Skip to content
Laya AI
Official Laya logo: a blue spiral mark, the word laya, and the line decisions, not text.
Official logo from the Convai Innovations model card.

Unofficial community documentation

Laya Model — the Laya AI System One decision engine

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.

Laya Model is the common name for Laya AI, the open System One decision engine: low latency, local weights, or a hosted prepaid key on this site. Jev is a closed API that works out of the box. Open source is the license story — System One decision model is the product category.

Get hosted API →Create account▶ Try playgroundSelf-host / download

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.

Browse all tools →

POST api.layaaimodel.com/v1/social/post-analyze

State — the input software gives Laya

207c

Questions — 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

  • choicehook
    scroll-stopping
    scroll-stopping
    72%
    solid
    9%
    weak
    9%
    none
    9%

    confidence 72%

  • noulopens_loop
    yes · 91%
    yes
    91%
    no
    9%

    confidence 91%

  • noulhas_evidence
    yes · 68%
    yes
    68%
    no
    32%

    confidence 32%

  • choiceformat
    how_to
    how_to
    68%
    story
    8%
    hot_take
    8%
    promo
    8%
    other
    8%

    confidence 68%

  • choiceviral_potential
    high
    high
    61%
    medium
    20%
    low
    20%

    confidence 61%

Anonymous: 1 free real-API run / IP · register for a laya_ key to keep going

Open this tool →

Laya vs Jev

Official chart comparing Laya with routing against TypeSafe Jev on accuracy, language coverage, speed, calibration, license, and cost.
Official figure from the convaiinnovations/laya model card. Jev bars are published third-party numbers.

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.

Official self-test

README table “Laya (with routing) vs Jev”. Laya figures are what Router().predict returns. Jev figures are third-party published and were not measured in the Laya repository.
Jev 1.13.0Laya (routed)
typed-decisions, 2,000 decisions0.7270.766+0.039
AG News, 4 labels0.9100.950+0.040
DAIR Emotion, 6 labels0.4800.595+0.115
Banking77 (72 vs 77 labels)0.8700.425Jev leads on >20 options

Full tables, calibration notes, and the third-party remeasurements are on the benchmarks page.

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.

Features

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 laya
python
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.