cd /news/artificial-intelligence/new-model-available · home › topics › artificial-intelligence › article
[ARTICLE · art-171680] src=zenmux.ai ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

New Model Available:

Microsoft released Microsoft-Decision-1.1, a successor to Microsoft-Decision-1 that returns a calibrated probability for each fixed answer option instead of generating text, letting applications act, defer, or ask for review based on the model's own confidence. Microsoft positions the model for classification, routing, prioritization, verification, workflow control, agent guardrails, and AI judging, and states it is not intended for open-ended generation, conversation, translation, or summarization. The model is listed with multi-provider routing, 24-hour uptime and latency figures, benchmarks sourced from Artificial Analysis, and traffic analytics showing which public apps send it the most requests.

key takeaway

Microsoft-Decision-1.1 returns a calibrated probability per fixed answer option rather than generated text, so applications can branch on confidence to act, defer, or request human review.

read1 min views5 publishedNov 18, 2026
New Model Available:
Image: Zenmux (auto-discovered)

Microsoft-Decision-1.1 is a model from Microsoft built for fast decision-making, and the successor to Microsoft-Decision-1. Instead of generating text, it reads the provided content and returns a calibrated probability for each fixed answer option, so the response carries its own confidence and can determine when an application acts, defers, or asks for review. It is suited to classification, routing, prioritization, verification, workflow control, agent guardrails, and AI judging. It is not intended for open-ended generation, conversation, translation, or summarization.

Back to Models

Providers #

Route requests across multiple providers. Copy a provider slug to set your preference.

Uptime #

24hours Direct request success rate on AI Gateway and per-provider.

Latency #

24hours P50 whole response time on live AI Gateway traffic, in milliseconds.

Activity #

Token volume and request traffic to this model over time.

Benchmarks #

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced fromArtificial Analysis

Apps #

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for. View All

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @microsoft 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/new-model-available] indexed:0 read:1min 2026-11-18 · —