vLLM Semantic Router
Open decision layer from the vLLM project, and the maker of the Decision models.
vLLM Semantic Router is an open-source project in the vLLM ecosystem that builds a programmable decision layer for routing work across models and compute. Its Decision model family (d1, d3) answers typed questions with a probability for every option instead of generating text; d3-ultra is the largest, a 26B multimodal decision model released under Apache-2.0.
vllm-sr.aiCall vLLM Semantic Router models through Opper with one API key. Sign up without a credit card.
Models from vLLM Semantic Router
| Model | Context | Provider | Region | Zero data retention | Training | Input | Output | Cache read |
|---|---|---|---|---|---|---|---|---|
| 66K | US | No | $0.04 | $0 | Input price |
Release timeline
Every dated vLLM Semantic Router release, newest first — 1 of 1 run on the Opper gateway today. Releases without a published date aren't listed. See the AI model release tracker.