Decisions,
not text.
Moderation, routing, intent and scoring for every message, over one Jev-compatible API.
Comments
moderation + spam
-
You are all idiots and I hope you get fired.
toxic 80% moderation
-
Your product is overpriced and the support is slow.
safe 71% moderation
-
Earn $5000 a day from home! Message me on WhatsApp.
spam 90% spam
-
Hi, is the conference room free on Friday afternoon?
legit 88% spam
Live demo
POST /v1/decide
Answer
recorded answer · laya-english
toxic
Support inbox
intent + routing
-
Please cancel my subscription at the end of this month.
cancellation 99% intent
-
The app crashes every time I open settings.
bug report 96% intent
-
The API returns 502 errors since this morning.
technical 92% routing
-
Can we get a discount if we sign for three years?
sales 57% routing
-
Our whole checkout is down and we are losing orders right now!
urgent 95% priority
Side panels show recorded answers from the API. The middle one runs the live model.
Migrate from Jev
One line.
Same /v1/systemone, same question types, answers and errors. The official Jev SDKs work as they are: point them at layahost and use a layahost key.
.env
- TYPESAFE_BASE_URL=https://api.typesafe.ai + TYPESAFE_BASE_URL=https://layahost.com TYPESAFE_API_KEY=lh_…
Both SDKs read these variables. Nothing else in your code changes.
import os
from typesafe_sdk import TypeSafeClient
client = TypeSafeClient(
base_url="https://layahost.com",
api_key=os.environ["LAYAHOST_API_KEY"],
)
import { TypeSafeClient } from "@typesafe-ai/sdk";
const client = new TypeSafeClient({
baseURL: "https://layahost.com",
apiKey: process.env.LAYAHOST_API_KEY,
});
Use cases
What you can build.
Anything that ends in a decision: one of your options, with a probability you can act on.
Content moderation
Hold back insults, harassment and threats before they are published.
“You are all idiots and I hope you get fired.”
→ toxic 80%
Spam and scam filtering
Keep fake prizes, phishing and get-rich-quick offers out of your inbox and forms.
“Earn $5000 a day from home! Message me on WhatsApp.”
→ spam 90%
Support triage
Know what a customer wants before anyone opens the ticket.
“Please cancel my subscription at the end of this month.”
→ cancellation 99%
Ticket routing
Send every message to the right team, with your own list of departments.
“The API returns 502 errors since this morning.”
→ technical 92%
Priority and escalation
Page someone for outages, let the rest wait for business hours.
“Our whole checkout is down and we are losing orders right now!”
→ urgent 95%
Language detection
Route or reply in the customer’s language, across 35 languages.
“Dzień dobry, mam pytanie o fakturę.”
→ pl 92%
Answers you can branch on
Only the options you define, each with a probability. No parsing, no malformed output.
EU-hosted, text never stored
Servers in Finland. Your text is processed in memory and never written to disk or used for training.
No lock-in
The Jev API on the open Laya model, which you can also run yourself.
Examples are real answers from the API.
Custom models
Trained on your data.
For your own labels, such as product categories, internal teams or policy rules, we fine-tune a private Laya checkpoint on your examples and serve it on the same API.
-
01
Send labelled examples · a CSV of texts and the answers you expect
-
02
We train and calibrate · on GPUs, with an accuracy report on held-out examples
-
03
Call your own model · same endpoints and SDKs, private to your account
On the Laya project’s typed-decisions benchmark, fine-tuning lifted accuracy from 36% to 77%.
Pricing
Flat. Prepaid. Simple.
One price per decision, whatever the length of the text. No subscription, no seats.
$5
per million decisions
- ✓$1 welcome credit (200K decisions), no card needed
- ✓Prepaid credit from $10, no subscription
- ✓+10% credit from $100, +20% from $500
- ✓Rejected and failed requests are free
- ✓Invoice with your VAT ID
- ✓Credit never expires
Estimate your bill
layahost
flat per decision
Jev list price
$0.042 per million input tokens
At this length layahost costs . For texts this short, Jev’s per-token price is lower. Flat pricing wins above about tokens per request. Jev price from its public docs, September 2026, one question per request.
FAQ
Straight answers.
What counts as a decision? +
One answered question. A call to /v1/decide is one decision; a /v1/systemone request with three questions is three. Rejected or failed requests (4xx, 5xx) are free.
Is it really compatible with Jev? +
Yes for the API: the same /v1/systemone and /v1/models endpoints, request and response shapes, errors and request IDs, tested with the official Python and JavaScript SDKs. Jev model names such as jev-latest are accepted. The model behind it is different, so probabilities are not identical.
Is Laya as accurate as Jev? +
Not on every task. Laya is an open model, and independent tests put it behind Jev on some benchmarks. Try the demo or the playground on your own data before you switch production traffic, and check any thresholds your code relies on.
Is there a free tier? +
New accounts get $1 of credit (200K decisions) once they verify their email, no card needed. After that, credit is prepaid from $10, which buys 2M decisions, and it does not expire while your account is active. The demo on this page is free to try.
Where is my data processed? +
On our servers in Helsinki, Finland (EU). Text is processed in memory and never used for training. Logs keep verdicts and metadata for 7 days; request text only if you turn it on.
Can it replace the Perspective API? +
Yes. Google shuts Perspective down on 31 December 2026, and layahost implements the same comments:analyze call with TOXICITY, INSULT, THREAT and the other attributes. Change the host and the key; see the Perspective migration guide in the docs.
Does layahost work with images? +
No. Like Jev, it decides on text only. For images, send the text you already have about them, such as a caption, alt text or OCR output.
Can you train a model on our data? +
Yes. We fine-tune a private Laya checkpoint on your labelled examples and serve it on the same API under your own model name. Write to [email protected] with a description of your decisions and how much labelled data you have.
What are the limits? +
600 requests per minute per key by default, up to 32 questions per request and 32,000 characters of text. Need more? Write to [email protected].
Your first decision in five minutes.
Create an account, verify your email for $1 of free credit, copy a key, send one request.