Typed answers, not text

Decisions

Get typed, probabilistic decisions instead of generated text with the OpenAI-compatible /v1/decisions endpoint.

Get startedRead the docs
POST /v1/decisions
Help! My payouts have been failing for 3 days.
  1. 1

    department = billing

    93%
  2. 2

    is_urgent = true

    88%
  3. 3

    impact = Critical

    71%
01

Typed output

Choice, predicate or score.

02

Probabilities

Calibrated confidence per answer.

03

No parsing

Branch on values directly.

04

Text or images

Decide on either input.

Built for

  • Ticket routing

    Send to the right team

  • Triage

    Flag urgent requests

  • Scoring

    Rate passages or leads

Ask a typed question
terminal
1curl https://api.llmgateway.io/v1/decisions \2  -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \3  -H "Content-Type: application/json" \4  -d '{5    "model": "gpt-6-luna-decisions",6    "input": "My payouts have been failing for 3 days.",7    "questions": [8      {9        "type": "predicate",10        "name": "is_urgent",11        "instructions": "Does this convey urgency?"12      }13    ]14  }'
Read docs

More in models & modalities

All features

Speech Generation

Text to natural speech

Transcription

Speech to text with word timestamps

Realtime API

Speech-to-speech over WebSockets

Start using Decisions today

One API key. Every model. Live in minutes.

Start buildingBrowse models