Get started

Quickstart

Create a key and make your first decision request.

1. Create a key

Sign in to the console and create a key under API keys. The key is shown once; store it somewhere safe and export it:

export PARSEC_API_KEY="..."

2. Ask a question

/v1/pick is the simplest call: a state, a list of options, and back comes the most likely option with a probability for each.

curl https://platform.parseclab.ai/v1/pick \
  -H "Authorization: Bearer $PARSEC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"state": "Which of these is a fruit?", "options": ["carrot", "apple"]}'
{
  "id": "req_…",
  "model": "utod-picker-12b-v1",
  "choice": "apple",
  "probs": {"carrot": 0.02, "apple": 0.98},
  "usage": {"input_tokens": 41, "cost_usd": 0.0},
  "truncated": false,
  "latency_ms": 180.4
}

3. Ask several typed questions at once

/v1/systemone takes several questions about the same state in one request. Each is a choice, a yes/no noul, or an ordinal score.

import os, requests

r = requests.post(
    "https://platform.parseclab.ai/v1/systemone",
    headers={"Authorization": f"Bearer {os.environ['PARSEC_API_KEY']}"},
    json={
        "state": "My card was stolen yesterday and I need it cancelled now.",
        "questions": {
            "intent": {"type": "choice",
                       "criteria": {"card_lost_or_stolen": "Card lost or stolen",
                                    "cancel_subscription": "Cancel a subscription"}},
            "urgent": {"type": "noul",
                       "criteria": {"true": "Needs action today", "false": "Can wait"}},
        },
    },
    timeout=60,
)
r.raise_for_status()
answers = r.json()["answers"]
print(answers["intent"]["choice"], answers["urgent"]["noul"])

The systemone reference has every field. To generate images instead, see Nano Banana.