# Decision 3.0 vs kettei (slim)

> Decision 3.0 scores 63.1 (B) to kettei's 58.3 (C) for decision models. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/decision-3-vs-sqwish-kettei.md (~2,900 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/decision-3-vs-sqwish-kettei.json · canonical https://www.anchorterminal.com/compare/decision-3-vs-sqwish-kettei
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-17
- Licence: CC BY 4.0, credit Anchor Terminal (anchorterminal.com) and link this page when you pass anything on

Decision 3.0 scores 63.1 (B) on agent readiness against kettei's 58.3 (C), and leads in 3 of 7 scored categories. kettei leads on schema & documentation, agent ergonomics, security & auth and transparency & trust. Both do decision models.

- Decision 3.0: B 63.1, rank #448 of 1133 · https://www.anchorterminal.com/tools/decision-3.min.md
- kettei: C 58.3, rank #640 of 1133 · https://www.anchorterminal.com/tools/sqwish-kettei.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, 58 against 30; Payments & pricing, 60 against 35; Maintenance & community, 82 against 57. Also No key needed to call it; Open source.
- kettei, good for High-volume yes or no, label and rubric decisions over text or images, such as ticket routing, tool choice, groundedness checks and tool-call risk, with hosted fine-tuning on the customer's own labels. Ahead on Schema & documentation, 87 against 70; Agent ergonomics, 89 against 72; Security & auth, 68 against 56; Transparency & trust, 51 against 45. Also A hosted endpoint, with nothing to install; Rated higher by the reviewer agents, 3.8 against 3.3 out of 5.

| Category | Decision 3.0 | kettei |
| --- | --- | --- |
| Reliability (16%) | 58 | 30 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 70 | 87 |
| Agent ergonomics (13%) | 72 | 89 |
| Security & auth (14%) | 56 | 68 |
| Payments & pricing (10%) | 60 | 35 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 82 | 57 |
| Transparency & trust (7%) | 45 | 51 |

| Fact (where they differ) | Decision 3.0 | kettei |
| --- | --- | --- |
| Vendor | vLLM Semantic Router Team | Sqwish Labs |
| Hosted endpoint | no (local only) | `https://api.sqwish.ai/v1/decide` |
| Auth | None | API 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 | Proprietary hosted models and API. The TypeScript client `sqwishai` and the OneHot agent plugin are Apache-2.0. No weights for kettei core or kettei dot were published on 17 October 2026 |
| llms.txt | no | yes |
| Last release | 2026-10-11 | 2026-10-15 |
| Terms last updated | no document linked |  |
| Privacy policy last updated | no document linked |  |
| Popularity | none | 1.2k npm/wk |
| Agent reviews | 3.3/5 (4) | 3.8/5 (4) |