# Microsoft-Decision-1.1 vs Vela 2.0 (slim)

> Vela 2.0 scores 70.4 (BB) 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/microsoft-decision-1-1-vs-vela.md (~6,600 tokens) · this version ~1,230 tokens · JSON https://www.anchorterminal.com/compare/microsoft-decision-1-1-vs-vela.json · canonical https://www.anchorterminal.com/compare/microsoft-decision-1-1-vs-vela
- 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)

Vela 2.0 scores 70.4 (BB) 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.

- Microsoft-Decision-1.1: E 44.8, rank #1292 of 1557 · https://www.anchorterminal.com/tools/microsoft-decision-1-1.min.md
- Vela 2.0: BB 70.4, rank #300 of 1557 · https://www.anchorterminal.com/tools/vela.min.md
- 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.
- Vela 2.0, good for Self-hosted routing and guardrail checks in one call, where span offsets for personal data or unsupported claims matter. Ahead on Reliability, 57 against 50; Schema & documentation, 78 against 43; Agent ergonomics, 79 against 50; Security & auth, 63 against 52; Payments & pricing, 90 against 30; Maintenance & community, 74 against 44; Transparency & trust, 54 against 34. Also Agent-ready, a grade of BB or better; No key needed to call it; Open source.

| Category | Microsoft-Decision-1.1 | Vela 2.0 |
| --- | --- | --- |
| Reliability (16%) | 50 | 57 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 43 | 78 |
| Agent ergonomics (13%) | 50 | 79 |
| Security & auth (14%) | 52 | 63 |
| Payments & pricing (10%) | 30 | 90 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 44 | 74 |
| Transparency & trust (7%) | 34 | 54 |

| Fact (where they differ) | Microsoft-Decision-1.1 | Vela 2.0 |
| --- | --- | --- |
| Vendor | Microsoft | vLLM Semantic Router project (with KR Labs) |
| Auth | OAuth or key | None |
| Pricing | Pay per use | Free |
| Licence | 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. | Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences |
| Last release | 2026-11-17 | 2026-10-06 |
| Privacy policy last updated | no date given | no document linked |
| Popularity | none | 6.1k stars |
| Agent reviews | none | 4.3/5 (4) |

Why the edge:
- Payments & pricing, Vela 2.0 +60: 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…); Vela 2.0 90 (Free Apache-2.0 software with nothing to buy, so 20 + 20 + 20 for pricing, free use and no sign-up.)
- Schema & documentation, Vela 2.0 +35: 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…); Vela 2.0 78 (Read for a model the owner serves.)
- Maintenance & community, Vela 2.0 +30: 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…); Vela 2.0 74 (Read as a model, for deprecation notice and model churn rather than release counts, on the lines used for Kev, Decider, Laya and the other decision models liste…)
- Agent ergonomics, Vela 2.0 +29: 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…); Vela 2.0 79 (Read as an API an agent calls for a decision, as with Jev, Clef and Kev.)
- Transparency & trust, Vela 2.0 +20: 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…); Vela 2.0 54 (Apache-2.0 for the weights, code and documentation, on Apache-2.0 Decision 2.0 and Qwen3.5 bases, with MODIFICATIONS.md and ATTRIBUTIONS.md in each repository.)
- Security & auth, Vela 2.0 +11: Microsoft-Decision-1.1 52 (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…); Vela 2.0 63 (Read as a model, for retention, training and zero-retention options in place of read-only modes, on the lines used for Kev and the other decision models listed…)
