# Decider vs ScaleDown (slim)

> Decider scores 69.5 (B) to ScaleDown's 48.6 (D) for decision models. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/decider-vs-scaledown.md (~2,650 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/decider-vs-scaledown.json · canonical https://www.anchorterminal.com/compare/decider-vs-scaledown
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-15
- Licence: CC BY 4.0, credit Anchor Terminal (anchorterminal.com) and link this page when you pass anything on

Decider scores 69.5 (B) on agent readiness against ScaleDown's 48.6 (D), and leads in 5 of 7 scored categories. ScaleDown leads on security & auth and transparency & trust. Both do decision models.

- Decider: B 69.5, rank #190 of 1094 · https://www.anchorterminal.com/tools/decider.min.md
- ScaleDown: D 48.6, rank #880 of 1094 · https://www.anchorterminal.com/tools/scaledown.min.md
- Decider, good for Local classification, routing, triage and checks where a team wants open weights in several sizes and a Jev-shaped route. Ahead on Reliability, 90 against 20; Schema & documentation, 78 against 69; Payments & pricing, 60 against 40; Maintenance & community, 87 against 56. Also No key needed to call it; Open source.
- 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 Security & auth, 48 against 38; Transparency & trust, 54 against 46. Also A hosted endpoint, with nothing to install; Free to start without a card.

| Category | Decider | ScaleDown |
| --- | --- | --- |
| Reliability (16%) | 90 | 20 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 78 | 69 |
| Agent ergonomics (13%) | 80 | 76 |
| Security & auth (14%) | 38 | 48 |
| Payments & pricing (10%) | 60 | 40 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 87 | 56 |
| Transparency & trust (7%) | 46 | 54 |

| Fact (where they differ) | Decider | ScaleDown |
| --- | --- | --- |
| Vendor | Mark Marosi (Mapika) | Carbon ScaleDown, Inc. |
| Hosted endpoint | no (local only) | `https://api.scaledown.xyz` |
| Auth | None | API key |
| Pricing | Free | Pay per use |
| Licence | Apache-2.0 (code and weights) | Proprietary hosted models under ScaleDown's Terms of Service. The langchain-scaledown integration is MIT |
| llms.txt | no | yes |
| Last release | 2026-10-07 | 2026-10-14 |
| Terms last updated | no document linked | couldn't be read |
| Privacy policy last updated | no document linked | 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 | 1.1k stars, 2.7k PyPI/wk | 0 stars |