# Laya

## Best for

Routing, classification, and guardrail decisions with calibrated probabilities

## When not to use

Generating text, chat, or tool use: it returns probabilities, never prose. It does not accept chat completions, Responses, or Messages requests, so coding harnesses cannot use it.

## Overview

Laya is ConvAI Innovations' non-autoregressive decision model. It does not generate text: it reads a state and answers typed questions in a single forward pass, each with calibrated probabilities. A `noul` question returns the probability that a statement is true, a `choice` question picks one of named options, and a `score` question places the state on a scale. It is designed for triage, routing, and guardrails, and answers many questions about the same input in one request.

`convaiinnovations/laya` (alias `laya`) sends each request to its English checkpoint, a 421M-parameter ModernBERT-large encoder with a decision head, or to its multilingual checkpoint for 100+ languages. Call it at `POST /v1/systemone`.

| | |
| --- | --- |
| API identifier | `convaiinnovations/laya` |
| Developer | ConvAI Innovations |
| Context window | 8,192 tokens |
| Supports | text |
| Status | Serving |

## Rates

The rate card is unavailable right now. Your existing rates are unchanged.

## Call it

Send a state and named questions to POST /v1/systemone. Each question is a noul, choice or score question, and each answer comes back with its probabilities. This model does not accept chat completions.

```bash
curl https://api.inference.boundless.network/v1/systemone \
  -H "Authorization: Bearer $BOUNDLESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "convaiinnovations/laya",
    "state": "Please refund my duplicate payment.",
    "questions": {
      "refund": {
        "type": "noul",
        "instructions": "Does the customer request a refund?"
      }
    }
  }'
```

Every model we serve is listed at [Models](https://inference.boundless.network/models); the rate card in full is on [Pricing](https://inference.boundless.network/docs/pricing).