Decisions
用 OpenAI Decisions 以结构化答案回答分类问题，以及 TypeSafe System One。
POST /v1/decisions 提供 OpenAI Decisions，使用与对话相同的 Key：发送输入和带类型的问题，返回的不是生成的文本，而是带概率的结构化答案。支持的模型是 openai/gpt-6-luna。
| 端点 | POST https://api.ohmygpt.com/v1/decisions |
| 鉴权 | Authorization: Bearer $OHMYGPT_API_KEY |
| 模型 | openai/gpt-6-luna |
| 响应 | 非流式（一个 JSON 响应） |
curl https://api.ohmygpt.com/v1/decisions \
-H "Authorization: Bearer $OHMYGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-6-luna",
"input": [{
"type": "message",
"role": "user",
"content": [{"type": "input_text", "text": "I was charged twice for my subscription this month."}]
}],
"questions": [{
"type": "choice",
"name": "department",
"instructions": "Which department should handle this?",
"choices": [
{"value": "billing", "description": "Payments and refunds."},
{"value": "support", "description": "General support."}
]
}]
}'{
"model": "gpt-6-luna",
"answers": [
{
"type": "choice",
"name": "department",
"choice": "billing",
"probabilities": [
{ "value": "billing", "probability": 1.0 },
{ "value": "support", "probability": 0.0 }
],
"confidence": 1.0
}
],
"usage": {
"input_tokens": 124,
"input_tokens_details": { "cached_tokens": 0, "cache_write_tokens": 0 },
"output_tokens": 0,
"output_tokens_details": { "reasoning_tokens": 0 },
"total_tokens": 124
}
}请求和响应与 OpenAI 的 Decisions 格式完全一致，所以 OpenAI 的示例只要换掉 Base URL、Key 和模型 ID 就能直接运行。Decisions 按输入 token 计费，和所有端点一样，每个响应的费用都在 X-Cost-Credits 响应头中。
TypeSafe System One
POST /v1/systemone 提供 TypeSafe System One，模型为 typesafe/jev-latest。请求和响应遵循 TypeSafe 的 System One 格式。可以发送 JSON，也可以发送 multipart/form-data：第一部分名为 request，内容是 JSON，之后每张图片各占一部分。以 TypeSafe-Danger-Zone- 开头的请求头会原样传给模型。