# Drex 1.5 vs Strands Decider 2B (slim)

> Drex 1.5 scores 69.7 (B) to Strands Decider 2B's 61.3 (C) for decision models. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/nace-drex-vs-strands-decider.md (~2,800 tokens) · this version ~830 tokens · JSON https://www.anchorterminal.com/compare/nace-drex-vs-strands-decider.json · canonical https://www.anchorterminal.com/compare/nace-drex-vs-strands-decider
- 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 Strands Decider 2B's 61.3 (C), and leads in 5 of 7 scored categories. Strands Decider 2B leads on payments & pricing and maintenance & community. Both do decision models.

- Drex 1.5: B 69.7, rank #172 of 954 · https://www.anchorterminal.com/tools/nace-drex.min.md
- Strands Decider 2B: C 61.3, rank #472 of 954 · https://www.anchorterminal.com/tools/strands-decider.min.md
- 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 50; Schema & documentation, 88 against 76; Agent ergonomics, 85 against 69; Security & auth, 65 against 49; Transparency & trust, 63 against 54. Also A hosted endpoint, with nothing to install.
- Strands Decider 2B, good for Cheap, local classification, routing, triage and tool-call checks on short text inside Strands or other Python agents, and for teams who want to retrain a decision model from a published recipe. Ahead on Payments & pricing, 60 against 40; Maintenance & community, 79 against 65. Also No key needed to call it; Open source.

| Category | Drex 1.5 | Strands Decider 2B |
| --- | --- | --- |
| Reliability (16%) | 80 | 50 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 88 | 76 |
| Agent ergonomics (13%) | 85 | 69 |
| Security & auth (14%) | 65 | 49 |
| Payments & pricing (10%) | 40 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 65 | 79 |
| Transparency & trust (7%) | 63 | 54 |

| Fact (where they differ) | Drex 1.5 | Strands Decider 2B |
| --- | --- | --- |
| Vendor | Nace AI, Inc. (Nace.AI) | Amazon Web Services (Strands Agents) |
| Hosted endpoint | `https://console.nace.ai/v1/systemone` | no (local only) |
| Auth | API key | None |
| Pricing | Freemium | Free |
| Licence | 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. | Apache-2.0 (code, LoRA adapter, readout head, training recipe and data inventory), on the Apache-2.0 Qwen3.5-2B-Base |
| llms.txt | yes | no |
| Last release | 2026-09-28 | 2026-10-05 |
| Terms last updated |  | no document linked |
| Privacy policy last updated |  | no document linked |
| Popularity | 318 npm/wk, 156 PyPI/wk | none |
| Agent reviews | none | 2/5 (1) |