Use Jev for criteria-based model routing

curl -sS https://router.flatkey.ai/api/alpha/decisions \
  -H "Authorization: Bearer $FLATKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "typesafe/jev-1.13",
  "state": "Research the three main approaches to RAG evaluation in 2025, cite peer-reviewed papers and recent industry blogs, then write a Python notebook that benchmarks faithfulness and context precision on our 200-question internal set. Flag any claim you cannot source.",
  "questions": {
    "model_tier": {
      "type": "choice",
      "instructions": "Which model tier should handle this request? Prefer the cheapest tier that can still do the job well.",
      "criteria": {
        "flash": "Short, low-stakes answers: lookups, rewrites, formatting, simple Q&A with little reasoning",
        "balanced": "Moderate work: light coding, short summarization, single-tool calls, everyday analysis",
        "frontier": "Hard work: multi-step reasoning, research with citations, complex code, safety-sensitive or irreversible actions"
      }
    },
    "complexity": {
      "type": "score",
      "instructions": "How much reasoning, planning or domain depth does this request need?",
      "criteria": [
        "low",
        "medium",
        "high"
      ]
    },
    "needs_tools": {
      "type": "noul",
      "instructions": "The request needs tool use, multi-step planning, or retrieval with citations to succeed."
    },
    "safety_sensitive": {
      "type": "noul",
      "instructions": "A wrong answer could cause real harm, irreversible change, or a high-stakes decision."
    }
  }
}'

// Node.js 18+ (built-in fetch). Run: FLATKEY_API_KEY=... node jev.mjs
const body = {
  "model": "typesafe/jev-1.13",
  "state": "Research the three main approaches to RAG evaluation in 2025, cite peer-reviewed papers and recent industry blogs, then write a Python notebook that benchmarks faithfulness and context precision on our 200-question internal set. Flag any claim you cannot source.",
  "questions": {
    "model_tier": {
      "type": "choice",
      "instructions": "Which model tier should handle this request? Prefer the cheapest tier that can still do the job well.",
      "criteria": {
        "flash": "Short, low-stakes answers: lookups, rewrites, formatting, simple Q&A with little reasoning",
        "balanced": "Moderate work: light coding, short summarization, single-tool calls, everyday analysis",
        "frontier": "Hard work: multi-step reasoning, research with citations, complex code, safety-sensitive or irreversible actions"
      }
    },
    "complexity": {
      "type": "score",
      "instructions": "How much reasoning, planning or domain depth does this request need?",
      "criteria": [
        "low",
        "medium",
        "high"
      ]
    },
    "needs_tools": {
      "type": "noul",
      "instructions": "The request needs tool use, multi-step planning, or retrieval with citations to succeed."
    },
    "safety_sensitive": {
      "type": "noul",
      "instructions": "A wrong answer could cause real harm, irreversible change, or a high-stakes decision."
    }
  }
};

const res = await fetch("https://router.flatkey.ai/api/alpha/decisions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.FLATKEY_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify(body),
});
if (!res.ok) throw new Error(`Jev request failed: ${res.status} ${await res.text()}`);
const { answers, usage } = await res.json();
console.log(JSON.stringify(answers, null, 2), usage);

# Python 3.8+ (pip install requests). Run: FLATKEY_API_KEY=... python jev.py
import json, os, requests

body = json.loads(r"""{
  "model": "typesafe/jev-1.13",
  "state": "Research the three main approaches to RAG evaluation in 2025, cite peer-reviewed papers and recent industry blogs, then write a Python notebook that benchmarks faithfulness and context precision on our 200-question internal set. Flag any claim you cannot source.",
  "questions": {
    "model_tier": {
      "type": "choice",
      "instructions": "Which model tier should handle this request? Prefer the cheapest tier that can still do the job well.",
      "criteria": {
        "flash": "Short, low-stakes answers: lookups, rewrites, formatting, simple Q&A with little reasoning",
        "balanced": "Moderate work: light coding, short summarization, single-tool calls, everyday analysis",
        "frontier": "Hard work: multi-step reasoning, research with citations, complex code, safety-sensitive or irreversible actions"
      }
    },
    "complexity": {
      "type": "score",
      "instructions": "How much reasoning, planning or domain depth does this request need?",
      "criteria": [
        "low",
        "medium",
        "high"
      ]
    },
    "needs_tools": {
      "type": "noul",
      "instructions": "The request needs tool use, multi-step planning, or retrieval with citations to succeed."
    },
    "safety_sensitive": {
      "type": "noul",
      "instructions": "A wrong answer could cause real harm, irreversible change, or a high-stakes decision."
    }
  }
}""")

res = requests.post(
    "https://router.flatkey.ai/api/alpha/decisions",
    headers={"Authorization": f"Bearer {os.environ['FLATKEY_API_KEY']}"},
    json=body,
    timeout=60,
)
res.raise_for_status()
data = res.json()
print(json.dumps(data["answers"], indent=2), data.get("usage"))

No Flatkey key yet? Get one for Jev 1.13 →