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-weights System One model from Convai Innovations. A fully fine-tuned ModernBERT-large encoder with a from-scratch decision head that scores one marker per option and answers every question in a single 33–39 ms pass. Runs on your own CPU or GPU.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
decision
laya
Fine-tuned from
qwen/qwen3.5-9b
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.4%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
39.5 ms
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 laya?
decision is from vLLM Semantic Router and laya from Convai Innovations. 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 512 tokens for laya. laya is the smaller model, at 421M parameters to 9.0B.
Which is more accurate, decision or laya?
Only decision publishes an accuracy figure (77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted)); laya does not, so there is no comparison to make without your own test.
Which is cheaper, decision or laya?
decision: Free (open weights). laya: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decision or laya locally?
Yes, both: systemone pull vllm-semantic-router/decision and systemone pull convai-innovations/laya download the weights.
