THE COMPLETE LIST
System One models
A System One model is a decision model: it reads a state and answers typed questions — choose an option, score on a scale, or give the probability that a condition holds — in one forward pass, with calibrated confidence and no generated text.
This page lists every System One model on the registry — 17 from 16 makers — with what each decides, its size, context, licence and price, and the benchmark numbers its publisher reports. Updated September 26, 2026.
What they answer
Every System One model
| Model | Decides | Parameters | Context | Availability and price | Licence | Reported accuracy | Median latency | Released |
|---|---|---|---|---|---|---|---|---|
| gliner2-5-decideFastino Labs | choice, score, noul, classify, extract, route | 340M | — | Open weights + hosted APIHosted, price not published, or free to self-host | apache-2.0 | 60.2%Fastino fast-decisions suite (17 datasets) | 38.3 ms | Sep 24, 2026 |
| clmContrastive-LM | choice, score, noul, rank, classify, route | 8.0B | — | Open weightsFree (open weights) | apache-2.0 | — | — | Sep 23, 2026 |
| tev1Together AI | choice, classify, route | 4.0B | — | Open weights + hosted API$0.042 / $0 per 1M, or free to self-host | other | 88.0%Together development set (reused, not held out) | — | Sep 23, 2026 |
| jevk5Alibi Serikbay | choice, score, noul, classify, route | 4.0B | — | Open weightsFree (open weights) | apache-2.0 | 78.4%JevBench public hard tier | 13.2 ms | Sep 22, 2026 |
| jev-omniakhilaaa3 | choice, noul, score, classify | 12B | — | Open weightsFree (open weights) | apache-2.0 | 87.6%DecisionBench Medium (author's set) | 83 ms | Sep 20, 2026 |
| openthai-systemoneiApp Technology | choice, score, noul, classify, route | 800M | — | Open weightsFree (open weights) | apache-2.0 | 74.3%Bespoke public subsets (13, macro average) | 40 ms | Sep 20, 2026 |
| laya-multilingual-mlxaac6fef | choice, score, noul | 322M | 1K tokens | Open weightsFree (open weights) | apache-2.0 | — | — | Sep 19, 2026 |
| laya-mlxaac6fef | choice, score, noul | 421M | 512 tokens | Open weightsFree (open weights) | apache-2.0 | — | — | Sep 19, 2026 |
| vonwfzyx | choice, score, noul, classify | 395M | 8K tokens | Open weightsFree (open weights) | apache-2.0 | 63.9%JevBench public standard tier | 18 ms | Sep 19, 2026 |
| kevJared Palmer | choice, score, noul, classify, route | 4.0B | 8K tokens | Open weightsFree (open weights) | apache-2.0 | 83.8%transfer-v4 (locked, out of domain) | — | Sep 19, 2026 |
| cua-s1-formsCua | choice | 706K | — | Open weightsFree (open weights) | mit | 100.0%196-decision evaluation on real forms | — | Sep 18, 2026 |
| bespoke-nimble-9bBespoke Labs | choice, noul, score, classify, route | 9.0B | 8K tokens | Open weights + hosted APIHosted, price not published, or free to self-host | apache-2.0 | 90.1%Bespoke held-out set (324 examples) | 106 ms | Sep 18, 2026 |
| layaConvai Innovations | choice, score, noul, classify, route | 421M | 512 tokens | Open weightsFree (open weights) | apache-2.0 | — | 39.5 ms | Sep 18, 2026 |
| nanojevTianyuCodings | choice, noul, score | 600M | — | Open weightsFree (open weights) | mit | — | — | Sep 17, 2026 |
| system-one-qwen3-5-4b-scorerpngwn | choice, score, noul, classify | 4.0B | — | Open weightsFree (open weights) | cc-by-nc-4.0 | 70.7%author-reported | 112 ms | Sep 16, 2026 |
| deciderMapika | choice, score, noul, classify, route | 2.0B | — | Open weightsFree (open weights) | apache-2.0 | 80.2%Decider 67-task regression set | 3.2 ms | Sep 16, 2026 |
| jevTypeSafe AI | choice, score, noul, classify, route | — | 32K tokens | Hosted API$0.042 / $0 per 1M | proprietary | — | — | Sep 15, 2026 |
Accuracy and latency are what each publisher reports, on its own suite and hardware. They are not a ranking: the suites differ. Parameters, context, licence and price are from each model’s manifest.
Use one
Pull any open-weight model from your terminal. Files are verified against their SHA-256 and cached.
pip install systemonemodels systemone pull convai-innovations/laya
Hosted models are called through their provider’s API; each model page has a playground that builds the request.
Fine-tune one
Laya Studio fine-tunes Laya on your own labelled data, on your own machine, measures it against the base model on the same held-out split, and publishes it here in one step.
Who makes them
- aac6fef2 models
- pngwn1 model
- akhilaaa31 model
- TianyuCodings1 model
- Alibi Serikbay1 model
- Cua1 model
- iApp Technology1 model
- wfzyx1 model
- Mapika1 model
- Bespoke Labs1 model
- Contrastive-LM1 model
- Convai Innovations1 model
- Jared Palmer1 model
- Fastino Labs1 model
- Together AI1 model
- TypeSafe AI1 model
Head to head
- laya-multilingual-mlx vs laya-mlx
- laya-multilingual-mlx vs system-one-qwen3-5-4b-scorer
- laya-multilingual-mlx vs jev-omni
- laya-multilingual-mlx vs nanojev
- laya-mlx vs system-one-qwen3-5-4b-scorer
- laya-mlx vs jev-omni
- laya-mlx vs nanojev
- system-one-qwen3-5-4b-scorer vs jev-omni
- system-one-qwen3-5-4b-scorer vs nanojev
- jev-omni vs nanojev
Community fine-tunes
- biplov/prompt-injection-demo-runfrom aac6fef/laya-mlx
- biplov/prompt-injection-balanced-englishfrom aac6fef/laya-mlx
- biplov/emotion-rlcd-objectivefrom aac6fef/laya-mlx
- biplov/emo-en-lora-properfrom aac6fef/laya-mlx
- biplov/banking77-balanced-multilingualfrom aac6fef/laya-multilingual-mlx
Questions
What is a System One model?
A System One model is a decision model: it reads a state and answers typed questions — choose an option, score on a scale, or give the probability that a condition holds — in one forward pass, with calibrated confidence and no generated text.
How many System One models are there?
The registry lists 17 System One models from 16 makers: 16 with open weights and 4 served as a hosted API, counting models that are both in each. People have published 5 fine-tunes and experiments on top of them.
What was the first System One model?
jev, from TypeSafe AI, released on Sep 15, 2026.
Which System One models are open source?
Open weights under a licence that allows commercial use: laya-multilingual-mlx (apache-2.0), laya-mlx (apache-2.0), jev-omni (apache-2.0), nanojev (mit), jevk5 (apache-2.0), cua-s1-forms (mit), openthai-systemone (apache-2.0), von (apache-2.0), decider (apache-2.0), bespoke-nimble-9b (apache-2.0), clm (apache-2.0), laya (apache-2.0), kev (apache-2.0) and gliner2-5-decide (apache-2.0). Some other models publish weights under a non-commercial licence or none at all, so check each model's licence before shipping it.
Which System One model is the fastest?
By the median latency their publishers report, the fastest are decider at 3.2 ms, jevk5 at 13.2 ms and von at 18 ms. The figures come from different hardware and different request sizes, so measure on your own setup before choosing on speed.
How much does a System One model cost?
Open-weight models are free to download and run on your own hardware. Hosted ones are billed by their providers per million input tokens: tev1 at $0.042 and jev at $0.042.
Which System One model is the most accurate?
There is no fair ranking yet. Every publisher reports accuracy on a different suite — their own held-out set, a JevBench tier, a domain benchmark — so the numbers in the table are not comparable with each other. The table shows the suite next to each figure; the reliable test is your own labelled examples.
How do I use a System One model?
Install the CLI with pip install systemonemodels, then systemone pull namespace/name downloads a model’s files, each verified against its SHA-256. Hosted models are called through their provider’s API, which each model page links to.
Can I fine-tune a System One model?
Yes. Laya Studio fine-tunes Laya on your own data, on your own machine, and publishes the result here in one step. Any open-weight model can be fine-tuned with its own training code and published with systemone push.
Read on: the glossary · What is a System One model? · System One models vs LLMs · The landscape, in depth