Laya: Open-Source Counterpart to Jev | Multilingual System 1 Model for Fast AI Decisions
Mohamed Naji Aboo
Overview of Laya as a multilingual System One decision model.
Open on YouTube
Unofficial community documentation
Laya AI — System One Decision Model
Typed decisions for agents and software — choice, score, and yes/no in one forward pass. Hosted prepaid API here; Apache 2.0 weights if you run locally. Compared with the closed Jev API throughout.
Jev is a closed API that works out of the box. Laya is the open System One option: low latency, local weights, or a hosted prepaid key on this site. Open source is the license story — System One decision model is the product category.
No GPU? Skip pip and weights — prepaid hosted API, key in minutes, typical decide ≈ $0.0004. Prefer local Apache 2.0 weights? Use Download.
Playground
Typed decisions, live
Pick a tool scenario, tweak the input, run the real API — choice, score, and yes/no with calibrated scores.
POST api.layaaimodel.com/v1/social/post-analyze
State — the input software gives Laya
207cQuestions — typed decisions you get back
- choicehookHow strong is the opening hook?
- noulopens_loopDoes it open an information loop?
- noulhas_evidenceDoes it include evidence or proof?
- choiceformatPost format?
- choiceviral_potentialViral potential?
Sample answers
sample · not yet run
- choicehookscroll-stoppingscroll-stopping72%solid9%weak9%none9%
confidence 72%
- noulopens_loopyes · 91%yes91%no9%
confidence 91%
- noulhas_evidenceyes · 68%yes68%no32%
confidence 32%
- choiceformathow_tohow_to68%story8%hot_take8%promo8%other8%
confidence 68%
- choiceviral_potentialhighhigh61%medium20%low20%
confidence 61%
Laya vs Jev
Two sources sit in separate tables on purpose. The first is the project's own README. The second is a Hugging Face community dataset that remeasured Laya. Jev cells in both places are published quotes unless a caption says otherwise. Limits, calibration notes, and Banking77 detail live on the Laya vs Jev benchmarks page — including which checkpoint the headline 0.766 figure belongs to.
Official self-test
| Jev 1.13.0 | Laya (routed) | ||
|---|---|---|---|
| typed-decisions, 2,000 decisions | 0.727 | 0.766 | +0.039 |
| AG News, 4 labels | 0.910 | 0.950 | +0.040 |
| DAIR Emotion, 6 labels | 0.480 | 0.595 | +0.115 |
| Banking77 (72 vs 77 labels) | 0.870 | 0.425 | Jev leads on >20 options |
| ECE (lower better) | 0.246 | 0.081 | 3× better (post-temperature) |
| p50 latency, 1 question | 236–276 ms | 32.8 ms | 7.8× faster |
| Languages usable | no published benchmark | 45 of 51 | — |
| Weights | closed API | Apache 2.0 | — |
| Cost | $0.042 / 1M tokens | $0 self-hosted | — |
Third-party independent test
| Model | Accuracy | ECE | ms per case |
|---|---|---|---|
| Laya, no fine-tuning | 0.360 | 0.175 | 15.9 |
| Laya fine-tuned on this task | 0.767 | 0.212 | 16.4 |
| Jev 1.13.0 (published) | 0.727 | 0.144 | 710 |
| Teacher self-agreement | 0.735 | — | — |
| Model | Accuracy | ECE | AUROC | Recall | p50 |
|---|---|---|---|---|---|
| Laya, raw | 0.505 | 0.441 | 0.678 | 0.012 | 9 ms |
| Laya, Platt-calibrated | 0.611 | — | 0.679 | — | 9 ms |
| Jev (published) | 0.626 | 0.154 | 0.689 | 0.432 | 239 ms |
| Claude Haiku 4.5 (published) | 0.813 | 0.097 | 0.837 | 0.764 | 687 ms |
| Model | Accuracy | Macro F1 | Top-3 accuracy |
|---|---|---|---|
| Laya English base, same 77-label protocol | 45.91% | 42.90% | 69.42% |
| Cahol fine-tune | 85.55% | 85.53% | 96.43% |
Videos
Community YouTube explainers about Laya and Laya vs Jev. These creators are not affiliated with Convai Innovations or with this site. Prefer the README and BENCHMARKS.md for numbers.
Open Source, Faster Jev is HERE
CoderOne
Walkthrough of the open-weight Laya stack against the closed Jev API.
Open on YouTubeLaya vs Jev: What "7.8x Faster" Actually Means
AICKStudio | Agentic AI
Latency claim from the README comparison, explained for producers.
Open on YouTubeRun This Powerful Jev AI on Your Laptop for $0
Edwin Chen | AI Automation
Local setup angle for the open System One model you can run without an API key.
Open on YouTubeFeatures
Fast Inference
Official T4 table: 32.8 ms for one question on laya-multilingual, 39.5 ms on laya. Batched multilingual throughput there is 7.2 ms/question at 10 questions.
Apache 2.0 Open Source
Weights and the pip package are Apache 2.0. Jev, in the same README comparison, is a closed API at a published $0.042 / 1M tokens.
100+ Languages
The README describes laya-multilingual as the 100+ language checkpoint. On the published 51-language MASSIVE sweep it clears 3× random on 45 of 51 languages.
No LLM Hallucinations
The project says there is no text generation, so there is nothing to parse. Outputs are choice, score, and yes/no. Wrong labels still show up in the tables below.
Run Laya locally
Shortened slice of the README Router quickstart. Hardware, preload pitfalls, and the full script are on Get Started. This site does not run the model.
bash
pip install layapython
import laya
from laya import Router
router = Router(preload=True)
state = {
"from": "[email protected]",
"subject": "Duplicate charge on invoice #4411",
"body": "Hi, we were billed twice for March. Please refund the duplicate today or we will cancel our plan."
}
questions = {
"department": {
"type": "choice",
"instructions": "Which department should handle this request?",
"criteria": {
"billing": "invoices, payments, refunds",
"technical": "bugs, outages, system errors",
"sales": "pricing, new contracts",
"other": "everything else"
}
}
}
res_en = router.predict(state, questions)
print("Department :", res_en["answers"]["department"]["choice"])
Use cases
Laya fits
Local or hosted System One: small label sets, open weights, or a prepaid laya_ key when you do not want to run GPU ops.
Where Jev differs
Closed API out of the box, or one choice question with a very wide label set. Want to try hosted Laya first? Packs from $5.
Skip the GPU install — hosted packs from $5, typical decide ≈ $0.0004.