# Core.Today AI API — Decision Models (TypeSafe Jev, OpenAI Decisions)

> Models that answer typed questions with probabilities instead of chatting, for classification, routing, guardrails, scoring and re-ranking. Served by the Core.Today LLM gateway with the same API key and credits, on each model's own endpoint.

Source: https://console.core.today/docs/decision
This file: https://console.core.today/llms/decision.txt
All models: https://console.core.today/llms.txt

## API Usage (decision models, not chat)

Base URL: https://api.core.today
Auth header: Authorization: Bearer YOUR_API_KEY
- TypeSafe Jev: POST https://api.core.today/llm/typesafe/v1/systemone
- OpenAI Decisions: POST https://api.core.today/llm/openai/v1/decisions
These are not chat completions: there is no messages field and no streaming, and each model has its own schema. Each model's exact endpoint is listed below.

## Models (2)

### GPT-6 Luna Decisions — `gpt-6-luna-decisions`

OpenAI's Decisions API on GPT-6 Luna, through the gateway. Not chat: send an input (text, or user messages with text and base64 images) plus typed questions - predicate (probability a condition is true), choice (one of your options with per-option probabilities) or score (a position on your ordered levels) - and get one typed answer per question with confidence. Roughly 10x faster than a Responses call and billed on input tokens only.

- Provider: OpenAI
- Credits: 0.19 (per 1K input tokens (output free))
- Speed: fast / Quality: high
- Context: 1,050,000 tokens / Max output: 0 tokens
- Token pricing (per 1M): input 185.8 credits; output tokens are not charged (input-only billing)
- Endpoint: POST /llm/openai/v1/decisions
- Required params: model (string), input (string | message[]), questions (array)
- Example input:
```json
{
  "model": "gpt-6-luna-decisions",
  "input": "I was charged twice for my order and support has not replied for 3 days.",
  "questions": [
    {
      "type": "predicate",
      "name": "is_urgent",
      "instructions": "Does this message convey urgency?"
    },
    {
      "type": "choice",
      "name": "department",
      "instructions": "Which department should handle this complaint?",
      "choices": [
        {
          "value": "billing",
          "description": "Payments, invoices, and refunds."
        },
        {
          "value": "technical",
          "description": "Problems using the product."
        },
        {
          "value": "other",
          "description": "Requests outside these categories."
        }
      ]
    },
    {
      "type": "score",
      "name": "severity",
      "instructions": "How severe is this issue for the customer?",
      "levels": [
        {
          "label": "Minor",
          "description": "Inconvenience only."
        },
        {
          "label": "Significant",
          "description": "Money or access affected."
        },
        {
          "label": "Critical",
          "description": "Blocked with no workaround."
        }
      ]
    }
  ]
}
```
- Full docs: https://console.core.today/docs/models/gpt-6-luna-decisions

### Jev 1.13 — `jev-1.13.0`

TypeSafe's System One model over the direct TypeSafe API. Jev does not chat or generate text: you send a state (text, object or array) plus a set of typed questions and get a structured answer for each - a yes/no probability (noul), a choice with per-option probabilities, or a score on a rubric you define - with calibrated confidence. Built for classification, routing, scoring, guardrails and re-ranking at low cost; billed on input tokens only.

- Provider: TypeSafe
- Credits: 0.08 (per 1K input tokens (output free))
- Speed: fast / Quality: high
- Context: 64,000 tokens / Max output: 0 tokens
- Token pricing (per 1M): input 78.036 credits; output tokens are not charged (input-only billing)
- Endpoint: POST /llm/typesafe/v1/systemone
- Required params: model (string), state (string | object | array), questions (object)
- Example input:
```json
{
  "model": "jev-latest",
  "state": "Help! My payouts have been failing for 3 days.",
  "questions": {
    "is_urgent": {
      "type": "noul",
      "instructions": "Does this convey urgency?"
    },
    "department": {
      "type": "choice",
      "instructions": "Which team should handle this?",
      "criteria": {
        "billing": "Payments, invoicing, refunds",
        "technical": null
      }
    },
    "frustration": {
      "type": "score",
      "instructions": "How frustrated is the customer?",
      "criteria": [
        "Calm",
        "Frustrated",
        "Very angry"
      ]
    }
  }
}
```
- Full docs: https://console.core.today/docs/models/jev-1.13.0