Microsoft Decision 1

by Microsoft

Released 666 days after Phi-4 · Announcement · All Microsoft releases

Microsoft Decision 1 is Microsoft's decision-scoring model, post-trained from Alibaba's Qwen3.5-9B. Given a situation and a question with predefined answer options, it returns a calibrated probability for each option in a single pass instead of generating text. It supports yes/no, multiple-choice, rating and rubric-based questions over text inputs of up to 32K tokens. Use it to classify and route requests, prioritize workflow items, check proposed agent actions, or grade AI responses against criteria and evidence you provide. Its probabilities let an application set thresholds for automatic action and escalate uncertain cases. Include an explicit option such as "cannot tell" when the evidence may be insufficient. The model does not generate explanations, answer open-ended questions or look beyond the supplied input for missing knowledge. It is text-only, and Microsoft does not design or evaluate it as the sole automated decision-maker for consequential decisions about people.

Call Microsoft Decision 1 on Opper through the System One evaluation API. Sign up without a credit card. Get started

Key info

Input
Output
Features
Context window
33K
Max output
—
Input price
$0.04 /1M
Output price
$0 /1M
Released
  • EU residency available
  • Zero data retention with abuse monitoring
  • No training by default
  • GDPR DPA available

Available routes

Microsoft Decision 1 runs on 2 different routes through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below. In the EU it is served by Azure. See every model hosted in the EU.

ProviderRegionZero data retentionTrainingInputOutputCache read
EUNo$0.04$0Input price
MultiNo$0.04$0Input price

Live routes and prices as JSON: api.opper.ai/v3/models?q=azure%3Aeu%2Fmicrosoft-decision-1

Uptime and availability

Microsoft Decision 1 runs on a single route through the Opper gateway today, so its availability is that provider's availability.

99.27%route uptime, last 30 days
Single route, no failover target within this model.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting Microsoft Decision 1 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Azure — EU🇪🇺

Zero data retention with abuse monitoring: nothing is logged or used for training; content flagged by abuse monitoring is held for review. No training on customer data. EU; DPA available.

Zero data retention
With abuse monitoring, flagged content held.
Training
No training on customer data.
Logging
None
Abuse monitoring
On by default, holds flagged content, stored in Sweden, a person can view samples
GDPR DPA
DPA available
Transfer mechanism
Not applicable — data stays in EU

Azure — Multi-region

Zero data retention with abuse monitoring: nothing is logged or used for training; content flagged by abuse monitoring is held for review. No training on customer data. GLOBAL; unknown; DPA available.

Zero data retention
With abuse monitoring, flagged content held.
Training
No training on customer data.
Logging
None
Abuse monitoring
On by default, holds flagged content, stored in Sweden, a person can view samples
GDPR DPA
DPA available
Transfer mechanism
unknown

Best for

The model directory pages that list Microsoft Decision 1.

Benchmarks

Microsoft Decision 1 played 100 games of Pac-Man against the four arcade ghosts.

JevMan: the Pac-Man benchmark for AI decision models

Watch Microsoft Decision 1's JevMan game
Rank in our runs10 of 15
Mean score2,390
Best game4,420
Games100
See the JevMan benchmark →Compare all decision modelsScores from Opper's own runs. Updated Oct 24, 2026.

Get started

Call Microsoft Decision 1 through the Opper gateway with one API key. Evaluate state against typed questions using TypeSafe’s System One API for yes/no decisions, classification, and rubric scoring.

See the Opper evaluation guide and the TypeSafe API reference for question types and response formats. Compare every decision model, on one API.

Microsoft Decision 1 is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

curl https://api.opper.ai/v3/compat/v1/systemone \
-H "Authorization: Bearer $OPPER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "azure:eu/microsoft-decision-1",
"state": "The customer cannot sign in and needs help immediately.",
"questions": {
"is_urgent": {
"type": "noul",
"instructions": "Does the customer need urgent help?"
}
}
}'

Use Microsoft Decision 1 in your apps

Pick your tool, then choose Microsoft Decision 1 to see how to run it through Opper.

Compare Microsoft Decision 1 with…

Side-by-side on privacy, EU hosting, pricing, and benchmarks.

Other models from Microsoft

Start building with 700+ models

One API key for every major provider, up and running in minutes.

Get startedView Documentation