# TypeSafe Jev 1.13 MCP and API - Typed decisions | FlyMy.AI

> TypeSafe Jev 1.13 makes fast, inexpensive typed decisions for classification, routing, triage and guardrails, with probabilities instead of prose.

Page: https://flymy.ai/mcp/models/typesafe-jev-1-13/

MCP / Models / Language models

# TypeSafe Jev 1.13 MCP: routing and triage with no API key

TypeSafe Jev 1.13 makes fast, inexpensive typed decisions for classification, routing, triage and guardrails, with probabilities instead of prose. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

[Use TypeSafe Jev 1.13](https://flymy.ai/mcp/models/typesafe-jev-1-13/#start) [Inputs and price](https://flymy.ai/mcp/models/typesafe-jev-1-13/#inputs)

No API key, $0.042 per 1M tokens, Typed decisions, FlyMy.AI, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use TypeSafe Jev 1.13 in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

```
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/typesafe-jev-1-13.md. Help me connect the FlyMy.AI MCP to this assistant, then run TypeSafe Jev 1.13 (flymyai/typesafe-jev-1_13) for this task: Route these support tickets to billing, technical or sales with TypeSafe Jev 1.13.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/typesafe-jev-1-13.md)

## What TypeSafe Jev 1.13 does

Give it text or JSON state and named, typed questions: Choice picks one of your options, Noul returns a yes probability from 0 to 1, and Score returns an expected level on an ordered scale. Route a ticket to billing, technical or sales, gate a refund, or label a lead hot, warm or cold. Review uncertain answers before acting on them.

## TypeSafe Jev 1.13 inputs

Every input of `flymyai/typesafe-jev-1_13` as its live schema lists them. Returns `answers` (object), `usage` (string).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/typesafe-jev-1-13/#input-state) `state` | string required Text or JSON context to evaluate |
| [#](https://flymy.ai/mcp/models/typesafe-jev-1-13/#input-questions) `questions` | string required JSON object of named Choice, Noul or Score questions |

## Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

**“Route these support tickets to billing, technical or sales with TypeSafe Jev 1.13.”** runs `flymyai/typesafe-jev-1_13`

**“Use TypeSafe Jev 1.13 to label each lead in my sheet hot, warm or cold.”** runs `flymyai/typesafe-jev-1_13`

**“Check each refund request with TypeSafe Jev 1.13: is it within our 30-day policy?”** runs `flymyai/typesafe-jev-1_13`

## TypeSafe Jev 1.13 price

$0.042 per 1M input tokens, output tokens free. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

[See usage pricing →](https://flymy.ai/pricing/)

## Call TypeSafe Jev 1.13 from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

### From an agent, through the MCP

The agent calls `get_model_schema`, then `run_model` with:

```
{
  "endpoint_id": "flymyai/typesafe-jev-1_13",
  "input": {
    "state": "I was charged twice for my order.",
    "questions": "{\n  \"team\": {\n    \"type\": \"choice\",\n    \"instructions\": \"Which team should handle this ticket?\",\n    \"criteria\": {\n      \"billing\": null,\n      \"technical\": null,\n      \"sales\": null\n    }\n  },\n  \"refund_requested\": {\n    \"type\": \"noul\",\n    \"instructions\": \"Does the customer explicitly request a refund?\"\n  },\n  \"urgency\": {\n    \"type\": \"score\",\n    \"instructions\": \"How urgent is this ticket?\",\n    \"criteria\": [\n      \"Routine request\",\n      \"Payment problem\",\n      \"Critical outage\"\n    ]\n  }\n}"
  }
}
```

### From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. The answer is a `prediction_id`; read the result at `https://api.flymy.ai/api/v1/flymyai/typesafe-jev-1_13/predict/async/result/?request_id=<prediction_id>`.

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/typesafe-jev-1_13/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'state=I was charged twice for my order.' \
  -F 'questions={
  "team": {
    "type": "choice",
    "instructions": "Which team should handle this ticket?",
    "criteria": {
      "billing": null,
      "technical": null,
      "sales": null
    }
  },
  "refund_requested": {
    "type": "noul",
    "instructions": "Does the customer explicitly request a refund?"
  },
  "urgency": {
    "type": "score",
    "instructions": "How urgent is this ticket?",
    "criteria": [
      "Routine request",
      "Payment problem",
      "Critical outage"
    ]
  }
}'
```

## Questions about TypeSafe Jev 1.13

**Do I need a separate account for TypeSafe Jev 1.13?**

No. TypeSafe Jev 1.13 is FlyMy.AI's own model: sign in to FlyMy.AI once and each run is billed to your balance.

**How much does TypeSafe Jev 1.13 cost?**

$0.042 per 1M input tokens, output tokens free. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-09.

**How do I use TypeSafe Jev 1.13 in Claude Code, Codex or Cursor?**

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Route these support tickets to billing, technical or sales with TypeSafe Jev 1.13." Your agent reads the inputs with get_model_schema and runs flymyai/typesafe-jev-1_13 with run_model.

**What does TypeSafe Jev 1.13 need as input?**

TypeSafe Jev 1.13 requires state and questions; it also takes 0 optional inputs, each listed on this page with its allowed values and default.

**Can I call TypeSafe Jev 1.13 from my own code?**

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/typesafe-jev-1_13/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

## More language models models

Chat and reasoning models for code, documents and agents, plus typed decisions for routing and triage.

### Kimi K3.1 Pro

Moonshot's flagship for agentic coding: tool calls, images and a 1M-token context.

Chat model / $2.00 / $10.00 per 1M tokens

Link: https://flymy.ai/mcp/models/kimi-k3-1-pro/

### DeepSeek V4.1 Flash

DeepSeek's quick reasoning model with tool calls, images and a priority tier.

Chat model / $0.30 / $1.20 per 1M tokens

Link: https://flymy.ai/mcp/models/deepseek-v4-1-flash/

### Grok 4.7

xAI's reasoning model with a 500K-token window for codebases and long contracts.

Chat model / $2.00 / $6.00 per 1M tokens

Link: https://flymy.ai/mcp/models/grok-4-7/

### Gemini 3 Flash

The Gemini 3 generation at Flash speed, with thinking you can turn down.

Chat model / $0.50 / $3.00 per 1M tokens

Link: https://flymy.ai/mcp/models/google-gemini-3-flash-preview/

### Gemini 3.1 Flash Lite

The cheapest Gemini text model for extraction, labels and short drafts at scale.

Chat model / $0.25 / $1.50 per 1M tokens

Link: https://flymy.ai/mcp/models/google-gemini-31-flash-lite-preview/

### Gemini 3.1 Pro

Gemini 3.1 Pro for the hard problems: long documents, code and careful reasoning.

Chat model / $2.00 / $12.00 per 1M tokens

Link: https://flymy.ai/mcp/models/google-gemini-31-pro-preview/

## Go to the source

[TypeSafe Jev 1.13 in the playground →](https://app.flymy.ai/models/flymyai/typesafe-jev-1_13), [TypeSafe Jev 1.13 guide in the docs →](https://docs.flymy.ai/guides/typesafe-jev), [Model endpoints in the docs →](https://docs.flymy.ai/api/models-endpoints), [Language models guide →](https://docs.flymy.ai/guides/use-llms), [Every model on FlyMy.AI →](https://flymy.ai/mcp/models/), [Every MCP in the catalog →](https://flymy.ai/mcp/#catalog), [Usage pricing →](https://flymy.ai/pricing/)

From the FlyMy.AI model catalog of 2026-11-09: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.

---

For agents: the FlyMyAI operating guide (sign up, connect, run models, tools and agents) is https://flymy.ai/skill.md, and https://flymy.ai/llms.txt lists the other pages and the documentation.