The flagship of the vLLM Semantic Router team's Decision 1.0 family. Qwen3.5-9B with a shared candidate head returns a probability for every supplied answer to choice, yes/no and score questions, over a 16,384-token input.
A typed-decision layer for Google's DiffusionGemma, from David Villalón at Maisa AI. It compiles a request into a small answer canvas, runs one denoising read on patched vLLM and reads the probabilities of the allowed labels, for text, images and images offered as options.
Decides
choice, score, noul, classify, route
choice, score, noul
Architecture
decision
djev
Fine-tuned from
qwen/qwen3.5-9b
google/diffusiongemma-26b-a4b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Maisa
Input price
—
$0.035/MTok
Decision accuracy
77.4%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between decision and djev?
decision is from vLLM Semantic Router and djev from Maisa. decision has open weights you can download and run; djev has open weights and a hosted API. Both answer choice, score and noul questions. Only decision answers classify and route. decision is the smaller model, at 9.0B parameters to 26B.
Which is more accurate, decision or djev?
Only decision publishes an accuracy figure (77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted)); djev does not, so there is no comparison to make without your own test.
Which is cheaper, decision or djev?
decision: Free (open weights). djev: $0.035 / $0 per 1M, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run decision or djev locally?
Yes, both: systemone pull vllm-semantic-router/decision and systemone pull maisa/djev download the weights.
