Loading the alternatives…
OPEN ALTERNATIVES TO JEV
Jev, from TypeSafe AI, is a hosted System One model: an AI decision model that returns typed answers with calibrated probabilities instead of text. Its weights are not published. These are the models you can download, run on your own hardware and fine-tune instead: 25 from 24 makers, listed from the live registry.
For each: what it decides, its size and licence, the benchmark its publisher reports with the suite named, and a head-to-head page against Jev. Updated September 27, 2026.
These serve TypeSafe’s POST /v1/systemone request format, according to their own documentation, so a client written for Jev can switch by changing its base URL.
| Model | Decides | Parameters | Licence | Reported accuracy | Median latency | Released | Against Jev |
|---|---|---|---|---|---|---|---|
| winnowEldanRing | choice, score, noul, classify, route | 12B | apache-2.0 | 85.7%JevBench public subset (231 items), Q8_0 | 143 ms | Sep 20, 2026 | Jev vs winnow |
| levInterfaze AI | choice, score, noul, classify, route | 4.0B | apache-2.0 | 68.9%S1Bench (13 public subsets, macro) | 69 ms | Sep 24, 2026 | Jev vs lev |
| decisionvLLM Semantic Router | choice, score, noul, classify, route | 9.0B | apache-2.0 | 77.4%vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted) | — | Sep 22, 2026 | Jev vs decision |
| jevk5Alibi Serikbay | choice, score, noul, classify, route | 4.0B | apache-2.0 | 78.4%JevBench public hard tier | 13.2 ms | Sep 22, 2026 | Jev vs jevk5 |
| openthai-systemoneiApp Technology | choice, score, noul, classify, route | 800M | apache-2.0 | 74.3%Bespoke public subsets (13, macro average) | 40 ms | Sep 20, 2026 | Jev vs openthai-systemone |
| vonwfzyx | choice, score, noul, classify | 395M | apache-2.0 | 63.9%JevBench public standard tier | 18 ms | Sep 19, 2026 | Jev vs von |
| deciderMapika | choice, score, noul, classify, route | 2.0B | apache-2.0 | 80.2%Decider 67-task regression set | 3.2 ms | Sep 16, 2026 | Jev vs decider |
| bespoke-nimble-9bBespoke Labs | choice, noul, score, classify, route | 9.0B | apache-2.0 | 90.1%Bespoke held-out set (324 examples) | 106 ms | Sep 18, 2026 | Jev vs bespoke-nimble-9b |
| clmContrastive-LM | choice, score, noul, rank, classify, route | 8.0B | apache-2.0 | — | — | Sep 23, 2026 | Jev vs clm |
| layaConvai Innovations | choice, score, noul, classify, route | 421M | apache-2.0 | — | 39.5 ms | Sep 18, 2026 | Jev vs laya |
| kevJared Palmer | choice, score, noul, classify, route | 4.0B | apache-2.0 | 83.8%transfer-v4 (locked, out of domain) | — | Sep 19, 2026 | Jev vs kev |
The same kind of model, with their own interface: a Python package, a different endpoint, or a chat-completions wrapper. Each model’s page shows how to call it.
| Model | Decides | Parameters | Licence | Reported accuracy | Median latency | Released | Against Jev |
|---|---|---|---|---|---|---|---|
| rizzo-flowRizzo AI Academy | choice, score, noul, classify, route | 4.0B | apache-2.0 | 64.8%LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0 | 195 ms | Sep 25, 2026 | Jev vs rizzo-flow |
| cygnetBlockbrain Labs | choice, score, noul | 12B | mit | 87.9%JevBench public set (231 items), JevBench CLI | 50 ms | Sep 24, 2026 | Jev vs cygnet |
| anyjevNokia Applied Research | choice, score, noul, classify, route | 8.0B | apache-2.0 | 77.1%LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question | — | Sep 21, 2026 | Jev vs anyjev |
| open-jev-deberta-v3-largeKotoba Labs | choice, score, noul, classify | 434M | apache-2.0 | 85.4%Kotoba held-out test, seen question types (banking77, SST-5, BoolQ) | 28 ms | Sep 18, 2026 | Jev vs open-jev-deberta-v3-large |
| hopperHopitAI | choice, score, noul, classify | 4.0B | other | 68.5%JevBench public hard tier (111 items, measured by the authors) | — | Sep 21, 2026 | Jev vs hopper |
| julia-1Supersonic Labs | choice, score, noul, classify, route | 144M | apache-2.0 | 73.2%typed-decisions test set (400 cases, 2,000 questions) | — | Sep 23, 2026 | Jev vs julia-1 |
| laya-multilingual-mlxaac6fef | choice, score, noul | 322M | apache-2.0 | — | — | Sep 19, 2026 | Jev vs laya-multilingual-mlx |
| laya-mlxaac6fef | choice, score, noul | 421M | apache-2.0 | — | — | Sep 19, 2026 | Jev vs laya-mlx |
| system-one-qwen3-5-4b-scorerpngwn | choice, score, noul, classify | 4.0B | cc-by-nc-4.0 | 70.7%author-reported | 112 ms | Sep 16, 2026 | Jev vs system-one-qwen3-5-4b-scorer |
| jev-omniakhilaaa3 | choice, noul, score, classify | 12B | apache-2.0 | 87.6%DecisionBench Medium (author's set) | 83 ms | Sep 20, 2026 | Jev vs jev-omni |
| nanojevTianyuCodings | choice, noul, score | 600M | mit | — | — | Sep 17, 2026 | Jev vs nanojev |
| cua-s1-formsCua | choice | 706K | mit | 100.0%196-decision evaluation on real forms | — | Sep 18, 2026 | Jev vs cua-s1-forms |
| gliner2-5-decideFastino Labs | choice, score, noul, classify, extract, route | 340M | apache-2.0 | 60.2%Fastino fast-decisions suite (17 datasets) | 38.3 ms | Sep 24, 2026 | Jev vs gliner2-5-decide |
| tev1Together AI | choice, classify, route | 4.0B | other | 88.0%Together development set (reused, not held out) | — | Sep 23, 2026 | Jev vs tev1 |
Accuracy and latency are what each publisher reports, on its own suite and hardware, so they are not a ranking. The reliable comparison is your own labelled examples. Every System One model, hosted ones included, is in one table.
Download any of them from your terminal. Every file is checked against its SHA-256 and cached.
pip install systemonemodels systemone pull convai-innovations/laya
Laya Studio fine-tunes Laya on your own data, on a Mac, Windows or Linux machine, and proves the result beats the base before you publish it.
systemone run studio
No. Jev is TypeSafe AI’s hosted System One model: you call it over an API ($0.042 / $0 per 1M tokens), and its weights are not published. The 25 models on this page are the open alternatives: you download the weights and run them yourself.
There is no fair ranking yet: each publisher reports accuracy on its own suite, so the numbers are not comparable. Choose by your constraints instead. If you already call Jev, start with the ones that speak its API: winnow, lev, decision and jevk5. The smallest are cua-s1-forms (706K), julia-1 (144M) and laya-multilingual-mlx (322M). The fastest reported are decider (3.2 ms), jevk5 (13.2 ms) and von (18 ms), on their publishers’ own hardware. Then measure the shortlist on your own labelled examples.
winnow, lev, decision, jevk5, openthai-systemone, von, decider, bespoke-nimble-9b, clm, laya and kev. Their own documentation says they serve TypeSafe’s POST /v1/systemone request format, so a client written for Jev can switch by changing the base URL. Check each model’s page for its server and the question types it supports.
Open weights under a licence that allows commercial use: rizzo-flow (apache-2.0), cygnet (mit), anyjev (apache-2.0), open-jev-deberta-v3-large (apache-2.0), winnow (apache-2.0), lev (apache-2.0), julia-1 (apache-2.0), decision (apache-2.0), 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). Others publish weights under a non-commercial or research-only licence; each model’s page names its licence.
Yes. pip install systemonemodels, then systemone pull namespace/name downloads any of them, with every file checked against its SHA-256. Laya also has MLX ports for Apple silicon, and Laya Studio fine-tunes it on your own Mac, Windows or Linux machine (systemone run studio).
Yes, which is the main reason to choose an open one. Laya Studio fine-tunes Laya with LoRA, DoRA, rsLoRA or LoRA+, scores the result against the base on held-out rows, and publishes it to the registry. The other models ship their own training code; systemone push publishes what you train.
Read on: What is an AI decision model? · The open reproductions, in depth · How Jev works · Jev alternative, defined