HOSTED

Microsoft-Decision-1

Q: What is Microsoft-Decision-1 by Microsoft?

Microsoft-Decision-1 : Microsoft's decision-scoring model for routing, classification, prioritisation, verification and workflow control. Microsoft-Decision-1 facts · Source: commandline.microsoft.com ↗

Q: How much does Microsoft-Decision-1 cost?

Microsoft-Decision-1 : Published price (vendor-reported): $0.042 per million input tokens; output free Microsoft-Decision-1 facts · Source: commandline.microsoft.com ↗

Q: Who makes Microsoft-Decision-1?

Microsoft-Decision-1 : Microsoft Microsoft-Decision-1 facts · Source: commandline.microsoft.com ↗

Microsoft-Decision-1 scores decisions and is post-trained from Qwen3.5-9B. Its listed price is $0.042 per million input tokens, output free.

By Microsoft · Released 9 Oct 2026

Microsoft's decision-scoring model for routing, classification, prioritisation, verification and workflow control. Post-trained from Qwen3.5-9B, available in Microsoft Foundry and on OpenRouter.

Quick answers

What is Microsoft-Decision-1 by Microsoft?

Microsoft-Decision-1: Microsoft's decision-scoring model for routing, classification, prioritisation, verification and workflow control.

Microsoft-Decision-1 facts · Source: commandline.microsoft.com ↗

How much does Microsoft-Decision-1 cost?

Microsoft-Decision-1: Published price (vendor-reported): $0.042 per million input tokens; output free

Microsoft-Decision-1 facts · Source: commandline.microsoft.com ↗

Who makes Microsoft-Decision-1?

Microsoft-Decision-1: Microsoft

Microsoft-Decision-1 facts · Source: commandline.microsoft.com ↗

Facts

Price: $0.042 per million input tokens; output free · Compare prices
Base: Qwen3.5-9B
Access: Microsoft Foundry, OpenRouter

Claims and sources

Ties GLiDE for second on Artificial Analysis's Decision Index at launch, on 54 (13 Oct 2026) independentsource

Links

Source: Announcement →

Related projects

Contract-review judge test

Source: james-tn/decision-model-contract-judge-eval ↗

Tests Microsoft-Decision-1 and a frontier reasoning model as contract-review judges on 2,091 ContractNLI and 1,224 CUAD judgments. Decision-1 with rules scores 82.9% and 90.0% accuracy. It reads overlapping chunks while the frontier model reads whole documents; added rules and confidence definitions differ. This is one author’s field test.

james-tn · ★ 0 · MIT · Microsoft-Decision-1

evaluation

Published author-run records, checked 5 Nov 2026; not reproduced in this scan.

Source: Licence file → Source: Integration code → Source: Published run →

All projects · Back to the model registry