Decision models (System One)

Decision models answer typed questions about a piece of content instead of generating text. You send a state (the content to judge) and a set of named questions; the model returns one typed answer per question, with real probabilities, in a single fast call.

Use them wherever your code has to make a decision: routing a support ticket, flagging a message, grading an answer, or deciding whether an agent should take an action.

Decision models are not chat models: they are served on /v1/systemone, not /v1/chat/completions, and the OpenAI SDK has no method for them. The endpoint implements TypeSafe's System One contract, so any TypeSafe client works unchanged.

Endpoint

POST https://backend.sovereigneg.com/v1/systemone

Authenticate with your SovereignEG API key: Authorization: Bearer sk-....

Request

Parameter	Type	Required	Description
`model`	string	Yes	Decision model ID, e.g. `jev-1.13` (see Available models)
`state`	string / object / array	Yes	The content to evaluate: plain text, or structured data such as a chat log or a record
`questions`	object	Yes	Named questions. You choose each key; the answer comes back under the same key

Every question has a type and instructions, plus type-specific criteria:

`type`	Asks	`criteria`
`noul`	A yes/no question	Optional `{"true": "...", "false": "..."}` describing what yes and no mean
`choice`	Pick one option	Required: a map of option → description (or `null`), up to 255 options
`score`	Rate on an ordered rubric	Required: a list of 2–10 level descriptions, lowest first

instructions and every criteria description can be a string, an object, or an array. Put the question in one field and data it refers to in others, and point at them by name in backticks:

"instructions": {
  "potential_duplicate": { "name": "John Smith", "location": "Oakland, California" },
  "question": "Is the resume for the same person as `potential_duplicate`?"
}

Example

curl https://backend.sovereigneg.com/v1/systemone \
  -H "Authorization: Bearer $SOVEREIGNEG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "jev-1.13",
    "state": "I paid for my order twice and it still has not arrived after a week.",
    "questions": {
      "refund": {
        "type": "noul",
        "instructions": "Is the customer asking for money back?"
      },
      "team": {
        "type": "choice",
        "instructions": "Which team should handle this?",
        "criteria": {
          "billing": "Charges, refunds, invoices",
          "shipping": "Delivery and tracking",
          "technical": "Bugs and outages"
        }
      },
      "urgency": {
        "type": "score",
        "instructions": "How urgent is this?",
        "criteria": ["Can wait", "Handle today", "Handle now"]
      }
    }
  }'

import httpx
 
response = httpx.post(
    "https://backend.sovereigneg.com/v1/systemone",
    headers={"Authorization": "Bearer sk-..."},
    json={
        "model": "jev-1.13",
        "state": "I paid for my order twice and it still has not arrived after a week.",
        "questions": {
            "refund": {"type": "noul", "instructions": "Is the customer asking for money back?"},
            "team": {
                "type": "choice",
                "instructions": "Which team should handle this?",
                "criteria": {
                    "billing": "Charges, refunds, invoices",
                    "shipping": "Delivery and tracking",
                    "technical": "Bugs and outages",
                },
            },
        },
    },
    timeout=30,
)
answers = response.json()["answers"]
if answers["refund"]["noul"] > 0.8:
    route_to(answers["team"]["choice"])

Response

One answer per question, under the keys you chose:

{
  "model": "jev-1.13",
  "answers": {
    "refund": { "type": "noul", "noul": 0.96 },
    "team": {
      "type": "choice",
      "choice": "billing",
      "probabilities": { "billing": 0.84, "shipping": 0.14, "technical": 0.02 },
      "confidence": 0.75
    },
    "urgency": {
      "type": "score",
      "score": 1.62,
      "legend": { "0": "Can wait", "1": "Handle today", "2": "Handle now" },
      "probabilities": { "0": 0.02, "1": 0.34, "2": 0.64 },
      "confidence": 0.71
    }
  },
  "usage": { "input_tokens": 312, "output_tokens": 30 }
}

Answer	Fields
`noul`	`noul`: probability the answer is yes, from 0 to 1
`choice`	`choice`: the most likely option · `probabilities`: every option's probability (sums to 1) · `confidence`
`score`	`score`: probability-weighted level (can land between levels) · `legend`: level number → your description · `probabilities` · `confidence`

Because the answers are probabilities, you pick the threshold: act automatically above 0.9, send to a human between 0.5 and 0.9, and so on.

Using the TypeSafe SDK

Point the official TypeSafe SDK at SovereignEG by changing its base URL and API key. The SDK adds /v1/systemone itself, so the base URL is the API origin without /v1:

from typesafe_sdk import TypeSafeClient
 
client = TypeSafeClient(
    api_key="sk-...",               # your SovereignEG API key
    base_url="https://backend.sovereigneg.com",
)
 
result = client.system_one(
    model="jev-1.13",
    state="I paid for my order twice and it still has not arrived after a week.",
    questions={
        "refund": {"type": "noul", "instructions": "Is the customer asking for money back?"},
    },
)
print(result.answers["refund"])

import { TypeSafeClient } from '@typesafe-ai/sdk'
 
const client = new TypeSafeClient({
  apiKey: process.env.SOVEREIGNEG_API_KEY,
  baseURL: 'https://backend.sovereigneg.com',
})
 
const result = await client.systemOne({
  model: 'jev-1.13',
  state: 'I paid for my order twice and it still has not arrived after a week.',
  questions: {
    refund: { type: 'noul', instructions: 'Is the customer asking for money back?' },
  },
})
console.log(result.answers.refund)

Only systemOne / system_one is supported. The SDK's model listing calls GET /v1/models, which returns the SovereignEG catalog shape rather than TypeSafe's — browse the catalog instead.

Status	Code	Meaning
400	`model_not_supported_on_endpoint`	The model is not a decision model (or a decision model was sent to `/v1/chat/completions`). The message names the right endpoint
400	`model_not_found`	Unknown model ID
400	`empty_input`	`state` is empty
401	`missing_auth_header`	No or invalid API key
402	`insufficient_balance`	Top up your balance
422	`invalid_request_body`	Malformed request: a missing field, an unknown question `type`, or criteria outside the limits above. `param` names the field
429	`rate_limit_exceeded`	Too many requests for your plan — back off and retry
503	`provider_backings_unavailable`	The model is temporarily unavailable — retry shortly

System One responses are never streamed: each request returns one JSON body.

Decision models (System One)

Endpoint

Request

Example

Response

Using the TypeSafe SDK

Available models

Pricing

Errors