# Celeris-1 Decision vs Drex 1.5 (slim)

> Drex 1.5 scores 69.7 (B) to Celeris-1 Decision's 49.3 (D) for decision models. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/celeris-1-decision-vs-nace-drex.md (~2,650 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/celeris-1-decision-vs-nace-drex.json · canonical https://www.anchorterminal.com/compare/celeris-1-decision-vs-nace-drex
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-10

Drex 1.5 scores 69.7 (B) on agent readiness against Celeris-1 Decision's 49.3 (D), and leads in every scored category. Both do decision models.

- Celeris-1 Decision: D 49.3, rank #798 of 954 · https://www.anchorterminal.com/tools/celeris-1-decision.min.md
- Drex 1.5: B 69.7, rank #172 of 954 · https://www.anchorterminal.com/tools/nace-drex.min.md
- Celeris-1 Decision, good for Multimodal classification, routing and bounded decisions with probabilities and optional explanations
- Drex 1.5, good for Routing, triage and yes or no gates inside an agent, where the caller supplies the options and acts on the probabilities. Suited to hosted use at a low per-token price, or to open weights where the licence fits. Ahead on Reliability, 80 against 40; Schema & documentation, 88 against 60; Agent ergonomics, 85 against 80; Security & auth, 65 against 45; Payments & pricing, 40 against 20; Maintenance & community, 65 against 40; Transparency & trust, 63 against 53.

| Category | Celeris-1 Decision | Drex 1.5 |
| --- | --- | --- |
| Reliability (16%) | 40 | 80 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 60 | 88 |
| Agent ergonomics (13%) | 80 | 85 |
| Security & auth (14%) | 45 | 65 |
| Payments & pricing (10%) | 20 | 40 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 40 | 65 |
| Transparency & trust (7%) | 53 | 63 |

| Fact (where they differ) | Celeris-1 Decision | Drex 1.5 |
| --- | --- | --- |
| Vendor | Celeris (Marqo Inc) | Nace AI, Inc. (Nace.AI) |
| Hosted endpoint | `https://inference.celeris.ai/celeris-1-decision/v1/systemone` | `https://console.nace.ai/v1/systemone` |
| Pricing | Pay per use | Freemium |
| Price for decision models | free | not published |
| Licence | Proprietary hosted model under Celeris terms of service | Hosted API under the Nace AI Terms of Service, last updated 5 May 2026. Weights under the Nace AI Open RAIL-M licence (modified, version 1.0, October 2026), which is not an open-source licence. Businesses above $1 million in revenue or funding need a separate commercial licence, and competing products are excluded. The bundled code/kev package, derived from Jared Palmer's Kev (https://github.com/jaredpalmer/kev), and the GitHub repository are Apache-2.0, and the agent skill is MIT. |
| Last release | 2026-10-08 | 2026-09-28 |
| Terms last updated | 2026-09-08 |  |
| Privacy policy last updated | 2026-07-23 |  |
| Customer content may train models | not found in the text |  |
| Terms restrict automated access | not found in the text |  |
| Terms restrict benchmarking | yes |  |
| Terms or service can change without notice | not found in the text |  |
| Arbitration or class-action waiver | not found in the text |  |
| Popularity | none | 318 npm/wk, 156 PyPI/wk |