All models
Microsoft
Microsoft-Decision-1
Microsoft's decision model for sorting requests, choosing a route and scoring results without generating a chat response.
Plain-English overview
What Microsoft-Decision-1 actually is
Microsoft-Decision-1 reads text or JSON and evaluates questions with answers you define. It returns choices, scores and probabilities that your application can act on or send for human review.
Built on Qwen3.5-9B, it is a specialist for bounded decisions rather than writing or conversation. Compare it with Clef and Jev using the same examples, error costs and review thresholds.
Good fit for
- Support ticket classification and routing
- Grading AI responses against a rubric
- Agent decisions with human escalation
Category comparison
The facts that matter for decision models
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
- Input price
- $0.042 / 1M input tokens; output freeCurrent provider price for the text or structured state submitted to the model, including whether decision outputs are billed.
- Input capacity
- 32,768 tokensMaximum documented state and question capacity for one request.
- Decision types
- Choice, Score, and Noul probability questionsThe bounded question forms the model can answer, such as choices, scores, or probabilities.
- Output contract
- Typed JSON decisions defined before inferenceHow the response is constrained for direct use by application code.
- Uncertainty
- Probabilities for each option; validate thresholds on your own dataWhether the endpoint exposes probabilities, confidence, or another calibrated signal.
- Where to use it
- Microsoft Foundry and OpenRouterCurrent API, SDK, playground, and access-stage information.
API and provider access
Where to get Microsoft-Decision-1
Microsoft FoundryMicrosoft-Decision-1 model catalogModel card, deployment access and supported input limits.Microsoft FoundryDecision API guideCall /providers/microsoft/v1/systemone using your deployment name and Entra ID or an API key.OpenRouterMicrosoft-Decision-1 on OpenRouterRouter model ID: microsoft/microsoft-decision-1. Check provider-specific terms and pricing.
Availability
Regions and access stage
Available through Microsoft Foundry and OpenRouter.
Foundry supports GlobalStandard and selected DataZoneStandard deployments. Global inference can cross regions; DataZone keeps processing within its zone. Confirm current region and account access.
Check live availabilityData and training
The route matters.
Microsoft says Foundry inputs and outputs are not used to train foundation models without permission. Abuse monitoring can retain flagged content for review. Confirm retention and residency for your deployment; OpenRouter adds its own data-handling terms.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
Microsoft-Decision-1 FAQ
What is Microsoft-Decision-1?
Microsoft's decision model for sorting requests, choosing a route and scoring results without generating a chat response. Microsoft-Decision-1 reads text or JSON and evaluates questions with answers you define. It returns choices, scores and probabilities that your application can act on or send for human review.
When was Microsoft-Decision-1 released?
Microsoft-Decision-1 was released on October 9, 2026 according to the cited provider materials.
Where can I access Microsoft-Decision-1?
Available through Microsoft Foundry and OpenRouter. The access routes listed in this guide are Microsoft Foundry and OpenRouter.
How much does Microsoft-Decision-1 cost?
$0.042 / 1M input tokens; output free. Microsoft and OpenRouter list the same input rate and no output charge. Confirm your Azure agreement or router fees before budgeting; other services cost extra.
Where is Microsoft-Decision-1 available?
Available through Microsoft Foundry and OpenRouter. Foundry supports GlobalStandard and selected DataZoneStandard deployments. Global inference can cross regions; DataZone keeps processing within its zone. Confirm current region and account access.
Is my Microsoft-Decision-1 API data used for training?
Microsoft says Foundry inputs and outputs are not used to train foundation models without permission. Abuse monitoring can retain flagged content for review. Confirm retention and residency for your deployment; OpenRouter adds its own data-handling terms. The policy belongs to the provider route and account terms, so verify it again before production use.
Related comparisons
Head-to-head comparisons
Microsoft-Decision-1 vs Clef
Cloudflare's larger decision model for classifying information and choosing an action without generating a chat response.
Open full comparisonMicrosoft-Decision-1 vs Clef-flash
A smaller Cloudflare decision model for frequent routing and classification tasks, with a lower input-token price than Clef.
Open full comparisonMicrosoft-Decision-1 vs Jev 1.13
TypeSafe AI's first System One model for fast, typed choices, scores, and probabilities that software can use directly.
Open full comparison
