Fixed-option probability scoring
Accepts fixed options and returns a calibrated probability for each in a single pass.
Loading page…
Automation / product dossier
Scores fixed options with calibrated probabilities for routing, classification, verification and agent control
Product brief
Microsoft-Decision-1 is a decision-scoring model for routing, classification, verification and agent control. Give it fixed options and it returns a calibrated probability for each in a single pass, as structured output software can act on directly. Post-trained from Qwen3.5-9B, it is about 35x faster than GPT-6 Sol at median latency, per Microsoft. Available now in Microsoft Foundry at $0.042 per million input tokens, with free output.
Why we selected it
A specialized model for software-actionable decisions rather than general chat. Structured probability outputs, explicit pricing and availability in Microsoft Foundry make it useful for builders implementing routing and.
Product preview saved with our daily selection
Capability scan
Only capabilities supported by the product information we collected are listed here.
Accepts fixed options and returns a calibrated probability for each in a single pass.
Produces structured output that software can act on directly rather than relying on conversational responses.
Supports decision scoring for routing and classification tasks.
Supports verification decisions and control decisions in agent workflows.
Best-fit use cases
FAQ
Given fixed options, it returns a calibrated probability for each option in a single pass, using structured output software can act on directly.
It is a specialized decision-scoring model for routing, classification, verification and agent control, rather than general chat.
The supplied description lists availability in Microsoft Foundry at $0.042 per million input tokens, with free output.
Microsoft-Decision-1 was post-trained from Qwen3.5-9B.