Three things before production: `cannot_tell` is deliberate.`choice` always picks one option. Without an abstention label, gibberish still gets a team. Learn says to include abstention when the model should not be forced.`api-key`.` DefaultAzureCredential`; the snippet uses an API key because it is shorter to read. Microsoft and OpenRouter both list **$0.042 / 1M input** and **$0 / 1M output**. Output is free because there are no completion tokens in the chat sense — you get structured answers. Illustrative only: 100,000 requests × 2,000 billable input tokens ≈ **$8.40** of model input (ignores retries, retrieval, review, platform fees). That is why decision models look attractive for the boring 80% of routing. OpenRouter lists a **32,768**-token context, text in, structured decision out. No images or audio here (unlike Liquid's multimodal d1-omni). No Azure and no OpenRouter key on the box, so I wrote a small preflight that only checks shapes: `messages` + `temperature=0`) is flagged as the wrong API.` noul` / `score` lints clean.`answers` object parses; a chat-completions-shaped mock raises `ValueError: missing answers object`. That is a smoke test of **your client**, not of Microsoft-Decision-1. Scripts live under `runs/16-microsoft-decision-1/` (`preflight.py`, `run_output.txt`). Microsoft says Decision-1 was post-trained from **Qwen3.5-9B**, and that it will **soon rebase** onto other bases including **MAI and OpenAI**. The API shape is supposed to stay put while the weights under it change. Practical consequences: Agent stacks are full of "call an LLM, beg for JSON, parse it." A hosted decision endpoint that returns calibrated probabilities, charges nothing for output, and already sits next to Foundry deployments is a concrete alternative for routing, gating, and grading. It does not replace a generative model for writing. It stops you from using one for a multiple-choice question. Keep Liquid's open d1 for edge and offline. Use Microsoft-Decision-1 when you already live in Azure or OpenRouter. Measure both on the same labeled set before you trust either. *YongBo Yu is an AI engineer in Toronto building LLM workflows and agent systems. More at [yongbo-yu.vercel.app](https://yongbo-yu.vercel.app) and [GitHub](https://github.com/YongBoYu1).*