← All models
TypeSafe: Jev 1.13NEW
typesafe/jev-1.13decisions
Jev is a structured decision model from TypeSafe, the first of its System One models. Send application state and typed questions, get back a typed answer with probabilities instead of generated text: noul (yes/no probability), choice (one of N with a full distribution), score (position on an ordered scale). Suited for routing, classification and gating agent tool calls where a fast, predictable answer matters more than prose. 32,000-token context.
Price request / response
Context
32K
Released
Sep 18, 2026
Parameters
staterequiredquestionsrequiredtypenoul · choice · scoreHow to use via API
import requests
r = requests.post(
"https://api.mixen.ai/v1/decisions",
headers={"Authorization": "Bearer mxn-..."},
json={
"model": "typesafe/jev-1.13",
"state": "Help! My payouts have been failing for 3 days.",
"questions": {
"is_urgent": {
"type": "noul",
"instructions": "Does this message convey urgency?",
"criteria": {"true": "Explicitly time-sensitive",
"false": "No urgency expressed"},
},
"department": {
"type": "choice",
"instructions": "Which team should handle this?",
"criteria": {"billing": "Payments, invoicing, refunds",
"technical": "Bugs, outages, integrations"},
},
},
},
)
answers = r.json()["answers"]
if answers["is_urgent"]["noul"] > 0.8 and answers["department"]["choice"] == "billing":
escalate_to_billing()