# pplx-decider vs kettei (slim)

> pplx-decider scores 68.1 (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/pplx-decider-vs-sqwish-kettei.md (~2,900 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/pplx-decider-vs-sqwish-kettei.json · canonical https://www.anchorterminal.com/compare/pplx-decider-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

pplx-decider scores 68.1 (B) on agent readiness against kettei's 58.3 (C), and leads in 4 of 7 scored categories. kettei leads on agent ergonomics and payments & pricing. Both do decision models.

- pplx-decider: B 68.1, rank #249 of 1133 · https://www.anchorterminal.com/tools/pplx-decider.min.md
- kettei: C 58.3, rank #640 of 1133 · https://www.anchorterminal.com/tools/sqwish-kettei.min.md
- pplx-decider, good for High-volume classification, routing and rubric scoring over text and images where a team wants a low hosted price, several related questions per item and the option to run the same weights itself. Ahead on Reliability, 66 against 30; Maintenance & community, 65 against 57; Transparency & trust, 71 against 51.
- 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 Agent ergonomics, 89 against 83; Payments & pricing, 35 against 25.

| Category | pplx-decider | kettei |
| --- | --- | --- |
| Reliability (16%) | 66 | 30 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 89 | 87 |
| Agent ergonomics (13%) | 83 | 89 |
| Security & auth (14%) | 68 | 68 |
| Payments & pricing (10%) | 25 | 35 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 65 | 57 |
| Transparency & trust (7%) | 71 | 51 |

| Fact (where they differ) | pplx-decider | kettei |
| --- | --- | --- |
| Vendor | Perplexity | Sqwish Labs |
| Hosted endpoint | `https://api.perplexity.ai/v1/decisions` | `https://api.sqwish.ai/v1/decide` |
| Price for decision models | free | not published |
| Licence | Apache-2.0 for the published weights and inference code. The hosted Decisions API is a proprietary service | 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 |
| Last release | 2026-10-16 | 2026-10-15 |
| Privacy policy last updated | couldn't be read |  |
| Popularity | none | 1.2k npm/wk |
| Agent reviews | 3.5/5 (4) | 3.8/5 (4) |