# Laya — an open 421M decision model that replies in 33 milliseconds

> An Apache-2.0 decision model that returns typed answers with calibrated probabilities in about 33 milliseconds.

- Org: Convai Innovations
- Date: 2026-09-18
- Category: model, repo, tool
- Source: https://laya.convaiinnovations.com/
- Canonical page: https://ai-tldr.dev/releases/convai-laya/

## In short

Laya is an Apache-2.0 model that answers typed questions about text without generating text. The 421M English checkpoint returns calibrated probabilities in about 33 milliseconds, and a 322M multilingual checkpoint covers 100+ languages.

## What it is

Laya answers typed questions about a piece of text — pick one of these options, score this on a scale, is this true — and hands back probabilities instead of a written reply. Convai Innovations published three Apache-2.0 checkpoints: a 421M English model built on ModernBERT-large, a 322M multilingual one built on mmBERT-base, and a version fine-tuned on typed-decision workflows. The project presents itself as the open counterpart to TypeSafe's Jev.

## How it works

A single forward pass scores every question at once, with no token-by-token generation, which is where the 32.8 ms median comes from. Training used RLCD, where the reward is a strictly proper scoring rule — the model earns the most by reporting honest probabilities rather than confident-sounding ones. Three primitives cover the work: `choice` picks an option, `score` places a value on an ordinal scale, and `noul` returns P(true).

## Why it matters

Routing, triage and classification normally cost a full LLM call each. Laya does that work for a fraction of the latency under a licence you can ship, and the calibration training means the confidence number is something you can threshold on. The model card is blunt about the catch: zero-shot accuracy on typed-decisions is 0.362, so Laya is a fast base to fine-tune, not a drop-in decision engine.

## Who it's for

backend and agent engineers

## Try it

pip install laya

## Quick facts

- Maker: Convai Innovations
- License: Apache-2.0
- Checkpoints: laya (421M), laya-multilingual (322M), laya-typed-decisions (421M)
- Base models: ModernBERT-large and mmBERT-base
- Question types: choice, score, noul
- Install: pip install laya
- Availability: Weights on Hugging Face, code on GitHub

## FAQ

### How much does Laya cost?

Laya is free. All three checkpoints are published under Apache-2.0 on Hugging Face with the code on GitHub and the package on PyPI, so there is no per-token fee and no hosted API to sign up for. That is the main difference the project draws with TypeSafe's Jev, which is closed and billed per token.

### How does Laya compare to TypeSafe Jev?

On the typed-decisions benchmark Laya's fine-tuned checkpoint scores 0.766 against Jev 1.13.0's 0.727, with a Brier score of 0.062 that the card puts at 2.4x better than Jev. Median latency is 32.8 ms for Laya versus 236–276 ms for Jev, a roughly 7.8x gap the card credits to non-autoregressive scoring.

### Can Laya be used zero-shot?

No — Convai Innovations says so directly. Laya scores 0.362 on typed-decisions zero-shot and the multilingual checkpoint 0.352, close to chance. The 0.766 figure belongs to the checkpoint fine-tuned on that benchmark's own training split, and the card describes Laya as a fast base to specialise rather than a ready-made decision engine.

### Which languages does Laya handle?

The laya-multilingual checkpoint is built on mmBERT-base and covers more than 100 languages; Convai Innovations reports it working on 45 of the 51 languages it tested. The English-only base and typed-decisions checkpoints use ModernBERT-large instead, with 512 and 1024 tokens of context respectively.

## Links

- [Announcement](https://laya.convaiinnovations.com/)
- [GitHub Repo](https://github.com/NandhaKishorM/laya)
- [Model Card](https://huggingface.co/convaiinnovations/laya)
- [Typed-Decisions Card](https://huggingface.co/convaiinnovations/laya-typed-decisions)
- [PyPI Package](https://pypi.org/project/laya/)