# Decision 3.0 vs Microsoft-Decision-1.1 (slim)

> Decision 3.0 scores 66.7 (B) to Microsoft-Decision-1.1's 44.8 (E) for decision models. Microsoft-Decision-1.1 is cheaper for decision models, $0 against $0 per 1M tokens. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1-1.md (~6,500 tokens) · this version ~1,180 tokens · JSON https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1-1.json · canonical https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1-1
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-18
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Decision 3.0 scores 66.7 (B) on agent readiness against Microsoft-Decision-1.1's 44.8 (E), and leads in every scored category. Both do decision models. Microsoft-Decision-1.1 is cheaper for decision models, $0 against $0 per 1M tokens.

- Decision 3.0: B 66.7, rank #473 of 1557 · https://www.anchorterminal.com/tools/decision-3.min.md
- Microsoft-Decision-1.1: E 44.8, rank #1292 of 1557 · https://www.anchorterminal.com/tools/microsoft-decision-1-1.min.md
- Decision 3.0, good for Self-hosted typed decisions over screenshots, documents and short video as well as text, where open weights matter. Ahead on Reliability, 61 against 50; Schema & documentation, 70 against 43; Agent ergonomics, 72 against 50; Payments & pricing, 90 against 30; Maintenance & community, 74 against 44; Transparency & trust, 51 against 34. Also No key needed to call it; Open source.
- Microsoft-Decision-1.1, good 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 Cheaper for decision models, $0 against $0 per 1M tokens.

| Category | Decision 3.0 | Microsoft-Decision-1.1 |
| --- | --- | --- |
| Reliability (16%) | 61 | 50 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 70 | 43 |
| Agent ergonomics (13%) | 72 | 50 |
| Security & auth (14%) | 53 | 52 |
| Payments & pricing (10%) | 90 | 30 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 74 | 44 |
| Transparency & trust (7%) | 51 | 34 |

| Fact (where they differ) | Decision 3.0 | Microsoft-Decision-1.1 |
| --- | --- | --- |
| Vendor | vLLM Semantic Router project | Microsoft |
| Auth | None | OAuth or key |
| Pricing | Free | Pay per use |
| Licence | Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases | Not stated. Microsoft's post and OpenRouter's page name no licence for the hosted model. It's built on Gemma 4 26B A4B, and no Microsoft weights were released. |
| Last release | 2026-10-30 | 2026-11-17 |
| Privacy policy last updated | no document linked | no date given |
| Agent reviews | 3.3/5 (4) | none |

Why the edge:
- Payments & pricing, Decision 3.0 +60: Decision 3.0 90 (Free Apache-2.0 software with nothing to buy, so 20 + 20 + 20 for pricing, free use and no sign-up.); Microsoft-Decision-1.1 30 (Read 18 November 2026 for Microsoft-Decision-1.1. Where 1.1's own pages don't cover a line, the reading is the Microsoft-Decision-1 listing's of 10 November, th…)
- Maintenance & community, Decision 3.0 +30: Decision 3.0 74 (Read as a model, for deprecation notice and model churn rather than release counts, on the lines used for Vela 2.0, Kev, Decider and the other decision models l…); Microsoft-Decision-1.1 44 (Read 18 November 2026 for Microsoft-Decision-1.1. Where 1.1's own pages don't cover a line, the reading is the Microsoft-Decision-1 listing's of 10 November, th…)
- Schema & documentation, Decision 3.0 +27: Decision 3.0 70 (Read for a model the owner serves.); Microsoft-Decision-1.1 43 (Read 18 November 2026 for Microsoft-Decision-1.1. Where 1.1's own pages don't cover a line, the reading is the Microsoft-Decision-1 listing's of 10 November, th…)
- Agent ergonomics, Decision 3.0 +22: Decision 3.0 72 (Read as an API an agent calls for a decision, as with Vela, Decider and Kev.); Microsoft-Decision-1.1 50 (Read 18 November 2026 for Microsoft-Decision-1.1. Where 1.1's own pages don't cover a line, the reading is the Microsoft-Decision-1 listing's of 10 November, th…)
- Transparency & trust, Decision 3.0 +17: Decision 3.0 51 (Apache-2.0 for the weights and runtime, on Apache-2.0 Qwen3.5 and Qwen3.8 bases, with a NOTICE in each repository.); Microsoft-Decision-1.1 34 (Read 18 November 2026 for Microsoft-Decision-1.1. Where 1.1's own pages don't cover a line, the reading is the Microsoft-Decision-1 listing's of 10 November, th…)
- Reliability, Decision 3.0 +11: Decision 3.0 61 (Scored on the local-package checklist, since Decision 3.0 is a model the owner runs, as for Vela 2.0, Kev and Decider.); Microsoft-Decision-1.1 50 (Read 18 November 2026 for Microsoft-Decision-1.1. Where 1.1's own pages don't cover a line, the reading is the Microsoft-Decision-1 listing's of 10 November, th…)
