A training-free layer that turns an open LLM into a decision model. It reads typed choice, yes/no and score answers from one prefill, removes option-order bias with no labels and, from a few hundred labels, calibrates or fits a closed-form head. Weights stay untouched.
Liquid AI's first decision model, served only through the Liquid API. Returns Choice, Score and Noul answers with probability distributions and zero output tokens, on the /v1/systemone request shape used by TypeSafe's SDK.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
anyjev
d1
Fine-tuned from
qwen/qwen3-8b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Liquid AI
Input price
—
—
Decision accuracy
77.1%
—
Calibration error
0.034
—
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 anyjev and d1?
anyjev is from Nokia and d1 from Liquid AI. anyjev has open weights you can download and run; d1 is only available as a hosted API. Both answer choice, score, noul, classify and route questions. anyjev is licensed apache-2.0; d1, proprietary.
Which is more accurate, anyjev or d1?
Only anyjev publishes an accuracy figure (77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question); d1 does not, so there is no comparison to make without your own test.
Which is cheaper, anyjev or d1?
anyjev: Free (open weights). d1: Hosted, price not published. Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or d1 locally?
anyjev yes — systemone pull nokia/anyjev downloads its weights. The other is only served as a hosted API.
Evaluation suite
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
