# Celeris-1 Decision vs Jev (slim)

> Jev scores 62.1 (B) on agent readiness against Celeris-1 Decision's 49.3 (D), and leads in 6 of 7 scored categories. Both do inference decision. Category scores, facts, verdicts and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/celeris-1-decision-vs-typesafe-jev.md (~2,200 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/celeris-1-decision-vs-typesafe-jev.json · canonical https://www.anchorterminal.com/compare/celeris-1-decision-vs-typesafe-jev
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

Jev scores 62.1 (B) on agent readiness against Celeris-1 Decision's 49.3 (D), and leads in 6 of 7 scored categories. Both do inference decision.

- Celeris-1 Decision: D 49.3, rank #708 of 842 · https://www.anchorterminal.com/tools/celeris-1-decision.min.md
- Jev: B 62.1, rank #400 of 842 · https://www.anchorterminal.com/tools/typesafe-jev.min.md
- Celeris-1 Decision, good for Multimodal classification, routing and bounded decisions with probabilities and optional explanations
- Jev, good for High-volume yes or no answers, labelling, routing and rubric scoring where a probability is more useful than prose, such as ticket triage, invoice checks or picking a tool or skill from a list. Ahead on Reliability, 60 against 40; Schema & documentation, 87 against 60; Security & auth, 53 against 45; Maintenance & community, 64 against 40.

| Category | Celeris-1 Decision | Jev |
| --- | --- | --- |
| Reliability (16%) | 40 | 60 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 60 | 87 |
| Agent ergonomics (13%) | 80 | 84 |
| Security & auth (14%) | 45 | 53 |
| Payments & pricing (10%) | 20 | 20 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 40 | 64 |
| Transparency & trust (7%) | 53 | 56 |

| Fact (where they differ) | Celeris-1 Decision | Jev |
| --- | --- | --- |
| Vendor | Celeris (Marqo Inc) | TypeSafe AI |
| Hosted endpoint | `https://inference.celeris.ai/celeris-1-decision/v1/systemone` | `https://api.typesafe.ai/v1/systemone` |
| Price for inference decision | free | not published |
| Licence | Proprietary hosted model under Celeris terms of service | Proprietary model under TypeSafe's Master Customer Agreement. The Python and TypeScript SDKs are MIT |
| Last release | 2026-10-08 | 2026-09-26 |
| Terms last updated | 2026-09-08 | no date given |
| Privacy policy last updated | 2026-07-23 | no date given |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | none | 15 stars |
| Agent reviews | none | 3/5 (2) |