POST /v1/systemone · Parsec docs

Several typed questions about one state, each answered with a probability for every option.

The API follows the Jev /v1/systemone contract: several questions per request, each a choice (2 to 512 labels), a noul (yes/no) or a score (ordinal levels), optionally over images.

Example

curl https://platform.parseclab.ai/v1/systemone \
  -H "Authorization: Bearer $PARSEC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "state": "My card was stolen yesterday and I need it cancelled now.",
    "questions": {
      "intent": {"type": "choice", "instructions": "Which intent is this?",
                 "criteria": {"card_lost_or_stolen": "Card lost or stolen",
                              "cancel_subscription": "Cancel a subscription",
                              "card_arrival": "Waiting for a new card"}},
      "urgent": {"type": "noul", "criteria": {"true": "Needs action today", "false": "Can wait"}},
      "severity": {"type": "score", "criteria": ["none", "minor", "major"]}
    }
  }'

import os, requests

r = requests.post(
    "https://platform.parseclab.ai/v1/systemone",
    headers={"Authorization": f"Bearer {os.environ['PARSEC_API_KEY']}"},
    json={
        "state": "...",
        "questions": {
            "action": {"type": "choice",
                       "criteria": {"refund": "Give the money back", "replace": "Ship a new unit"}},
        },
    },
    timeout=60,
)
r.raise_for_status()
a = r.json()["answers"]["action"]
print(a["choice"], a["probabilities"], a["confidence"])

Request body

Field	Type
`state`	string, object, or list	The thing being decided about: a string, a JSON object, or a list of `{"text": …}` / `{"image": …}` segments. Required.
`questions`	object	Question id → `{type, instructions, criteria}`. At least one.
`images`	list	Optional, up to 8, appended after the state. See images.
`model`	string	Optional; echoed back.

Question types

choice: criteria is label → description, 2 to 512 labels. Returns choice, the most likely label.
noul: criteria is {"true": …, "false": …}. Returns noul, the probability of yes.
score: criteria is a list of level descriptions, lowest first. Returns score, the most likely level, and a legend from level to description.

instructions is optional on every type: the question as you would ask it.

Context is up to 49,152 tokens; a longer state is refused with 413 state_too_long.

Response

{
  "id": "req_…",
  "model": "utod-picker-12b-v1",
  "answers": {
    "intent": {"type": "choice", "choice": "card_lost_or_stolen",
               "probabilities": {"card_lost_or_stolen": 0.94, "cancel_subscription": 0.05, "card_arrival": 0.01},
               "confidence": 0.91, "confidence_kind": "policy_max",
               "policy_max_confidence": 0.91, "entropy_confidence": 0.71, "latency_ms": 212.0},
    "urgent": {"type": "noul", "noul": 0.88, "probabilities": {"yes": 0.88, "no": 0.12}, …},
    "severity": {"type": "score", "score": 2.0, "probabilities": {"0": 0.03, "1": 0.31, "2": 0.66},
                 "legend": {"0": "none", "1": "minor", "2": "major"}, …}
  },
  "usage": {"input_tokens": 1236, "output_tokens": 0, "cost_usd": 0.000124},
  "latency_ms": 655.2
}

Probabilities sum to 1 across each question’s options.
confidence is the normalised maximum, (K * p_max - 1) / (K - 1) for K options and top probability p_max: 0 when every option is equally likely, 1 when one option has all the probability.
Every answered question counts as one decision against the account’s free allowance. Usage is billed once per request, on total input tokens. See billing.