跳转到主要内容
POST
/
api
/
v1
/
responses
创建 Codex 响应
curl --request POST \
  --url https://api.kie.ai/api/v1/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-5.1-codex",
  "input": [
    {
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "What is in this image?"
        },
        {
          "type": "input_image",
          "image_url": "https://file.aiquickdraw.com/custom-page/akr/section-images/1759055072437dqlsclj2.png"
        }
      ]
    }
  ],
  "tools": [
    {
      "type": "web_search"
    }
  ],
  "reasoning": {
    "effort": "high"
  }
}
'
event: response.output_text.delta
data: {"content_index":0,"delta":"Hello","item_id":"msg_xxx","output_index":1,"sequence_number":1,"type":"response.output_text.delta"}

event: response.output_text.delta
data: {"content_index":0,"delta":"!","item_id":"msg_xxx","output_index":1,"sequence_number":2,"type":"response.output_text.delta"}

event: response.output_text.delta
data: {"content_index":0,"delta":" How","item_id":"msg_xxx","output_index":1,"sequence_number":3,"type":"response.output_text.delta"}

event: response.output_text.delta
data: {"content_index":0,"delta":" can","item_id":"msg_xxx","output_index":1,"sequence_number":4,"type":"response.output_text.delta"}

event: response.output_text.delta
data: {"content_index":0,"delta":" I help you today?","item_id":"msg_xxx","output_index":1,"sequence_number":5,"type":"response.output_text.delta"}

event: response.completed
data: {"credits_consumed":0.49,"response":{"usage":{"input_tokens":4427,"input_tokens_details":{"cached_tokens":3584},"output_tokens":137,"output_tokens_details":{"reasoning_tokens":64},"total_tokens":4564}},"type":"response.completed"}

data: [DONE]

多模态输入

在单条消息中同时接收文本、图片和文件等多种内容。

推理力度控制

通过 reasoning.effort 从 minimal 到 xhigh 精细控制推理强度。

Tools 与联网搜索

支持 Web Search 或自定义函数调用（Function Calling）。

统一响应端点

通过统一的 /api/v1/responses 端点，指定 model 为 gpt-5-codex、gpt-5.1-codex、gpt-5.2-codex 或 gpt-5.3-codex 之一即可使用。

​
Tools 与 tool_choice

tools 数组用于开启 联网搜索 (Web Search) 或 函数调用 (Function Calling) 能力。
Web Search 与 Function Calling 互斥：
在同一个请求中只能选择其一。请勿在同一个 tools 数组中同时配置 {"type": "web_search"} 与 {"type": "function", ...}。
定义可被模型调用的业务函数，让模型在需要时主动调用：
{
  "tools": [
    {
      "type": "function",
      "name": "get_current_weather",
      "description": "Get the current weather in a given location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string",
            "description": "The city and state, e.g. San Francisco, CA"
          },
          "unit": {
            "type": "string",
            "enum": ["celsius", "fahrenheit"]
          }
        },
        "required": ["location", "unit"]
      }
    }
  ],
  "tool_choice": "auto"
}
当 tools 中配置了函数调用工具时，将 tool_choice 设置为 "auto"，允许模型根据需要自动决定是否调用函数；如果没有配置任何函数工具，请不要设置 tool_choice 字段。
event: response.output_text.delta
data: {"content_index":0,"delta":"Hello","item_id":"msg_xxx","output_index":1,"sequence_number":1,"type":"response.output_text.delta"}

event: response.output_text.delta
data: {"content_index":0,"delta":"!","item_id":"msg_xxx","output_index":1,"sequence_number":2,"type":"response.output_text.delta"}

event: response.output_text.delta
data: {"content_index":0,"delta":" How","item_id":"msg_xxx","output_index":1,"sequence_number":3,"type":"response.output_text.delta"}

event: response.output_text.delta
data: {"content_index":0,"delta":" can","item_id":"msg_xxx","output_index":1,"sequence_number":4,"type":"response.output_text.delta"}

event: response.output_text.delta
data: {"content_index":0,"delta":" I help you today?","item_id":"msg_xxx","output_index":1,"sequence_number":5,"type":"response.output_text.delta"}

event: response.completed
data: {"credits_consumed":0.49,"response":{"usage":{"input_tokens":4427,"input_tokens_details":{"cached_tokens":3584},"output_tokens":137,"output_tokens_details":{"reasoning_tokens":64},"total_tokens":4564}},"type":"response.completed"}

data: [DONE]

授权

​
Authorization
string
header
必填

所有 API 均需要通过 Bearer Token 进行身份验证。

获取 API Key：

  1. 访问 API Key 管理页面 获取您的 API Key

使用方法： 在请求头中添加： Authorization: Bearer YOUR_API_KEY

注意：

  • 请妥善保管您的 API Key，不要与他人分享
  • 如果您怀疑 API Key 已泄露，请立即在管理页面重置

请求体

application/json
​
model
enum<string>
必填

目标模型名称。可选值：gpt-5-codex、gpt-5.1-codex、gpt-5.2-codex、gpt-5.3-codex。

可用选项:
gpt-5-codex,
gpt-5.1-codex,
gpt-5.2-codex,
gpt-5.3-codex
示例:

"gpt-5.1-codex"

​
input
必填

input 可以是字符串类型。

​
reasoning
object

模型推理配置。

​
tools
object[]

可选，模型可以调用的工具数组。一次请求中应仅配置联网搜索或函数调用其一，请勿同时配置。

联网搜索工具配置。

​
tool_choice
string

工具选择行为。当在 tools 中配置了函数调用工具时，将其设置为 auto，让模型自动决定何时调用函数。

示例:

"auto"

响应

请求成功。仅支持以 Server-Sent Events (SSE) 形式返回的流式响应。

流式响应以 Server-Sent Events (SSE) 的形式返回，响应头为 Content-Type: text/event-stream。

普通返回

  • 文本增量事件：event: response.output_text.delta
    • data.delta：流中的增量文本内容
    • data.type：事件类型，固定为 response.output_text.delta
  • 完成事件：event: response.completed
    • data.response.usage：Token 用量信息，如 input_tokens、output_tokens 等

函数调用（Function Calling）

  • 函数参数增量事件：event: response.function_call_arguments.delta
    • data.delta：函数参数的增量字符串内容
    • data.type：事件类型，固定为 response.function_call_arguments.delta
  • 完成事件：event: response.completed
    • data.response.usage：Token 用量信息，如 input_tokens、output_tokens 等

最后一行 data: [DONE] 为流结束标记，表示不会再有新的事件发送。