curl https://api.openai.com/v1/decisions \
    -H "Authorization: Bearer $(llm keys get openai)" \
    -H "Content-Type: application/json" \
    --data '
  {
    "model": "gpt-6-luna",
    "input": [{
      "role": "user",
      "content": [
        {"type": "input_text", "text": "I am angry about the new product feature"}
      ]
    }],
    "questions": [{
      "type": "predicate",
      "name": "complaint",
      "instructions": "Is this a complaint?"
    }, {
      "type": "predicate",
      "name": "compliment",
      "instructions": "Is this a compliment?"
    }]
  }'

Returned:

  {
    "model": "gpt-6-luna",
    "answers": [
      {
        "type": "predicate",
        "name": "complaint",
        "probability": 0.91
      },
      {
        "type": "predicate",
        "name": "compliment",
        "probability": 0.06
      }
    ],
    "usage": {
      "input_tokens": 310,
      "input_tokens_details": {
        "cached_tokens": 0,
        "cache_write_tokens": 0
      },
      "output_tokens": 0,
      "output_tokens_details": {
        "reasoning_tokens": 0
      },
      "total_tokens": 310
    }
  }

That https://api.openai.com/v1/decisions endpoint is notable because usually when OpenAI define an endpoint like that it ends up as a defecto standard for other providers.

(I turned this all into a new llm plugin: https://github.com/simonw/llm-openai-decisions)