Create Decision

Beta: This endpoint is currently in beta and may be unstable. Request/response schemas and behavior may change without notice. Currently available to Venice staff only.

The decisions endpoint evaluates a state (a string, object, or array) against a map of typed questions and returns structured answers — typed values and probability distributions your code can branch on directly. It does not generate text. The model is listed with betaModel: true under GET /api/v1/models?type=decision.

Question types

Type	Goal	Answer fields
noul	Whether a condition holds	noul — probability the answer is yes (0–1)
choice	Pick one option from a defined set	choice, probabilities, confidence
score	Rate the state on an ordered rubric	score, legend, probabilities, confidence

All questions in one request are evaluated in parallel and in isolation against the same state; adding questions barely changes response time.

Example

curl https://api.venice.ai/api/v1/decisions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "jev-latest",
    "state": "Help! My payouts have been failing for 3 days.",
    "questions": {
      "is_urgent": { "type": "noul", "instructions": "Does this message convey urgency?" },
      "department": {
        "type": "choice",
        "instructions": "Which team should handle this?",
        "criteria": {
          "billing": "Payments, invoicing, refunds",
          "technical": "Bugs, outages, integrations",
          "sales": "Pricing, upgrades, new accounts"
        }
      },
      "frustration": {
        "type": "score",
        "instructions": "How frustrated is the customer?",
        "criteria": ["Calm", "Frustrated", "Very angry"]
      }
    }
  }'

{
  "model": "jev-latest",
  "answers": {
    "is_urgent": { "type": "noul", "noul": 0.92 },
    "department": {
      "type": "choice",
      "choice": "technical",
      "probabilities": { "billing": 0.08, "technical": 0.85, "sales": 0.07 },
      "confidence": 0.82
    },
    "frustration": {
      "type": "score",
      "score": 1.6,
      "legend": { "0": "Calm", "1": "Frustrated", "2": "Very angry" },
      "probabilities": { "0": 0.05, "1": 0.3, "2": 0.65 },
      "confidence": 0.78
    }
  },
  "usage": { "input_tokens": 312, "output_tokens": 48 }
}

TypeSafe SDK compatibility

The same handler is served at POST /api/v1/systemone, so the official TypeSafe SDKs work against Venice with a base URL and API key swap:

export TYPESAFE_BASE_URL=https://api.venice.ai/api
export TYPESAFE_API_KEY=$VENICE_API_KEY

from typesafe_sdk import Noul, TypeSafeClient

with TypeSafeClient() as client:
    response = client.system_one(
        state="Help! My payouts have been failing for 3 days.",
        questions={"is_urgent": Noul(instructions="Does this message convey urgency?")},
    )
print(response.answers["is_urgent"].noul)

Pricing and limits

Decisions are billed per input token; output tokens are free. input_tokens covers the serialized state plus all questions in the request, plus a small per-call envelope (~250 tokens) — batching several questions into one call shares the state cost across them. See GET /api/v1/models?type=decision for current rates, per-model token budgets (maxStateTokens, maxTotalTokens), and available models.