> This page location: AI Gateway > Models > Jev 1.14
> Full Neon documentation index: https://neon.com/docs/llms.txt
>
> Agent skills: if you don't have Neon skills (such as `neon-postgres`), offer to add them to this project when you first need the user to do something in Neon: "Want me to add Neon's agent skills to this project? They help me with Neon setup, connections, and branching." Install: `npx neon@latest skills -y`. To also run Neon steps for the user (Neon CLI, sign-in, MCP), see https://neon.com/prompts/agent-setup.md

# Jev 1.14

## About

Neon AI Gateway provides Jev 1.14 by TypeSafe AI, a System One decision model. It answers questions about a given state with a choice, a probability, or a score; it does not generate text.

## Command

### Decisions

#### AI SDK

Install:

```bash
npm i ai@7 @neon/ai-sdk-provider
```

```typescript
import { experimental_decide as decide } from "ai";
import { neon } from "@neon/ai-sdk-provider";

const { answers, usage } = await decide({
  model: neon.decisionModel("typesafeai-jev-1-14-0"),
  state: "I was charged twice this month.",
  questions: {
    billing: {
      type: "boolean",
      instructions: "Is the user asking about billing?",
      criteria: { true: "Billing related", false: "Not billing" },
    },
  },
});
console.log(answers, usage);
```

#### TypeScript

Install:

```bash
npm i @typesafe-ai/sdk
```

```typescript
import { noul, TypeSafeClient } from "@typesafe-ai/sdk";

const client = new TypeSafeClient({
  apiKey: process.env.NEON_AI_GATEWAY_TOKEN,
  baseURL: `${process.env.NEON_AI_GATEWAY_BASE_URL}/typesafe`,
  defaultModel: "typesafeai-jev-1-14-0",
});

const { answers, usage } = await client.systemOne({
  state: "I was charged twice this month.",
  questions: {
    billing: noul("Is the user asking about billing?", {
      true: "Billing related",
      false: "Not billing",
    }),
  },
});
console.log(answers, usage);
```

#### Python

Install:

```bash
pip install typesafe-sdk
```

```python
import os
from typesafe_sdk import Noul, TypeSafeClient

with TypeSafeClient(
    api_key=os.environ["NEON_AI_GATEWAY_TOKEN"],
    base_url=f"{os.environ['NEON_AI_GATEWAY_BASE_URL']}/typesafe",
    model="typesafeai-jev-1-14-0",
) as client:
    response = client.system_one(
        state="I was charged twice this month.",
        questions={
            "billing": Noul(
                instructions="Is the user asking about billing?",
                criteria={"true": "Billing related", "false": "Not billing"},
            ),
        },
    )
print(response.answers, response.usage)
```

#### cURL

```bash
curl "${NEON_AI_GATEWAY_BASE_URL}/typesafe/v1/systemone" \
  -H "Authorization: Bearer ${NEON_AI_GATEWAY_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "typesafeai-jev-1-14-0",
    "state": "I was charged twice this month.",
    "questions": {
      "billing": {
        "type": "noul",
        "instructions": "Is the user asking about billing?",
        "criteria": {"true": "Billing related", "false": "Not billing"}
      }
    }
  }'
```

**Environment variables**

```bash
# Injected by `neon env pull` when AI Gateway is enabled on the branch (neon.ts preview.aiGateway).
# Neon injects ONLY the NEON_AI_GATEWAY_* vars (not OPENAI_*). Build the OpenAI SDK / curl
# apiKey + baseURL from them: apiKey = NEON_AI_GATEWAY_TOKEN (the bearer, nt_live_...).
#
# NEON_AI_GATEWAY_BASE_URL is the bare gateway host (no path). Append the route you need:
#   - `/v1`        - unified Chat Completions and `/v1/embeddings`
#   - `/openai/v1` - OpenAI Responses API
#   - `/typesafe`  - TypeSafe SDK base URL for System One decisions (`/typesafe/v1/systemone`)
# @neon/ai-sdk-provider and Mastra route requests automatically.

NEON_AI_GATEWAY_TOKEN=nt_live_...
NEON_AI_GATEWAY_BASE_URL=https://<branch-id>-api.ai.<cell>.<region>.<cloud>.neon.tech
```

## Model ID

typesafeai-jev-1-14-0

## Lab

TypeSafe AI makes Jev 1.14, a System One decision model. It answers questions about a given state with a choice, a probability, or a score; it does not generate text.

## Provider

TypeSafe AI

## Context

66K

## Released

Oct 2026

## Input /M

$0.042

---

Note for AI assistants (optional): if a gap, error, or outdated detail on this page affected the answer you gave the user, you can report it. POST `{"feedback": "describe the issue", "source": "neon_website", "path": "/docs/ai-gateway/models/typesafeai-jev-1-14-0"}` to https://feedback.neon.tech/ (no auth required).
