Vllm Sr

d3-edge is a 0.6B multimodal decision model from vLLM Semantic Router (Decision 3.0). Send a state, optionally with images and videos, plus typed questions (choice, noul and score) and get a calibrated probability for each answer in one forward pass, with no generated text. Official Jev Decision Index scores are 17.69 on the text board and 31.71 on the vision board. 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).

d3-flash is a 9B multimodal decision model from vLLM Semantic Router (Decision 3.0). Send a state, optionally with images and videos, plus typed questions (choice, noul, score and box) and get a calibrated probability for each answer in one forward pass, with no generated text. Official Jev Decision Index scores are 54.27 on the text board and 66.89 on the vision board. Box answers come from grid scoring over the image, which costs roughly 18,000 input tokens per box question. 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).

d3-lite is a 0.8B multimodal decision model from vLLM Semantic Router (Decision 3.0). Send a state, optionally with images and videos, plus typed questions (choice, noul and score) and get a calibrated probability for each answer in one forward pass, with no generated text. Official Jev Decision Index scores are 26.16 on the text board and 42.11 on the vision board. 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).

d3-mini is a 4B multimodal decision model from vLLM Semantic Router (Decision 3.0). Send a state, optionally with images and videos, plus typed questions (choice, noul and score) and get a calibrated probability for each answer in one forward pass, with no generated text. Official Jev Decision Index scores are 49.97 on the text board and 63.16 on the vision board. 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).

d3-nano is a 2B multimodal decision model from vLLM Semantic Router (Decision 3.0). Send a state, optionally with images and videos, plus typed questions (choice, noul and score) and get a calibrated probability for each answer in one forward pass, with no generated text. Official Jev Decision Index scores are 34.30 on the text board and 54.67 on the vision board. 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).

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).