# Microsoft-Decision-1 vs ScaleDown (slim)

> ScaleDown scores 48.6 (D) to Microsoft-Decision-1's 38.8 (E) for decision models. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/microsoft-decision-1-vs-scaledown.md (~2,800 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/microsoft-decision-1-vs-scaledown.json · canonical https://www.anchorterminal.com/compare/microsoft-decision-1-vs-scaledown
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-14
- Licence: CC BY 4.0, credit Anchor Terminal (anchorterminal.com) and link this page when you pass anything on

ScaleDown scores 48.6 (D) on agent readiness against Microsoft-Decision-1's 38.8 (E), and leads in 5 of 7 scored categories. Microsoft-Decision-1 leads on reliability. Both do decision models.

- Microsoft-Decision-1: E 38.8, rank #999 of 1084 · https://www.anchorterminal.com/tools/microsoft-decision-1.min.md
- ScaleDown: D 48.6, rank #873 of 1084 · https://www.anchorterminal.com/tools/scaledown.min.md
- Microsoft-Decision-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. Ahead on Reliability, 30 against 20.
- ScaleDown, good for Cheap, high-volume labelling, routing and yes or no checks where a probability is more useful than prose, and for pulling described fields with offsets from text, images or PDFs. Ahead on Schema & documentation, 69 against 43; Agent ergonomics, 76 against 50; Payments & pricing, 40 against 20; Maintenance & community, 56 against 40; Transparency & trust, 54 against 29. Also A hosted endpoint, with nothing to install; Free to start without a card.

| Category | Microsoft-Decision-1 | ScaleDown |
| --- | --- | --- |
| Reliability (16%) | 30 | 20 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 43 | 69 |
| Agent ergonomics (13%) | 50 | 76 |
| Security & auth (14%) | 52 | 48 |
| Payments & pricing (10%) | 20 | 40 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 40 | 56 |
| Transparency & trust (7%) | 29 | 54 |

| Fact (where they differ) | Microsoft-Decision-1 | ScaleDown |
| --- | --- | --- |
| Vendor | Microsoft | Carbon ScaleDown, Inc. |
| Hosted endpoint | no (local only) | `https://api.scaledown.xyz` |
| Auth | OAuth or key | API key |
| Price for decision models | free | not published |
| Licence | Not stated. The announcement and OpenRouter's model page name no licence, and no weights repository was found. | Proprietary hosted models under ScaleDown's Terms of Service. The langchain-scaledown integration is MIT |
| llms.txt | no | yes |
| Last release | 2026-10-09 | 2026-10-14 |
| Terms last updated | no document linked | couldn't be read |
| Privacy policy last updated | no date given | couldn't be read |
| Customer content may train models |  | couldn't be read |
| Terms restrict automated access |  | couldn't be read |
| Terms restrict benchmarking |  | couldn't be read |
| Terms or service can change without notice |  | couldn't be read |
| Arbitration or class-action waiver |  | couldn't be read |
| Popularity | none | 0 stars |