Head to head · Decision models · October 2026 research run
Decision 3.0 vs Microsoft-Decision-1
Decision 3.0 scores 63.1 (B) on agent readiness against Microsoft-Decision-1's 39 (E), and leads in every scored category. Both do decision models. Microsoft-Decision-1 is cheaper for decision models, $0 against $0 per 1M tokens.
Best decision models for AI agents · All 105 decisions comparisons
Which one, for what
Best for Self-hosted typed decisions over screenshots, documents and short video as well as text, where open weights matter.
Ahead on
- Reliability, 58 against 30
- Schema & documentation, 70 against 43
- Agent ergonomics, 72 against 50
- Payments & pricing, 60 against 20
- Maintenance & community, 82 against 40
- Transparency & trust, 45 against 32
Also in its favour
- No key needed to call it
- Open source
Watch for
Released on 10 October 2026, with five tagged releases of each model by 11 October
Best for Routing, classification, prioritisation and rubric checks over text, where a fixed set of options and a low price per token matter more than generated text.
Also in its favour
- Cheaper for decision models, $0 against $0 per 1M tokens
Watch for
Public preview only. Microsoft's post gives no general availability date and states no licence for the hosted model
Score by category
| Category | Weight this run | Decision 3.0 | Microsoft-Decision-1 | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 58 | 30 | Decision 3.0 +28 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 70 | 43 | Decision 3.0 +27 |
| Agent ergonomics | 13%16.2 | 72 | 50 | Decision 3.0 +22 |
| Security & auth | 14%17.5 | 56 | 52 | Decision 3.0 +4 |
| Payments & pricing | 10%12.5 | 60 | 20 | Decision 3.0 +40 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 82 | 40 | Decision 3.0 +42 |
| Transparency & trust | 7%8.8 | 45 | 32 | Decision 3.0 +13 |
| Negative events | ≤15 | 0 | 0 | |
| Total | B 63.1/100 | E 39/100 |
Facts side by side
| Fact | Decision 3.0 | Microsoft-Decision-1 |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | vLLM Semantic Router Team | Microsoft |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP | HTTP |
| Auth | None | OAuth or key |
| Pricing | Free | Pay per use |
| Price for decision models | free | free |
| x402 | no | no |
| Licence | Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases | Not stated. The announcement and OpenRouter's model page name no licence, and no weights repository was found. |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-11 | 2026-10-09 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | |
| Customer content may train models | ||
| Terms restrict automated access | ||
| Terms restrict benchmarking | ||
| Terms or service can change without notice | ||
| Arbitration or class-action waiver |
Verdicts
Decision 3.0
Open Apache-2.0 decision models that read images and video as well as text and answer several typed questions in one call, with a probability per option and tagged Hub releases. They are two days old, need a GPU and trust_remote_code, drop Vela's set and span types, and publish no calibration figures.
Microsoft-Decision-1
Microsoft publishes $0.042 per million input tokens, with output free, and the model is callable through Microsoft Foundry and OpenRouter. It is in public preview. No licence, model-specific retention statement, rate limit or deprecation policy was found, and the Foundry route needs an Azure deployment and an Entra token. Latency and accuracy figures are Microsoft's claims.
Before you call either
Decision 3.0
- Pin a tag or commit with
revision=when loading from the Hub. Each model had five tagged releases on 10 and 11 October - Send images and videos to
d3_server.pyas base64 data URLs only. The server refuses paths and http URLs with 422 - Set
DECISION_API_KEYbefore binding the bundled server beyond 127.0.0.1. It is open otherwise - Turn on
permutation_average=Truewhen routing must not depend on option order. It is off by default - Expect one request at a time from the bundled server. Use the router's model runtime for queued serving
Microsoft-Decision-1
- Use OpenRouter's Decisions method, not an OpenAI chat-completions SDK. OpenRouter says chat completions SDKs will not work with this model
- On Foundry, send the request to the deployment's /providers/microsoft/v1/systemone path with a Microsoft Entra token for https://cognitiveservices.azure.com/.default, not an API key
- Take the deployment name from the Foundry quickstart before the first call. Microsoft says to confirm the route and authentication header, and the pages reviewed do not give the name
- Keep each request within OpenRouter's 32,768-token context and send only fixed options, since the model is not intended for open-ended generation
- Measure latency and calibration on your own labelled cases before relying on Microsoft's latency and 'nine times out of 10' statements
Questions
Which is better for AI agents, Decision 3.0 or Microsoft-Decision-1?
Decision 3.0 scores 63.1 (B) on agent readiness against Microsoft-Decision-1's 39 (E), and leads in every scored category.
Which is cheaper for decision models, Decision 3.0 or Microsoft-Decision-1?
Decision 3.0, at free against free for Microsoft-Decision-1. These are the vendors' published prices for the job.
Do Decision 3.0 and Microsoft-Decision-1 need an API key?
Decision 3.0 needs no key. Microsoft-Decision-1 takes an API key or an OAuth sign-in.
Can an agent call Decision 3.0 and Microsoft-Decision-1 without installing anything?
No hosted endpoint is listed for Decision 3.0. No hosted endpoint is listed for Microsoft-Decision-1.
Are Decision 3.0 and Microsoft-Decision-1 open source?
Decision 3.0 is open source (Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases). No open-source release is listed for Microsoft-Decision-1.
Other comparisons with Decision 3.0 or Microsoft-Decision-1
- Celeris-1 Decision vs Decision 3.0
- Celeris-1 Decision vs Microsoft-Decision-1
- Clef vs Decision 3.0
- Clef vs Microsoft-Decision-1
- Laya vs Decision 3.0
- Laya vs Microsoft-Decision-1
- Decider vs Decision 3.0
- Decider vs Microsoft-Decision-1
- Decision 3.0 vs GLiClass
- Decision 3.0 vs Kev
- Decision 3.0 vs Liquid d1
- Decision 3.0 vs Drex 1.5
- Decision 3.0 vs OpenAI Decisions API
- Decision 3.0 vs pplx-decider
- Decision 3.0 vs Strands Decider 2B
- Decision 3.0 vs Jev
- Decision 3.0 vs Vela 2.0
- GLiClass vs Microsoft-Decision-1
- Kev vs Microsoft-Decision-1
- Liquid d1 vs Microsoft-Decision-1
- Microsoft-Decision-1 vs Drex 1.5
- Microsoft-Decision-1 vs OpenAI Decisions API
- Microsoft-Decision-1 vs pplx-decider
- Microsoft-Decision-1 vs Strands Decider 2B
- Microsoft-Decision-1 vs Jev
- Microsoft-Decision-1 vs Vela 2.0
Machine-readable
- This page as Markdown
/compare/decision-3-vs-microsoft-decision-1.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/decision-3.json·/api/v1/tools/microsoft-decision-1.json - From a terminal
anchor compare decision-3 microsoft-decision-1(the CLI) - Over MCP
compare_tools {"a": "decision-3", "b": "microsoft-decision-1"}at/mcp, no key