Decision 1.0 is the vLLM Semantic Router project's open model family. Six models were announced on 22 Sep 2026, with sizes from 0.6B to 9B.
By vLLM Semantic Router · Released 22 Sep 2026
Open decision models from the vLLM Semantic Router project, published as "Decision 1.0: towards open decision foundation models". Six were announced on 22 Sep. The follow-up, Decision 3.0 (d3), is Apache-2.0 and reads text, images and video, with sizes up to 27B.
A DeepSeek Harness plugin uses vLLM-SR d3-ultra to triage steps, guard tool calls, strip injected lines and check whether work is done. This is the model maker's integration, by Xunzhuo Liu, co-founder of vLLM Semantic Router. In his small probes, the guard got 35 of 36 commands right, stopping all 16 risky ones, and the shield got 22 of 22 passages right. He reports a 0.49 s median across 53 guard decisions. Triage of 230 tickets took 121 s and 117,877 LLM prompt tokens, against 543 s and at least 510,986 for the LLM alone.