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: 23 from 23 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 October 3, 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 |
|---|---|---|---|---|---|---|---|
| layaConvai Innovations | choice, score, noul, classify, route | 421M | apache-2.0 | — | 39.5 ms | Sep 18, 2026 | Jev vs laya |
| clmContrastive-LM | choice, score, noul, rank, classify, route | 8.0B | apache-2.0 | — | — | Sep 23, 2026 | Jev vs clm |
| startlux-decisionStartLux | choice, score, noul | 4.7B | cc-by-nc-4.0 | 88.3%JevBench public set (231 items; 204 correct), maker's run | 26 ms | Sep 29, 2026 | Jev vs startlux-decision |
| deciderMapika | choice, score, noul, classify, route | 1.9B | apache-2.0 | 75.2%Decider regression set, 28 held-out tasks (decider-2b v11) | — | Sep 24, 2026 | Jev vs decider |
| lumma-fevFrontiersMind | choice, score, noul | 649M | apache-2.0 | 64.0%typed-decisions (maker's table; split not stated) | 45.8 ms | Sep 22, 2026 | Jev vs lumma-fev |
| 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 |
| 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 |
| xorJuspay | choice, score, noul, classify, route | 35B | apache-2.0 | 90.0%JevBench public set (231 items), maker's self-run of Xor 1.2 | 69 ms | Sep 21, 2026 | Jev vs xor |
| 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 |
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 |
|---|---|---|---|---|---|---|---|
| miraSAGEA | choice, score, noul, classify, route | — | apache-2.0 | 61.3%s1-decision-bench | 30 ms | — | Jev vs mira |
| 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 |
| 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 |
| neohorse-jevTokenRhythm | choice, score, noul, classify, route | 4.0B | apache-2.0 | 75.3%JevBench public set (231 items), vLLM, maker's run | — | Sep 23, 2026 | Jev vs neohorse-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 |
| 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 |
| tev1Together AI | choice, classify, route | 4.0B | other | 88.0%Together development set (reused, not held out) | — | Sep 23, 2026 | Jev vs tev1 |
| anyjevNokia | 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 |
| cua-s1-formsCua | choice | 706K | mit | 100.0%196-decision evaluation on real forms | — | Sep 18, 2026 | Jev vs cua-s1-forms |
| metask-jevMetask Lab | choice, score, noul, classify, route | 4.5B | apache-2.0 | 80.1%JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run | 62.8 ms | Sep 21, 2026 | Jev vs metask-jev |
| djevMaisa | choice, score, noul | 26B | apache-2.0 | — | — | Sep 19, 2026 | Jev vs djev |
| jev-27bAutoTrust AI Lab | choice, score, noul | 27B | apache-2.0 | 88.7%JevBench public set (231 items), family-macro score, maker's run | 137 ms | Sep 25, 2026 | Jev vs jev-27b |
| runeSurogate (Invergent) | choice, score, noul, classify, route | 26B | apache-2.0 | — | — | Sep 21, 2026 | Jev vs rune |
| simple-jevFeatherless AI | choice, score, noul, classify, route | — | apache-2.0 | — | — | Sep 18, 2026 | Jev vs simple-jev |
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
System One 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 23 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: laya, clm, startlux-decision and decider. The smallest are cua-s1-forms (706K), julia-1 (144M) and gliner2-5-decide (340M). The fastest reported are startlux-decision (26 ms), open-jev-deberta-v3-large (28 ms) and mira (30 ms), on their publishers’ own hardware. Then measure the shortlist on your own labelled examples.
laya, clm, startlux-decision, decider, lumma-fev, kev, bespoke-nimble-9b, xor and decision. 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: mira (apache-2.0), laya (apache-2.0), gliner2-5-decide (apache-2.0), julia-1 (apache-2.0), clm (apache-2.0), neohorse-jev (apache-2.0), rizzo-flow (apache-2.0), open-jev-deberta-v3-large (apache-2.0), decider (apache-2.0), lumma-fev (apache-2.0), kev (apache-2.0), bespoke-nimble-9b (apache-2.0), anyjev (apache-2.0), cua-s1-forms (mit), xor (apache-2.0), decision (apache-2.0), metask-jev (apache-2.0), djev (apache-2.0), jev-27b (apache-2.0), rune (apache-2.0) and simple-jev (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 System One 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. System One 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