创建深度搜索 (巨贵,一次几十刀,慎用)

开发中

POST

/v1/responses

最后修改时间：2025-08-12 01:33:31

责任人：未设置

https://platform.openai.com/docs/api-reference/responses/create
部分OpenAI模型仅支持Response格式，例如o3-pro，codex-mini-latest

请求参数

Authorization

在 Header 添加参数

Authorization

，其值为在 Bearer 之后拼接 Token

示例：

Authorization: Bearer ********************

Header 参数

Body 参数application/json

示例

{
  "model": "o3-deep-research",
  "input": "Research the economic impact of semaglutide on global healthcare systems. Include specific figures, trends, statistics, and measurable outcomes. Prioritize reliable, up-to-date sources: peer-reviewed research, health organizations (e.g., WHO, CDC), regulatory agencies, or pharmaceutical earnings reports. Include inline citations and return all source metadata. Be analytical, avoid generalities, and ensure that each section supports data-backed reasoning that could inform healthcare policy or financial modeling.",
  "tools": [
    {
      "type": "web_search_preview"
    }
  ],
  "stream": true
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST '/v1/responses' \
--header 'Accept: application/json' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "o3-deep-research",
  "input": "Research the economic impact of semaglutide on global healthcare systems. Include specific figures, trends, statistics, and measurable outcomes. Prioritize reliable, up-to-date sources: peer-reviewed research, health organizations (e.g., WHO, CDC), regulatory agencies, or pharmaceutical earnings reports. Include inline citations and return all source metadata. Be analytical, avoid generalities, and ensure that each section supports data-backed reasoning that could inform healthcare policy or financial modeling.",
  "tools": [
    {
      "type": "web_search_preview"
    }
  ],
  "stream": true
}'

返回响应

🟢200OK

application/json

Body

示例

{
    "id": "chatcmpl-123",
    "object": "chat.completion",
    "created": 1677652288,
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "\n\nHello there, how may I assist you today?"
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 9,
        "completion_tokens": 12,
        "total_tokens": 21
    }
}

修改于 2025-08-12 01:33:31

创建模型响应 (控制思考长度)

创建网络搜索