d3-ultra

d3-ultra is a 27B multimodal decision model from vLLM Semantic Router (Decision 3.0). Send a state, optionally with images and videos, plus typed questions (choice, noul, score, box and track) and get a calibrated probability for each answer in one forward pass, with no generated text. Official Jev Decision Index scores are 70.18 on the text board and 70.59 on the vision board. It is the only Decision 3.0 model that tracks a target through a video, and its box output comes from the model itself in one call. vllm-sr/d3-turbo and vllm-sr/d3 are aliases of it. Context is 131,072 tokens per request. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler). The service logs requests and may train on them, so it is skipped when Always enforce ZDR is on (Dashboard, Privacy).