Nace AI's Drex 2.0: a 35B decision-only model with 3B active params beats Jev on Decision Index
techNmak · x · 2026-10-13
- Nace AI launched Drex 2.0, a decision-only model (no text generation) with 35B total and only 3B active parameters, which outscored Jev on the Decision Index.
- Claims up to 38% faster inference vs Drex 1.5 on 32K–128K inputs, priced at $0.06 per 1M input tokens, running on SGLang with Day 0 Fireworks AI support and a $25 signup bonus.
- Notable demo: in a New York delivery simulation, the model re-picks warehouses as road closures, equipment failures and recalls unfold.
- The author argues specialized decision models embedded inside agents are a direction to watch.
- Nace also offers NDI document intelligence; Parse Index shows Drex 1.5 on the cost-accuracy Pareto frontier.
More from coding & agent
- Meta launches Muse Wonder, its largest frontier model built for agents — ZeroStateReflex · 2026-10-13
- HeyGen launches Lessons: turn class notes into videos via MCP — HeyGen · 2026-10-13
- PageIndex SDK v0.4 claims tree indexing now cheaper than vector indexing by ~15% — solyarisoftware · 2026-10-13
- Economist: agentic coding lets you write your own Fortran optimizers, not just ask for Stata packages — Apoorva__Lal · 2026-10-13
- Tencent open-sources Agent Memory: local long-term memory, 61% fewer tokens, 48%→76% accuracy — solyarisoftware · 2026-10-13
- Testing AI agents with simulations: replay real traces, 50 curated sims beat 1000 random ones — HamelHusain · 2026-10-13