Decision-model landscape

System One Models & Typed Decision Engines

Laya is part of a fast-growing model category focused on typed decisions rather than long-form generation. This page tracks the different approaches without collapsing them into one ranking.

Model / approachStatusAccessDeploymentApproachLanguagesSource
Laya

Open-source System 1 decision model family with Router, local inference, fine-tuning and multiple runtimes.

Open weightsApache 2.0 projectLocal / self-hostedNon-autoregressive typed decision model with choice, score and noul headsEnglish + multilingual checkpointNandhaKishorM/laya
TypeSafe Jev

Hosted System One decision model that established much of the current typed-decision API vocabulary.

Hosted modelManaged APIProvider-hostedTyped choice, score and noul decisions through a hosted model APIProvider-dependentTypeSafe documentation
AnyJev

Nokia Applied Research project that turns compatible LLMs into Jev-style typed decision models without task-specific training.

Open libraryApache 2.0Bring your own LLM backendTraining-free typed decision layer over existing LLM logits with debiasing and calibration levelsDepends on underlying LLMnokia-applied-research/AnyJev
Bespoke Nimble

Bespoke Labs publishes a model, training methodology, evaluation tools, and recipe for open typed decisions.

Open model + recipeOpen repositoryApple Silicon / NVIDIAJev-inspired local typed decisions plus data curation and training recipeModel-dependentbespokelabsai/nimble
OpenThai-SystemOne

Thai and English System One model with a Jev-compatible request/response contract and an open training pipeline.

Open weightsApache 2.0CUDA / MPS / CPUQwen3.5-0.8B text tower with a 256-way slot head for choice, score and noulThai + Englishiapp-technology/openthai-systemone
Decider

A growing family of open System One-style models with training data, evaluation, serving, games, and vision experiments.

Open model familyApache 2.0Local / HTTP servingQwen3.5-based one-pass typed decisions with calibrated probabilities and serving enginesModel-dependentMapika/decider

What makes a System One decision model different?

The common idea is to answer structured questions about a state without generating a long free-form response token by token. Applications ask for a label, ordered score, probability, or similarly constrained output and receive machine-readable results.

The projects above are not interchangeable. Some are specialized trained models, some are hosted services, and some are libraries that read or calibrate logits from an existing LLM. Compare deployment model, calibration, task distribution, language coverage, option count, latency, and reproducibility before choosing an approach.

laya-ai.com remains focused on Laya. This category page exists to explain the ecosystem around it and to track adjacent techniques as the decision-model space evolves.