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.
An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
decision
kev
Fine-tuned from
qwen/qwen3.5-9b
qwen/qwen3.5-4b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.4%
83.8%
Calibration error
—
0.042
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 kev?
decision is from vLLM Semantic Router and kev from Jared Palmer. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. decision reads up to 16K tokens of state, against 8K tokens for kev. kev is the smaller model, at 4.0B parameters to 9.0B.
Which is more accurate, decision or kev?
They report on different suites — decision 77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted), kev 83.8% on transfer-v4 (locked, out of domain) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, decision or kev?
decision: Free (open weights). kev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decision or kev locally?
Yes, both: systemone pull vllm-semantic-router/decision and systemone pull jared-palmer/kev download the weights.
