Model tracker / Decision models / Microsoft
Microsoft-Decision-1
Microsoft-Decision-1 is a closed decision model from Microsoft: it answers typed questions, such as yes or no, pick one or pick several, with probabilities instead of writing text. It costs $0.042 per million input tokens (Microsoft Foundry, OpenRouter, Vercel AI Gateway), and output is free. It scores 70.8 on the independent JevBench Capability Score (board v1.7.46), where Jev, the reference, scores 77.1.
- Made by
- Microsoft
- Weights
- Closed
- Size
- 9B (post-trained Qwen3.5-9B)
- Where
- Microsoft Foundry, OpenRouter, Vercel AI Gateway
- Images
- No, text only
- Context
- 32,768 (OpenRouter)
- Fine-tuning
- Not stated
Microsoft-Decision-1 price
US dollars per million input tokens. Decision models don't write text, so none of the hosted ones charge for output.
| Where | Input | Output | Notes | Checked |
|---|---|---|---|---|
| Microsoft Foundry, OpenRouter, Vercel AI Gateway | $0.042 | Free | Output is free. Microsoft has not released the weights. | 2026-10-14 |
Microsoft-Decision-1 benchmarks
| Benchmark | Result | What it measures | Reported by |
|---|---|---|---|
| JevBench v1.7.46 | 70.8 | Capability Score: accuracy and calibration on typed decisions, with Jev as the reference system | Independent |
| JevBench time | 0.46 s | Seconds per decision: measured end to end for hosted APIs, the board's estimate for self-hosted models | Independent |
| Reported speed | 85 ms median, 125 ms p95, measured through Foundry | Latency on the maker's own hardware | Microsoft |
Makers' speeds are measured on their own hardware and aren't comparable with each other or with JevBench's timings.
Decision models like Microsoft-Decision-1
Every other decision model we track, by independent JevBench score.
| Model | Input / M | JevBench | Weights |
|---|---|---|---|
| Microsoft-Decision-1 | $0.042 | 70.8 | Closed |
| Jev 1.13 TypeSafe AI | $0.042 | 77.1 | Closed |
| Clef Cloudflare | $0.24 | 75.3 | Open |
| d1 Liquid AI | $0.04 | 74.4 | Closed |
| OpenAI Decisions (GPT-6 Luna) OpenAI | $0.10 | 73.5 | Closed |
| Clef-flash Cloudflare | $0.038 | 63.8 | Open |
| Clef-omni Cloudflare | $0.15 | 58.3 | Open |
| d1-3B Liquid AI | Self-host | 49.5 | Open |
| d1-omni-600M (experimental) Liquid AI | Self-host | 32.8 | Open |
| Laya Convai Innovations | Free | 32.5 | Open |
| CLM-8B Stanford and NVIDIA | Self-host | 20.1 | Open |
| Strands Decider 2B AWS Strands Labs | Self-host | – | Open |
Compare them all in the decision models table →
Microsoft-Decision-1 on dbggr
- Haiku 5.5 and four-cent decision models: the AI price war reaches the bottom tier Saturday edition, 2026-10-10
- Microsoft enters decision models at Jev's price as TypeSafe raises $870M Daily, 2026-10-09
Microsoft-Decision-1 FAQ
How much does Microsoft-Decision-1 cost?
Microsoft-Decision-1 costs $0.042 per million input tokens at Microsoft Foundry, OpenRouter, Vercel AI Gateway. Output is free. Microsoft has not released the weights. Checked 14 October 2026.
Is Microsoft-Decision-1 open weight?
No. Microsoft-Decision-1 is only available through Microsoft Foundry, OpenRouter, Vercel AI Gateway.
How fast is Microsoft-Decision-1?
Microsoft reports 85 ms median, 125 ms p95, measured through Foundry, measured on its own hardware. JevBench gives 0.46 seconds per decision, measured end to end.
How does Microsoft-Decision-1 compare with Jev?
On JevBench's Capability Score (board v1.7.46), Microsoft-Decision-1 scores 70.8 against Jev's 77.1. Jev costs $0.042 per million input tokens; Microsoft-Decision-1 costs $0.042. JevBench is a one-person project that uses Jev as its reference, which favours cheap hosted models.