---
title: Laya | Runware Docs
url: https://runware.ai/docs/models/laya
description: Open-weight System 1 model for low-latency typed decisions without free-form generation
---
# Laya

![Laya](https://assets.runware.ai/covers/laya.jpg)

Laya is an open-weight, non-autoregressive System 1 decision model. Its 421M-parameter English checkpoint pairs a ModernBERT-large encoder with a decision head that evaluates a shared text or JSON state against typed choice, score, and boolean questions in a single forward pass. It returns probabilities and confidence instead of prose, which suits ticket routing, moderation, guardrails, relevance scoring, and other low-latency automation.

- **Status**: compatible-only
- **ID**: `laya`
- **Context window**: 512 context
- **Creator**: 512 context
- **Release Date**: September 18, 2026
- **Capabilities**: Text to Text, Classification, Checkpoint

**Laya** is served through Runware's **compatible endpoints**, which take another provider's request format. Point the SDK you already use at Runware by changing the base URL and the API key, and set `model` to `runware:laya@1`.

Requests and responses keep the provider's format, so **its reference documents every parameter**.

| Endpoint | Format |
| --- | --- |
| `/v1/decisions` | [TypeSafe decisions](https://runware.ai/docs/tools/compatible-apis#decisions) |

### [Decisions](https://runware.ai/docs/models/laya#decisions)

**cURL**:

```bash
curl -X POST https://api.runware.ai/v1/decisions \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "runware:laya@1",
    "state": "I was charged twice. Please fix this ASAP.",
    "questions": {
      "category": {
        "type": "choice",
        "instructions": "What is this ticket about?",
        "criteria": {"billing": null, "technical": null, "other": null}
      }
    }
  }'
```

**Python**:

```python
from typesafe_sdk import Choice, TypeSafeClient

client = TypeSafeClient(
    api_key="your_runware_api_key",
    base_url="https://api.runware.ai",
)

response = client.system_one(
    model="runware:laya@1",
    state={"document": "I was charged twice. Please fix this ASAP."},
    questions={
        "category": Choice(
            instructions="What is this ticket about?",
            criteria={"billing": None, "technical": None, "other": None},
        ),
    },
)

print(response.answers["category"].choice)
```

**TypeScript**:

```typescript
import { choice, TypeSafeClient } from '@typesafe-ai/sdk';

const client = new TypeSafeClient({
  apiKey: 'your_runware_api_key',
  baseURL: 'https://api.runware.ai',
});

const response = await client.systemOne({
  model: 'runware:laya@1',
  state: { document: 'I was charged twice. Please fix this ASAP.' },
  questions: {
    category: choice('What is this ticket about?', {
      billing: null,
      technical: null,
      other: null,
    }),
  },
});

console.log(response.answers.category.choice);
```

[Compatible APIs](https://runware.ai/docs/tools/compatible-apis#decisions) covers the question types and the TypeSafe SDK setup, and the [TypeSafe docs](https://docs.typesafe.ai/) lists every parameter.

## Cost and speed

**Rates** (per 1M tokens)

- Input: `$0.02`

billed per token, so a request costs what the model produced · [How pricing works](https://runware.ai/docs/models-api/pricing)